From 5c209a3b1c6183cba632cf5cd8ec84644b9292ec Mon Sep 17 00:00:00 2001 From: "mingjiang.li" Date: Mon, 3 Mar 2025 17:46:16 +0800 Subject: [PATCH 1/3] update model template to unify formats Signed-off-by: mingjiang.li --- docs/README_TEMPLATE.md | 47 ++++++++++++++++++++++++++++++----------- 1 file changed, 35 insertions(+), 12 deletions(-) diff --git a/docs/README_TEMPLATE.md b/docs/README_TEMPLATE.md index 345a38ed..7531a916 100644 --- a/docs/README_TEMPLATE.md +++ b/docs/README_TEMPLATE.md @@ -1,18 +1,40 @@ -# MODEL_NAME +# MODEL_NAME (IGIE/IxRT/vLLM/TGI/TRT-LLM/IxFormer) -## Description +## Model Description A brief introduction about this model. +A brief introduction about this model. +A brief introduction about this model. + +## Supported Environments + +| Iluvatar GPU | IXUCA | +|--------------|-------| +| MR-V50 | 4.1.2 | +| MR-V100 | 4.2.0 | + +## Model Preparation + +### Prepare Datasets -## Setup +```bash +python3 dataset/coco/download_coco.py +``` + +### Prepare Pre-trained Weights (for LLM) -### Install (remove this step if not necessary) +Go to huggingface. -### Download (remove this step if not necessary) +### Install Dependencies + +```bash +pip install -r requirements.txt +python3 setup.py install +``` -### Model Conversion (remove this step if not necessary) +### Model Conversion -## Inference +## Model Inference ### FP16 @@ -26,12 +48,13 @@ bash test_fp16.sh bash test_int8.sh ``` -## Results (leave empty for testing team to complete) +## Model Results -Model | BatchSize | Precision | FPS | ACC -------|-----------|-----------|-----|---- -MODEL_NAME | | | | +| Model | GPU | Precision | Performance | +|------------|------------|-----------|-------------| +| MODEL_NAME | MR-V100 x1 | | | -## Referenece (remove if not necessary) +## References - [refer-page-name](https://refer-links) +- [Paper](Paper_link) -- Gitee From 6d2590c9caf3e6fd5126c0cf90af537d94efb51c Mon Sep 17 00:00:00 2001 From: "mingjiang.li" Date: Tue, 4 Mar 2025 11:33:14 +0800 Subject: [PATCH 2/3] update and unify readme title and chapter --- docs/README_TEMPLATE.md | 4 +-- .../conformer/igie/README.md | 12 +++---- .../conformer/ixrt/README.md | 10 +++--- .../transformer_asr/ixrt/README.md | 12 +++---- .../cv/classification/alexnet/igie/README.md | 12 +++---- .../cv/classification/alexnet/ixrt/README.md | 12 +++---- models/cv/classification/clip/igie/README.md | 12 +++---- .../conformer_base/igie/README.md | 14 ++++---- .../convnext_base/igie/README.md | 12 +++---- .../convnext_base/ixrt/README.md | 12 +++---- .../classification/convnext_s/igie/README.md | 14 ++++---- .../convnext_small/igie/README.md | 12 +++---- .../convnext_small/ixrt/README.md | 12 +++---- .../cspdarknet53/igie/README.md | 14 ++++---- .../cspdarknet53/ixrt/README.md | 14 ++++---- .../classification/cspresnet50/igie/README.md | 14 ++++---- .../classification/cspresnet50/ixrt/README.md | 12 +++---- .../classification/deit_tiny/igie/README.md | 14 ++++---- .../classification/deit_tiny/ixrt/README.md | 14 ++++---- .../classification/densenet121/igie/README.md | 12 +++---- .../classification/densenet121/ixrt/README.md | 12 +++---- .../classification/densenet161/igie/README.md | 12 +++---- .../classification/densenet161/ixrt/README.md | 12 +++---- .../classification/densenet169/igie/README.md | 12 +++---- .../classification/densenet169/ixrt/README.md | 12 +++---- .../classification/densenet201/igie/README.md | 12 +++---- .../classification/densenet201/ixrt/README.md | 12 +++---- .../efficientnet_b0/igie/README.md | 12 +++---- .../efficientnet_b0/ixrt/README.md | 12 +++---- .../efficientnet_b1/igie/README.md | 12 +++---- .../efficientnet_b1/ixrt/README.md | 12 +++---- .../efficientnet_b2/igie/README.md | 12 +++---- .../efficientnet_b2/ixrt/README.md | 12 +++---- .../efficientnet_b3/igie/README.md | 12 +++---- .../efficientnet_b3/ixrt/README.md | 12 +++---- .../efficientnet_b4/igie/README.md | 12 +++---- .../efficientnet_v2/igie/README.md | 12 +++---- .../efficientnet_v2/ixrt/README.md | 12 +++---- .../efficientnet_v2_s/igie/README.md | 12 +++---- .../efficientnet_v2_s/ixrt/README.md | 12 +++---- .../efficientnetv2_rw_t/igie/README.md | 12 +++---- .../efficientnetv2_rw_t/ixrt/README.md | 12 +++---- .../classification/googlenet/igie/README.md | 12 +++---- .../classification/googlenet/ixrt/README.md | 12 +++---- .../classification/hrnet_w18/igie/README.md | 14 ++++---- .../classification/hrnet_w18/ixrt/README.md | 12 +++---- .../inception_resnet_v2/ixrt/README.md | 12 +++---- .../inception_v3/igie/README.md | 12 +++---- .../inception_v3/ixrt/README.md | 12 +++---- .../mlp_mixer_base/igie/README.md | 14 ++++---- .../classification/mnasnet0_5/igie/README.md | 12 +++---- .../classification/mnasnet0_75/igie/README.md | 12 +++---- .../mobilenet_v2/igie/README.md | 12 +++---- .../mobilenet_v2/ixrt/README.md | 12 +++---- .../mobilenet_v3/igie/README.md | 12 +++---- .../mobilenet_v3/ixrt/README.md | 12 +++---- .../mobilenet_v3_large/igie/README.md | 12 +++---- .../classification/mvitv2_base/igie/README.md | 14 ++++---- .../regnet_x_16gf/igie/README.md | 12 +++---- .../regnet_x_1_6gf/igie/README.md | 12 +++---- .../regnet_y_1_6gf/igie/README.md | 12 +++---- .../cv/classification/repvgg/igie/README.md | 14 ++++---- .../cv/classification/repvgg/ixrt/README.md | 12 +++---- .../classification/res2net50/igie/README.md | 14 ++++---- .../classification/res2net50/ixrt/README.md | 12 +++---- .../classification/resnest50/igie/README.md | 14 ++++---- .../classification/resnet101/igie/README.md | 12 +++---- .../classification/resnet101/ixrt/README.md | 12 +++---- .../classification/resnet152/igie/README.md | 12 +++---- .../cv/classification/resnet18/igie/README.md | 12 +++---- .../cv/classification/resnet18/ixrt/README.md | 12 +++---- .../cv/classification/resnet34/ixrt/README.md | 12 +++---- .../cv/classification/resnet50/igie/README.md | 12 +++---- .../cv/classification/resnet50/ixrt/README.md | 12 +++---- .../classification/resnetv1d50/igie/README.md | 14 ++++---- .../classification/resnetv1d50/ixrt/README.md | 12 +++---- .../resnext101_32x8d/igie/README.md | 12 +++---- .../resnext101_64x4d/igie/README.md | 12 +++---- .../resnext50_32x4d/igie/README.md | 12 +++---- .../resnext50_32x4d/ixrt/README.md | 12 +++---- .../classification/seresnet50/igie/README.md | 14 ++++---- .../shufflenet_v1/ixrt/README.md | 12 +++---- .../shufflenetv2_x0_5/igie/README.md | 12 +++---- .../shufflenetv2_x1_0/igie/README.md | 12 +++---- .../shufflenetv2_x1_5/igie/README.md | 12 +++---- .../shufflenetv2_x2_0/igie/README.md | 12 +++---- .../squeezenet_v1_0/igie/README.md | 12 +++---- .../squeezenet_v1_0/ixrt/README.md | 12 +++---- .../squeezenet_v1_1/ixrt/README.md | 12 +++---- .../cv/classification/svt_base/igie/README.md | 14 ++++---- .../swin_transformer/igie/README.md | 12 +++---- .../swin_transformer_large/ixrt/README.md | 12 +++---- models/cv/classification/vgg11/igie/README.md | 12 +++---- models/cv/classification/vgg16/igie/README.md | 12 +++---- models/cv/classification/vgg16/ixrt/README.md | 12 +++---- .../wide_resnet101/igie/README.md | 12 +++---- .../wide_resnet50/igie/README.md | 12 +++---- .../wide_resnet50/ixrt/README.md | 12 +++---- .../face_recognition/facenet/ixrt/README.md | 12 +++---- .../mask_rcnn/ixrt/README.md | 8 ++--- .../solov1/ixrt/README.md | 12 +++---- .../deepsort/igie/README.md | 12 +++---- .../fastreid/igie/README.md | 12 +++---- .../repnet/igie/README.md | 14 ++++---- .../cv/object_detection/atss/igie/README.md | 14 ++++---- .../object_detection/centernet/igie/README.md | 14 ++++---- .../object_detection/centernet/ixrt/README.md | 14 ++++---- .../cv/object_detection/detr/ixrt/README.md | 12 +++---- .../cv/object_detection/fcos/igie/README.md | 14 ++++---- .../cv/object_detection/fcos/ixrt/README.md | 12 +++---- .../object_detection/foveabox/igie/README.md | 14 ++++---- .../object_detection/foveabox/ixrt/README.md | 14 ++++---- .../cv/object_detection/fsaf/igie/README.md | 14 ++++---- .../cv/object_detection/fsaf/ixrt/README.md | 14 ++++---- .../cv/object_detection/hrnet/igie/README.md | 14 ++++---- .../cv/object_detection/hrnet/ixrt/README.md | 14 ++++---- models/cv/object_detection/paa/igie/README.md | 14 ++++---- .../retinaface/igie/README.md | 14 ++++---- .../retinaface/ixrt/README.md | 14 ++++---- .../object_detection/retinanet/igie/README.md | 14 ++++---- .../cv/object_detection/rtmdet/igie/README.md | 14 ++++---- .../cv/object_detection/sabl/igie/README.md | 14 ++++---- .../object_detection/yolov10/igie/README.md | 14 ++++---- .../object_detection/yolov11/igie/README.md | 14 ++++---- .../cv/object_detection/yolov3/igie/README.md | 12 +++---- .../cv/object_detection/yolov3/ixrt/README.md | 12 +++---- .../cv/object_detection/yolov4/igie/README.md | 14 ++++---- .../cv/object_detection/yolov4/ixrt/README.md | 14 ++++---- .../cv/object_detection/yolov5/igie/README.md | 12 +++---- .../cv/object_detection/yolov5/ixrt/README.md | 12 +++---- .../object_detection/yolov5s/ixrt/README.md | 12 +++---- .../cv/object_detection/yolov6/igie/README.md | 14 ++++---- .../cv/object_detection/yolov6/ixrt/README.md | 14 ++++---- .../cv/object_detection/yolov7/igie/README.md | 14 ++++---- .../cv/object_detection/yolov7/ixrt/README.md | 12 +++---- .../cv/object_detection/yolov8/igie/README.md | 12 +++---- .../cv/object_detection/yolov8/ixrt/README.md | 12 +++---- .../cv/object_detection/yolov9/igie/README.md | 14 ++++---- .../cv/object_detection/yolox/igie/README.md | 14 ++++---- .../cv/object_detection/yolox/ixrt/README.md | 14 ++++---- models/cv/ocr/kie_layoutxlm/igie/README.md | 10 +++--- models/cv/ocr/svtr/igie/README.md | 10 +++--- .../pose_estimation/hrnetpose/igie/README.md | 14 ++++---- .../lightweight_openpose/ixrt/README.md | 33 +++++++++++-------- .../cv/pose_estimation/rtmpose/igie/README.md | 14 ++++---- .../cv/pose_estimation/rtmpose/ixrt/README.md | 10 +++--- .../stable-diffusion/README.md | 10 +++--- .../chameleon_7b/vllm/README.md | 10 +++--- .../clip/ixformer/README.md | 8 ++--- .../fuyu_8b/vllm/README.md | 10 +++--- .../intern_vl/vllm/README.md | 10 +++--- .../llava/vllm/README.md | 10 +++--- .../llava_next_video_7b/vllm/README.md | 10 +++--- .../minicpm_v_2/vllm/README.md | 10 +++--- models/nlp/llm/baichuan2-7b/vllm/README.md | 10 +++--- models/nlp/llm/chatglm3-6b-32k/vllm/README.md | 10 +++--- models/nlp/llm/chatglm3-6b/vllm/README.md | 8 ++--- .../vllm/README.md | 10 +++--- .../vllm/README.md | 12 +++---- .../vllm/README.md | 12 +++---- .../vllm/README.md | 12 +++---- .../vllm/README.md | 12 +++---- .../vllm/README.md | 12 +++---- models/nlp/llm/llama2-13b/trtllm/README.md | 12 +++---- models/nlp/llm/llama2-70b/trtllm/README.md | 10 +++--- models/nlp/llm/llama2-7b/trtllm/README.md | 10 +++--- models/nlp/llm/llama2-7b/vllm/README.md | 10 +++--- models/nlp/llm/llama3-70b/vllm/README.md | 10 +++--- models/nlp/llm/qwen-7b/vllm/README.md | 10 +++--- models/nlp/llm/qwen1.5-14b/vllm/README.md | 12 +++---- models/nlp/llm/qwen1.5-32b/vllm/README.md | 10 +++--- models/nlp/llm/qwen1.5-72b/vllm/README.md | 12 +++---- models/nlp/llm/qwen1.5-7b/tgi/README.md | 12 +++---- models/nlp/llm/qwen1.5-7b/vllm/README.md | 12 +++---- models/nlp/llm/qwen2-72b/vllm/README.md | 10 +++--- models/nlp/llm/qwen2-7b/vllm/README.md | 10 +++--- models/nlp/llm/stablelm/vllm/README.md | 12 +++---- models/nlp/plm/albert/ixrt/README.md | 12 +++---- models/nlp/plm/bert_base_ner/igie/README.md | 12 +++---- models/nlp/plm/bert_base_squad/igie/README.md | 12 +++---- models/nlp/plm/bert_base_squad/ixrt/README.md | 8 ++--- .../nlp/plm/bert_large_squad/igie/README.md | 12 +++---- .../nlp/plm/bert_large_squad/ixrt/README.md | 6 ++-- models/nlp/plm/deberta/ixrt/README.md | 12 +++---- models/nlp/plm/roberta/ixrt/README.md | 12 +++---- models/nlp/plm/roformer/ixrt/README.md | 12 +++---- models/nlp/plm/videobert/ixrt/README.md | 12 +++---- .../wide_and_deep/ixrt/README.md | 12 +++---- 188 files changed, 1148 insertions(+), 1145 deletions(-) diff --git a/docs/README_TEMPLATE.md b/docs/README_TEMPLATE.md index 7531a916..04daa0d9 100644 --- a/docs/README_TEMPLATE.md +++ b/docs/README_TEMPLATE.md @@ -15,14 +15,12 @@ A brief introduction about this model. ## Model Preparation -### Prepare Datasets +### Prepare Resources ```bash python3 dataset/coco/download_coco.py ``` -### Prepare Pre-trained Weights (for LLM) - Go to huggingface. ### Install Dependencies diff --git a/models/audio/speech_recognition/conformer/igie/README.md b/models/audio/speech_recognition/conformer/igie/README.md index 47bafe82..54255769 100644 --- a/models/audio/speech_recognition/conformer/igie/README.md +++ b/models/audio/speech_recognition/conformer/igie/README.md @@ -1,15 +1,15 @@ # Conformer -## Description +## Model Description Conformer is a speech recognition model proposed by Google in 2020. It combines the advantages of CNN and Transformer. CNN efficiently extracts local features, while Transformer is more effective in capturing long sequence dependencies. Conformer applies convolution to the Encoder layer of Transformer, enhancing the performance of Transformer in the ASR (Automatic Speech Recognition) domain. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash pip3 install -r requirements.txt @@ -17,7 +17,7 @@ cd ctc_decoder/swig && bash setup.sh cd ../../ ``` -### Download +### Prepare Resources Pretrained model: @@ -47,7 +47,7 @@ onnxsim encoder_bs24_seq384_static.onnx encoder_bs24_seq384_static_opt.onnx python3 alter_onnx.py --batch_size 24 --path encoder_bs24_seq384_static_opt.onnx ``` -## Inference +## Model Inference ```bash # Need to unzip aishell to the current directory. For details, refer to data.list @@ -63,7 +63,7 @@ bash scripts/infer_conformer_fp16_accuracy.sh bash scripts/infer_conformer_fp16_performance.sh ``` -## Results +## Model Results | Model | BatchSize | Precision | FPS | ACC | |-----------|-----------|-----------|----------|-------| diff --git a/models/audio/speech_recognition/conformer/ixrt/README.md b/models/audio/speech_recognition/conformer/ixrt/README.md index ed858421..bea43b9b 100644 --- a/models/audio/speech_recognition/conformer/ixrt/README.md +++ b/models/audio/speech_recognition/conformer/ixrt/README.md @@ -1,12 +1,12 @@ # Conformer -## Description +## Model Description Conformer is a speech recognition model proposed by Google in 2020. It combines the advantages of CNN and Transformer. CNN efficiently extracts local features, while Transformer is more effective in capturing long sequence dependencies. Conformer applies convolution to the Encoder layer of Transformer, enhancing the performance of Transformer in the ASR (Automatic Speech Recognition) domain. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash # Install libGL @@ -18,7 +18,7 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -50,7 +50,7 @@ bash scripts/infer_conformer_fp16_accuracy.sh bash scripts/infer_conformer_fp16_performance.sh ``` -## Results +## Model Results | Model | BatchSize | Precision | QPS | CER | | --------- | --------- | --------- | ------- | ------ | diff --git a/models/audio/speech_recognition/transformer_asr/ixrt/README.md b/models/audio/speech_recognition/transformer_asr/ixrt/README.md index 601362a2..f7e9f24b 100644 --- a/models/audio/speech_recognition/transformer_asr/ixrt/README.md +++ b/models/audio/speech_recognition/transformer_asr/ixrt/README.md @@ -1,20 +1,20 @@ # Transformer ASR（BeamSearch） -## Description +## Model Description Beam search allows us to exert control over the output of text generation. This is useful because we sometimes know exactly what we want inside the output. For example, in a Neural Machine Translation task, we might know which words must be included in the final translation with a dictionary lookup. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -51,7 +51,7 @@ ln -s /PATH/to/data_aishell /home/data/speechbrain/aishell/ cp results/transformer/8886/*.csv /home/data/speechbrain/aishell/csv_data ``` -## Inference +## Model Inference ### Build faster kernels @@ -78,7 +78,7 @@ python3 builder.py \ python3 inference.py hparams/train_ASR_transformer.yaml --data_folder=/home/data/speechbrain/aishell --engine_path transformer.engine ``` -## Results +## Model Results | Model | BatchSize | Precision | QPS | CER | |-----------------|-----------|-----------|-------|------| diff --git a/models/cv/classification/alexnet/igie/README.md b/models/cv/classification/alexnet/igie/README.md index 0720e0ff..686248aa 100644 --- a/models/cv/classification/alexnet/igie/README.md +++ b/models/cv/classification/alexnet/igie/README.md @@ -1,6 +1,6 @@ # AlexNet -## Description +## Model Description AlexNet, developed by Alex Krizhevsky, Ilya Sutskever, and Geoffrey Hinton, is a groundbreaking convolutional neural network (CNN) architecture that achieved remarkable success in the 2012 ImageNet Large Scale Visual Recognition @@ -8,15 +8,15 @@ Challenge (ILSVRC). This neural network comprises eight layers, incorporating fi connected layers. The architecture employs the Rectified Linear Unit (ReLU) activation function to introduce non-linearity, allowing the model to learn complex features from input images. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -28,7 +28,7 @@ Dataset: to download the validation dat python3 export.py --weight alexnet-owt-7be5be79.pth --output alexnet.onnx ``` -## Inference +## Model Inference ```bash export DATASETS_DIR=/Path/to/imagenet_val/ @@ -52,7 +52,7 @@ bash scripts/infer_alexnet_int8_accuracy.sh bash scripts/infer_alexnet_int8_performance.sh ``` -## Results +## Model Results | Model | BatchSize | Precision | FPS | Top-1(%) | Top-5(%) | |---------|-----------|-----------|----------|----------|----------| diff --git a/models/cv/classification/alexnet/ixrt/README.md b/models/cv/classification/alexnet/ixrt/README.md index a111e406..8284d2ab 100644 --- a/models/cv/classification/alexnet/ixrt/README.md +++ b/models/cv/classification/alexnet/ixrt/README.md @@ -1,13 +1,13 @@ # AlexNet -## Description +## Model Description AlexNet is a classic convolutional neural network architecture. It consists of convolutions, max pooling and dense layers as the basic building blocks. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash # Install libGL @@ -19,7 +19,7 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -32,7 +32,7 @@ mkdir checkpoints python3 export_onnx.py --origin_model /path/to/alexnet-owt-7be5be79.pth --output_model checkpoints/alexnet.onnx ``` -## Inference +## Model Inference ```bash export PROJ_DIR=./ @@ -60,7 +60,7 @@ bash scripts/infer_alexnet_int8_accuracy.sh bash scripts/infer_alexnet_int8_performance.sh ``` -## Results +## Model Results | Model | BatchSize | Precision | FPS | Top-1(%) | Top-5(%) | |---------|-----------|-----------|----------|----------|----------| diff --git a/models/cv/classification/clip/igie/README.md b/models/cv/classification/clip/igie/README.md index 1f864a06..57cc7042 100644 --- a/models/cv/classification/clip/igie/README.md +++ b/models/cv/classification/clip/igie/README.md @@ -1,18 +1,18 @@ # CLIP -## Description +## Model Description CLIP (Contrastive Language-Image Pre-Training) is a neural network trained on a variety of (image, text) pairs. It can be instructed in natural language to predict the most relevant text snippet, given an image, without directly optimizing for the task, similarly to the zero-shot capabilities of GPT-2 and 3. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -32,7 +32,7 @@ python3 export.py --output clip.onnx onnxsim clip.onnx clip_opt.onnx ``` -## Inference +## Model Inference ```bash export DATASETS_DIR=/Path/to/imagenet_val/ @@ -47,7 +47,7 @@ bash scripts/infer_clip_fp16_accuracy.sh bash scripts/infer_clip_fp16_performance.sh ``` -## Results +## Model Results Model |BatchSize |Precision |FPS |Top-1(%) |Top-5(%) ------|-----------|----------|----------|----------|-------- diff --git a/models/cv/classification/conformer_base/igie/README.md b/models/cv/classification/conformer_base/igie/README.md index d79d899d..a3b1f5bd 100644 --- a/models/cv/classification/conformer_base/igie/README.md +++ b/models/cv/classification/conformer_base/igie/README.md @@ -1,18 +1,18 @@ # Conformer Base -## Description +## Model Description Conformer is a novel network architecture that addresses the limitations of conventional Convolutional Neural Networks (CNNs) and visual transformers. Rooted in the Feature Coupling Unit (FCU), Conformer efficiently fuses local features and global representations at different resolutions through interactive processes. Its concurrent architecture ensures the maximal retention of both local and global features. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -28,7 +28,7 @@ onnxsim conformer_base.onnx conformer_base_opt.onnx ``` -## Inference +## Model Inference ```bash export DATASETS_DIR=/Path/to/imagenet_val/ @@ -43,12 +43,12 @@ bash scripts/infer_conformer_base_fp16_accuracy.sh bash scripts/infer_conformer_base_fp16_performance.sh ``` -## Results +## Model Results Model |BatchSize |Precision |FPS |Top-1(%) |Top-5(%) ----------|-----------|----------|----------|----------|-------- Conformer Base | 32 | FP16 | 428.73 | 83.83 | 96.59 -## Reference +## References - [Conformer](https://github.com/pengzhiliang/Conformer) diff --git a/models/cv/classification/convnext_base/igie/README.md b/models/cv/classification/convnext_base/igie/README.md index 37ca8560..b0b6812a 100644 --- a/models/cv/classification/convnext_base/igie/README.md +++ b/models/cv/classification/convnext_base/igie/README.md @@ -1,18 +1,18 @@ # ConvNext Base -## Description +## Model Description The ConvNeXt Base model represents a significant stride in the evolution of convolutional neural networks (CNNs), introduced by researchers at Facebook AI Research (FAIR) and UC Berkeley. It is part of the ConvNeXt family, which challenges the dominance of Vision Transformers (ViTs) in the realm of visual recognition tasks. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -24,7 +24,7 @@ Dataset: to download the validation dat python3 export.py --weight convnext_base-6075fbad.pth --output convnext_base.onnx ``` -## Inference +## Model Inference ```bash export DATASETS_DIR=/Path/to/imagenet_val/ @@ -39,7 +39,7 @@ bash scripts/infer_convnext_base_fp16_accuracy.sh bash scripts/infer_convnext_base_fp16_performance.sh ``` -## Results +## Model Results | Model | BatchSize | Precision | FPS | Top-1(%) | Top-5(%) | | -------------- | --------- | --------- | ------- | -------- | -------- | diff --git a/models/cv/classification/convnext_base/ixrt/README.md b/models/cv/classification/convnext_base/ixrt/README.md index 0e4da2e6..4dc0adab 100644 --- a/models/cv/classification/convnext_base/ixrt/README.md +++ b/models/cv/classification/convnext_base/ixrt/README.md @@ -1,12 +1,12 @@ # ConvNeXt Base -## Description +## Model Description The ConvNeXt Base model represents a significant stride in the evolution of convolutional neural networks (CNNs), introduced by researchers at Facebook AI Research (FAIR) and UC Berkeley. It is part of the ConvNeXt family, which challenges the dominance of Vision Transformers (ViTs) in the realm of visual recognition tasks. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash # Install libGL @@ -24,7 +24,7 @@ pip3 install tqdm pip3 install cuda-python ``` -### Download +### Prepare Resources Pretrained model: @@ -36,7 +36,7 @@ Dataset: to download the validation dat python3 export.py --weight convnext_base-6075fbad.pth --output convnext_base.onnx ``` -## Inference +## Model Inference ```bash export DATASETS_DIR=/Path/to/imagenet_val/ @@ -52,7 +52,7 @@ bash scripts/infer_convnext_base_fp16_accuracy.sh bash scripts/infer_convnext_base_fp16_performance.sh ``` -## Results +## Model Results | Model | BatchSize | Precision | FPS | Top-1(%) | Top-5(%) | | -------------- | --------- | --------- | ------- | -------- | -------- | diff --git a/models/cv/classification/convnext_s/igie/README.md b/models/cv/classification/convnext_s/igie/README.md index 9d133a66..8bedb4b1 100644 --- a/models/cv/classification/convnext_s/igie/README.md +++ b/models/cv/classification/convnext_s/igie/README.md @@ -1,12 +1,12 @@ # ConvNext-S (OpenMMLab) -## Description +## Model Description ConvNeXt-S is a small-sized model in the ConvNeXt family, designed to balance performance and computational complexity. With 50.22M parameters and 8.69G FLOPs, it achieves 83.13% Top-1 accuracy on ImageNet-1k. Modernized from traditional ConvNets, ConvNeXt-S incorporates features such as large convolutional kernels (7x7), LayerNorm, and GELU activations, making it highly efficient and scalable. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash # Install libGL @@ -18,7 +18,7 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -38,7 +38,7 @@ onnxsim convnext_s.onnx convnext_s_opt.onnx ``` -## Inference +## Model Inference ```bash export DATASETS_DIR=/Path/to/imagenet_val/ @@ -53,12 +53,12 @@ bash scripts/infer_convnext_s_fp16_accuracy.sh bash scripts/infer_convnext_s_fp16_performance.sh ``` -## Results +## Model Results | Model | BatchSize | Precision | FPS | Top-1(%) | Top-5(%) | | ------------ | --------- | --------- | -------- | -------- | -------- | | ConvNext-S | 32 | FP16 | 728.32 | 82.786 | 96.415 | -## Reference +## References ConvNext-S: diff --git a/models/cv/classification/convnext_small/igie/README.md b/models/cv/classification/convnext_small/igie/README.md index 9d1711a9..44713c53 100644 --- a/models/cv/classification/convnext_small/igie/README.md +++ b/models/cv/classification/convnext_small/igie/README.md @@ -1,18 +1,18 @@ # ConvNeXt Small -## Description +## Model Description The ConvNeXt Small model represents a significant stride in the evolution of convolutional neural networks (CNNs), introduced by researchers at Facebook AI Research (FAIR) and UC Berkeley. It is part of the ConvNeXt family, which challenges the dominance of Vision Transformers (ViTs) in the realm of visual recognition tasks. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -24,7 +24,7 @@ Dataset: to download the validation dat python3 export.py --weight convnext_small-0c510722.pth --output convnext_small.onnx ``` -## Inference +## Model Inference ```bash export DATASETS_DIR=/Path/to/imagenet_val/ @@ -39,7 +39,7 @@ bash scripts/infer_convnext_small_fp16_accuracy.sh bash scripts/infer_convnext_small_fp16_performance.sh ``` -## Results +## Model Results | Model | BatchSize | Precision | FPS | Top-1(%) | Top-5(%) | | -------------- | --------- | --------- | ------- | -------- | -------- | diff --git a/models/cv/classification/convnext_small/ixrt/README.md b/models/cv/classification/convnext_small/ixrt/README.md index 70d1e0a8..ff84232f 100644 --- a/models/cv/classification/convnext_small/ixrt/README.md +++ b/models/cv/classification/convnext_small/ixrt/README.md @@ -1,12 +1,12 @@ # ConvNeXt Small -## Description +## Model Description The ConvNeXt Small model represents a significant stride in the evolution of convolutional neural networks (CNNs), introduced by researchers at Facebook AI Research (FAIR) and UC Berkeley. It is part of the ConvNeXt family, which challenges the dominance of Vision Transformers (ViTs) in the realm of visual recognition tasks. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash # Install libGL @@ -18,7 +18,7 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -30,7 +30,7 @@ Dataset: to download the validation dat python3 export.py --weight convnext_small-0c510722.pth --output convnext_small.onnx ``` -## Inference +## Model Inference ```bash export DATASETS_DIR=/Path/to/imagenet_val/ @@ -46,7 +46,7 @@ bash scripts/infer_convnext_small_fp16_accuracy.sh bash scripts/infer_convnext_small_fp16_performance.sh ``` -## Results +## Model Results | Model | BatchSize | Precision | FPS | Top-1(%) | Top-5(%) | | -------------- | --------- | --------- | ------- | -------- | -------- | diff --git a/models/cv/classification/cspdarknet53/igie/README.md b/models/cv/classification/cspdarknet53/igie/README.md index ca15f15a..f409b0a0 100644 --- a/models/cv/classification/cspdarknet53/igie/README.md +++ b/models/cv/classification/cspdarknet53/igie/README.md @@ -1,12 +1,12 @@ # CSPDarkNet53 -## Description +## Model Description CSPDarkNet53 is an enhanced convolutional neural network architecture that reduces redundant computations by integrating cross-stage partial network features and truncating gradient flow, thereby maintaining high accuracy while lowering computational costs. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash # Install libGL @@ -18,7 +18,7 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -41,7 +41,7 @@ onnxsim cspdarknet53.onnx cspdarknet53_opt.onnx ``` -## Inference +## Model Inference ```bash export DATASETS_DIR=/Path/to/imagenet_val/ @@ -56,12 +56,12 @@ bash scripts/infer_cspdarknet53_fp16_accuracy.sh bash scripts/infer_cspdarknet53_fp16_performance.sh ``` -## Results +## Model Results | Model | BatchSize | Precision | FPS | Top-1(%) | Top-5(%) | | ------------ | --------- | --------- | -------- | -------- | -------- | | CSPDarkNet53 | 32 | FP16 | 3214.387 | 79.063 | 94.492 | -## Reference +## References CSPDarkNet53: diff --git a/models/cv/classification/cspdarknet53/ixrt/README.md b/models/cv/classification/cspdarknet53/ixrt/README.md index 40addd41..b0dbdd06 100644 --- a/models/cv/classification/cspdarknet53/ixrt/README.md +++ b/models/cv/classification/cspdarknet53/ixrt/README.md @@ -1,12 +1,12 @@ # CSPDarkNet53 -## Description +## Model Description CSPDarkNet53 is an enhanced convolutional neural network architecture that reduces redundant computations by integrating cross-stage partial network features and truncating gradient flow, thereby maintaining high accuracy while lowering computational costs. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash # Install libGL @@ -18,7 +18,7 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -42,7 +42,7 @@ onnxsim cspdarknet5.onnx checkpoints/cspdarknet53_sim.onnx ``` -## Inference +## Model Inference ```bash export DATASETS_DIR=/Path/to/imagenet_val/ @@ -68,13 +68,13 @@ bash scripts/infer_cspdarknet53_int8_accuracy.sh bash scripts/infer_cspdarknet53_int8_performance.sh ``` -## Results +## Model Results | Model | BatchSize | Precision | FPS | Top-1(%) | Top-5(%) | | ------------ | --------- | --------- | -------- | -------- | -------- | | CSPDarkNet53 | 32 | FP16 | 3282.318 | 79.09 | 94.52 | | CSPDarkNet53 | 32 | INT8 | 6335.86 | 75.49 | 92.66 | -## Reference +## References CSPDarkNet53: diff --git a/models/cv/classification/cspresnet50/igie/README.md b/models/cv/classification/cspresnet50/igie/README.md index 46341ba6..3d5c62f2 100644 --- a/models/cv/classification/cspresnet50/igie/README.md +++ b/models/cv/classification/cspresnet50/igie/README.md @@ -1,12 +1,12 @@ # CSPResNet50 -## Description +## Model Description CSPResNet50 combines the strengths of ResNet50 and CSPNet (Cross-Stage Partial Network) to create a more efficient and high-performing architecture. By splitting and fusing feature maps across stages, CSPResNet50 reduces redundant computations, optimizes gradient flow, and enhances feature representation. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash # Install libGL @@ -18,7 +18,7 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -38,7 +38,7 @@ onnxsim cspresnet50.onnx cspresnet50_opt.onnx ``` -## Inference +## Model Inference ```bash export DATASETS_DIR=/Path/to/imagenet_val/ @@ -53,12 +53,12 @@ bash scripts/infer_cspresnet50_fp16_accuracy.sh bash scripts/infer_cspresnet50_fp16_performance.sh ``` -## Results +## Model Results | Model | BatchSize | Precision | FPS | Top-1(%) | Top-5(%) | | ------------ | --------- | --------- | -------- | -------- | -------- | | CSPResNet50 | 32 | FP16 | 4553.80 | 78.507 | 94.142 | -## Reference +## References CSPResNet50: diff --git a/models/cv/classification/cspresnet50/ixrt/README.md b/models/cv/classification/cspresnet50/ixrt/README.md index fa054551..abc1094d 100644 --- a/models/cv/classification/cspresnet50/ixrt/README.md +++ b/models/cv/classification/cspresnet50/ixrt/README.md @@ -1,13 +1,13 @@ # CSPResNet50 -## Description +## Model Description Neural networks have enabled state-of-the-art approaches to achieve incredible results on computer vision tasks such as object detection. CSPResNet50 is the one of best models. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash # Install libGL @@ -19,7 +19,7 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Dataset: to download the validation dataset. @@ -35,7 +35,7 @@ python3 export_onnx.py \ --output_model ./checkpoints/cspresnet50.onnx ``` -## Inference +## Model Inference ```bash export PROJ_DIR=./ @@ -64,7 +64,7 @@ bash scripts/infer_cspresnet50_int8_accuracy.sh bash scripts/infer_cspresnet50_int8_performance.sh ``` -## Results +## Model Results Model |BatchSize |Precision |FPS |Top-1(%) |Top-5(%) ------------|-----------|----------|---------|----------|-------- diff --git a/models/cv/classification/deit_tiny/igie/README.md b/models/cv/classification/deit_tiny/igie/README.md index 89cb1aa4..0e705a42 100644 --- a/models/cv/classification/deit_tiny/igie/README.md +++ b/models/cv/classification/deit_tiny/igie/README.md @@ -1,12 +1,12 @@ # DeiT-tiny -## Description +## Model Description DeiT Tiny is a lightweight vision transformer designed for data-efficient learning. It achieves rapid training and high accuracy on small datasets through innovative attention distillation methods, while maintaining the simplicity and efficiency of the model. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash # Install libGL @@ -18,7 +18,7 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -38,7 +38,7 @@ onnxsim deit_tiny.onnx deit_tiny_opt.onnx ``` -## Inference +## Model Inference ```bash export DATASETS_DIR=/Path/to/imagenet_val/ @@ -53,12 +53,12 @@ bash scripts/infer_deit_tiny_fp16_accuracy.sh bash scripts/infer_deit_tin_fp16_performance.sh ``` -## Results +## Model Results | Model | BatchSize | Precision | FPS | Top-1(%) | Top-5(%) | | --------- | --------- | --------- | -------- | -------- | -------- | | DeiT-tiny | 32 | FP16 | 2172.771 | 74.334 | 92.175 | -## Reference +## References Deit_tiny: diff --git a/models/cv/classification/deit_tiny/ixrt/README.md b/models/cv/classification/deit_tiny/ixrt/README.md index 42710f0f..813acbfb 100644 --- a/models/cv/classification/deit_tiny/ixrt/README.md +++ b/models/cv/classification/deit_tiny/ixrt/README.md @@ -1,12 +1,12 @@ # DeiT-tiny -## Description +## Model Description DeiT Tiny is a lightweight vision transformer designed for data-efficient learning. It achieves rapid training and high accuracy on small datasets through innovative attention distillation methods, while maintaining the simplicity and efficiency of the model. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash # Install libGL @@ -24,7 +24,7 @@ pip3 install tqdm pip3 install cuda-python ``` -### Download +### Prepare Resources Pretrained model: @@ -45,7 +45,7 @@ onnxsim deit_tiny.onnx deit_tiny_opt.onnx ``` -## Inference +## Model Inference ```bash export DATASETS_DIR=/Path/to/imagenet_val/ @@ -62,12 +62,12 @@ bash scripts/infer_deit_tiny_fp16_performance.sh ``` -## Results +## Model Results | Model | BatchSize | Precision | FPS | Top-1(%) | Top-5(%) | | --------- | --------- | --------- | -------- | -------- | -------- | | DeiT-tiny | 32 | FP16 | 1446.690 | 74.34 | 92.21 | -## Reference +## References Deit_tiny: diff --git a/models/cv/classification/densenet121/igie/README.md b/models/cv/classification/densenet121/igie/README.md index 61deb581..f93055b1 100644 --- a/models/cv/classification/densenet121/igie/README.md +++ b/models/cv/classification/densenet121/igie/README.md @@ -1,18 +1,18 @@ # DenseNet121 -## Description +## Model Description DenseNet-121 is a convolutional neural network architecture that belongs to the family of Dense Convolutional Networks.The network consists of four dense blocks, each containing a varying number of densely connected convolutional layers. Transition layers with pooling operations reduce the spatial dimensions between dense blocks. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -24,7 +24,7 @@ Dataset: to download the validation dat python3 export.py --weight densenet121-a639ec97.pth --output densenet121.onnx ``` -## Inference +## Model Inference ```bash export DATASETS_DIR=/Path/to/imagenet_val/ @@ -39,7 +39,7 @@ bash scripts/infer_densenet121_fp16_accuracy.sh bash scripts/infer_densenet121_fp16_performance.sh ``` -## Results +## Model Results Model |BatchSize |Precision |FPS |Top-1(%) |Top-5(%) ------------|-----------|----------|---------|---------|-------- diff --git a/models/cv/classification/densenet121/ixrt/README.md b/models/cv/classification/densenet121/ixrt/README.md index 7e2afd49..1d3dbfd3 100644 --- a/models/cv/classification/densenet121/ixrt/README.md +++ b/models/cv/classification/densenet121/ixrt/README.md @@ -1,12 +1,12 @@ # DenseNet -## Description +## Model Description Dense Convolutional Network (DenseNet), connects each layer to every other layer in a feed-forward fashion. Whereas traditional convolutional networks with L layers have L connections - one between each layer and its subsequent layer - our network has L(L+1)/2 direct connections. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash # Install libGL @@ -18,7 +18,7 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Dataset: to download the validation dataset. @@ -29,7 +29,7 @@ mkdir checkpoints python3 export_onnx.py --output_model checkpoints/densenet121.onnx ``` -## Inference +## Model Inference ```bash export DATASETS_DIR=/path/to/imagenet_val/ @@ -47,7 +47,7 @@ bash scripts/infer_densenet_fp16_accuracy.sh bash scripts/infer_densenet_fp16_performance.sh ``` -## Results +## Model Results | Model | BatchSize | Precision | FPS | Top-1(%) | Top-5(%) | | -------- | --------- | --------- | ------- | -------- | -------- | diff --git a/models/cv/classification/densenet161/igie/README.md b/models/cv/classification/densenet161/igie/README.md index ba2b2757..3add49cc 100644 --- a/models/cv/classification/densenet161/igie/README.md +++ b/models/cv/classification/densenet161/igie/README.md @@ -1,18 +1,18 @@ # DenseNet161 -## Description +## Model Description DenseNet161 is a convolutional neural network architecture that belongs to the family of Dense Convolutional Networks (DenseNets). Introduced as an extension to the previous DenseNet models, DenseNet161 offers improved performance and deeper network capacity, making it suitable for various computer vision tasks. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -24,7 +24,7 @@ Dataset: to download the validation dat python3 export.py --weight densenet161-8d451a50.pth --output densenet161.onnx ``` -## Inference +## Model Inference ```bash export DATASETS_DIR=/Path/to/imagenet_val/ @@ -39,7 +39,7 @@ bash scripts/infer_densenet161_fp16_accuracy.sh bash scripts/infer_densenet161_fp16_performance.sh ``` -## Results +## Model Results | Model | BatchSize | Precision | FPS | Top-1(%) | Top-5(%) | | ----------- | --------- | --------- | ------ | -------- | -------- | diff --git a/models/cv/classification/densenet161/ixrt/README.md b/models/cv/classification/densenet161/ixrt/README.md index 58659f82..d3bf9c29 100644 --- a/models/cv/classification/densenet161/ixrt/README.md +++ b/models/cv/classification/densenet161/ixrt/README.md @@ -1,12 +1,12 @@ # DenseNet161 -## Description +## Model Description DenseNet161 is a convolutional neural network architecture that belongs to the family of Dense Convolutional Networks (DenseNets). Introduced as an extension to the previous DenseNet models, DenseNet161 offers improved performance and deeper network capacity, making it suitable for various computer vision tasks. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash # Install libGL @@ -18,7 +18,7 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: Dataset: to download the validation dataset. @@ -29,7 +29,7 @@ Dataset: to download the validation dat python3 export.py --weight densenet161-8d451a50.pth --output densenet161.onnx ``` -## Inference +## Model Inference ```bash export DATASETS_DIR=/Path/to/imagenet_val/ @@ -44,7 +44,7 @@ bash scripts/infer_densenet161_fp16_accuracy.sh bash scripts/infer_densenet161_fp16_performance.sh ``` -## Results +## Model Results | Model | BatchSize | Precision | FPS | Top-1(%) | Top-5(%) | | ----------- | --------- | --------- | ------- | -------- | -------- | diff --git a/models/cv/classification/densenet169/igie/README.md b/models/cv/classification/densenet169/igie/README.md index 0acd325a..9e95b177 100644 --- a/models/cv/classification/densenet169/igie/README.md +++ b/models/cv/classification/densenet169/igie/README.md @@ -1,18 +1,18 @@ # DenseNet169 -## Description +## Model Description DenseNet-169 is a variant of the Dense Convolutional Network (DenseNet) architecture, characterized by its 169 layers and a growth rate of 32. This network leverages the dense connectivity pattern, where each layer is connected to every other layer in a feed-forward fashion, resulting in a substantial increase in the number of direct connections compared to traditional convolutional networks. This connectivity pattern facilitates the reuse of features and enhances the flow of information and gradients throughout the network, which is particularly beneficial for deep architectures. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -24,7 +24,7 @@ Dataset: to download the validation dat python3 export.py --weight densenet169-b2777c0a.pth --output densenet169.onnx ``` -## Inference +## Model Inference ```bash export DATASETS_DIR=/Path/to/imagenet_val/ @@ -39,7 +39,7 @@ bash scripts/infer_densenet169_fp16_accuracy.sh bash scripts/infer_densenet169_fp16_performance.sh ``` -## Results +## Model Results | Model | BatchSize | Precision | FPS | Top-1(%) | Top-5(%) | | ----------- | --------- | --------- | -------- | -------- | -------- | diff --git a/models/cv/classification/densenet169/ixrt/README.md b/models/cv/classification/densenet169/ixrt/README.md index 0e3aee4c..a8ce1435 100644 --- a/models/cv/classification/densenet169/ixrt/README.md +++ b/models/cv/classification/densenet169/ixrt/README.md @@ -1,12 +1,12 @@ # DenseNet169 -## Description +## Model Description Dense Convolutional Network (DenseNet), connects each layer to every other layer in a feed-forward fashion. Whereas traditional convolutional networks with L layers have L connections - one between each layer and its subsequent layer - our network has L(L+1)/2 direct connections. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash # Install libGL @@ -18,7 +18,7 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -30,7 +30,7 @@ Dataset: to download the validation dat python3 export.py --weight densenet169-b2777c0a.pth --output densenet169.onnx ``` -## Inference +## Model Inference ```bash export DATASETS_DIR=/Path/to/imagenet_val/ @@ -45,7 +45,7 @@ bash scripts/infer_densenet169_fp16_accuracy.sh bash scripts/infer_densenet169_fp16_performance.sh ``` -## Results +## Model Results | Model | BatchSize | Precision | FPS | Top-1(%) | Top-5(%) | | -------- | --------- | --------- | ------- | -------- | -------- | diff --git a/models/cv/classification/densenet201/igie/README.md b/models/cv/classification/densenet201/igie/README.md index 072ff591..1fc6b13f 100644 --- a/models/cv/classification/densenet201/igie/README.md +++ b/models/cv/classification/densenet201/igie/README.md @@ -1,18 +1,18 @@ # DenseNet201 -## Description +## Model Description DenseNet201 is a deep convolutional neural network that stands out for its unique dense connection architecture, where each layer integrates features from all previous layers, effectively reusing features and reducing the number of parameters. This design not only enhances the network's information flow and parameter efficiency but also increases the model's regularization effect, helping to prevent overfitting. DenseNet201 consists of multiple dense blocks and transition layers, capable of capturing rich feature representations while maintaining computational efficiency, making it suitable for complex image recognition tasks. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -24,7 +24,7 @@ Dataset: to download the validation dat python3 export.py --weight densenet201-c1103571.pth --output densenet201.onnx ``` -## Inference +## Model Inference ```bash export DATASETS_DIR=/Path/to/imagenet_val/ @@ -39,7 +39,7 @@ bash scripts/infer_densenet201_fp16_accuracy.sh bash scripts/infer_densenet201_fp16_performance.sh ``` -## Results +## Model Results | Model | BatchSize | Precision | FPS | Top-1(%) | Top-5(%) | | ----------- | --------- | --------- | -------- | -------- | -------- | diff --git a/models/cv/classification/densenet201/ixrt/README.md b/models/cv/classification/densenet201/ixrt/README.md index e7e2b9ae..185c08ef 100644 --- a/models/cv/classification/densenet201/ixrt/README.md +++ b/models/cv/classification/densenet201/ixrt/README.md @@ -1,12 +1,12 @@ # DenseNet201 -## Description +## Model Description DenseNet201 is a deep convolutional neural network that stands out for its unique dense connection architecture, where each layer integrates features from all previous layers, effectively reusing features and reducing the number of parameters. This design not only enhances the network's information flow and parameter efficiency but also increases the model's regularization effect, helping to prevent overfitting. DenseNet201 consists of multiple dense blocks and transition layers, capable of capturing rich feature representations while maintaining computational efficiency, making it suitable for complex image recognition tasks. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash # Install libGL @@ -24,7 +24,7 @@ pip3 install tqdm pip3 install cuda-python ``` -### Download +### Prepare Resources Pretrained model: @@ -36,7 +36,7 @@ Dataset: to download the validation dat python3 export.py --weight densenet201-c1103571.pth --output densenet201.onnx ``` -## Inference +## Model Inference ```bash export DATASETS_DIR=/Path/to/imagenet_val/ @@ -51,7 +51,7 @@ bash scripts/infer_densenet201_fp16_accuracy.sh bash scripts/infer_densenet201_fp16_performance.sh ``` -## Results +## Model Results | Model | BatchSize | Precision | FPS | Top-1(%) | Top-5(%) | | ----------- | --------- | --------- | -------- | -------- | -------- | diff --git a/models/cv/classification/efficientnet_b0/igie/README.md b/models/cv/classification/efficientnet_b0/igie/README.md index 40ccbfad..03ab87d2 100644 --- a/models/cv/classification/efficientnet_b0/igie/README.md +++ b/models/cv/classification/efficientnet_b0/igie/README.md @@ -1,18 +1,18 @@ # EfficientNet B0 -## Description +## Model Description EfficientNet-B0 is a lightweight yet highly efficient convolutional neural network architecture. It is part of the EfficientNet family, known for its superior performance in balancing model size and accuracy. Developed with a focus on resource efficiency, EfficientNet-B0 achieves remarkable results across various computer vision tasks, including image classification and feature extraction. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -24,7 +24,7 @@ Dataset: to download the validation dat python3 export.py --weight efficientnet_b0_rwightman-7f5810bc.pth --output efficientnet_b0.onnx ``` -## Inference +## Model Inference ```bash export DATASETS_DIR=/Path/to/imagenet_val/ @@ -39,7 +39,7 @@ bash scripts/infer_efficientnet_b0_fp16_accuracy.sh bash scripts/infer_efficientnet_b0_fp16_performance.sh ``` -## Results +## Model Results Model |BatchSize |Precision |FPS |Top-1(%) |Top-5(%) ----------------|-----------|----------|----------|----------|-------- diff --git a/models/cv/classification/efficientnet_b0/ixrt/README.md b/models/cv/classification/efficientnet_b0/ixrt/README.md index e7c96a28..61b87328 100644 --- a/models/cv/classification/efficientnet_b0/ixrt/README.md +++ b/models/cv/classification/efficientnet_b0/ixrt/README.md @@ -1,12 +1,12 @@ # EfficientNet B0 -## Description +## Model Description EfficientNet B0 is a convolutional neural network architecture that belongs to the EfficientNet family, which was introduced by Mingxing Tan and Quoc V. Le in their paper "EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks." The EfficientNet family is known for achieving state-of-the-art performance on various computer vision tasks while being more computationally efficient than many existing models. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash # Install libGL @@ -18,7 +18,7 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -30,7 +30,7 @@ Dataset: to download the validation dat python3 export_onnx.py --origin_model /path/to/efficientnet_b0_rwightman-3dd342df.pth --output_model efficientnet_b0.onnx ``` -## Inference +## Model Inference ```bash export DATASETS_DIR=/path/to/imagenet_val/ @@ -54,7 +54,7 @@ bash scripts/infer_efficientnet_b0_int8_accuracy.sh bash scripts/infer_efficientnet_b0_int8_performance.sh ``` -## Results +## Model Results | Model | BatchSize | Precision | FPS | Top-1(%) | Top-5(%) | | --------------- | --------- | --------- | ------- | -------- | -------- | diff --git a/models/cv/classification/efficientnet_b1/igie/README.md b/models/cv/classification/efficientnet_b1/igie/README.md index 2707cbce..44864622 100644 --- a/models/cv/classification/efficientnet_b1/igie/README.md +++ b/models/cv/classification/efficientnet_b1/igie/README.md @@ -1,18 +1,18 @@ # EfficientNet B1 -## Description +## Model Description EfficientNet B1 is a convolutional neural network architecture that falls under the EfficientNet family, known for its remarkable balance between model size and performance. Introduced as part of the EfficientNet series, EfficientNet B1 offers a compact yet powerful solution for various computer vision tasks, including image classification, object detection and segmentation. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -24,7 +24,7 @@ Dataset: to download the validation dat python3 export.py --weight efficientnet_b1-c27df63c.pth --output efficientnet_b1.onnx ``` -## Inference +## Model Inference ```bash export DATASETS_DIR=/Path/to/imagenet_val/ @@ -39,7 +39,7 @@ bash scripts/infer_efficientnet_b1_fp16_accuracy.sh bash scripts/infer_efficientnet_b1_fp16_performance.sh ``` -## Results +## Model Results Model |BatchSize |Precision |FPS |Top-1(%) |Top-5(%) ----------------|-----------|----------|---------|---------|-------- diff --git a/models/cv/classification/efficientnet_b1/ixrt/README.md b/models/cv/classification/efficientnet_b1/ixrt/README.md index a2076bbb..ae95d1d7 100644 --- a/models/cv/classification/efficientnet_b1/ixrt/README.md +++ b/models/cv/classification/efficientnet_b1/ixrt/README.md @@ -1,12 +1,12 @@ # EfficientNet B1 -## Description +## Model Description EfficientNet B1 is one of the variants in the EfficientNet family of neural network architectures, introduced by Mingxing Tan and Quoc V. Le in their paper "EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks." EfficientNet B1 is a scaled-up version of the baseline model (B0) and is designed to achieve better performance on various computer vision tasks. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash # Install libGL @@ -18,7 +18,7 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Dataset: to download the validation dataset. @@ -29,7 +29,7 @@ mkdir checkpoints python3 export_onnx.py --output_model checkpoints/efficientnet-b1.onnx ``` -## Inference +## Model Inference ```bash export PROJ_DIR=./ @@ -57,7 +57,7 @@ bash scripts/infer_efficientnet_b1_int8_accuracy.sh bash scripts/infer_efficientnet_b1_int8_performance.sh ``` -## Results +## Model Results Model |BatchSize |Precision |FPS |Top-1(%) |Top-5(%) ----------------|-----------|----------|---------|----------|-------- diff --git a/models/cv/classification/efficientnet_b2/igie/README.md b/models/cv/classification/efficientnet_b2/igie/README.md index 0a2b56dc..ab138a37 100644 --- a/models/cv/classification/efficientnet_b2/igie/README.md +++ b/models/cv/classification/efficientnet_b2/igie/README.md @@ -1,18 +1,18 @@ # EfficientNet B2 -## Description +## Model Description EfficientNet B2 is a member of the EfficientNet family, a series of convolutional neural network architectures that are designed to achieve excellent accuracy and efficiency. Introduced by researchers at Google, EfficientNets utilize the compound scaling method, which uniformly scales the depth, width, and resolution of the network to improve accuracy and efficiency. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -24,7 +24,7 @@ Dataset: to download the validation dat python3 export.py --weight efficientnet_b2_rwightman-c35c1473.pth --output efficientnet_b2.onnx ``` -## Inference +## Model Inference ```bash export DATASETS_DIR=/Path/to/imagenet_val/ @@ -39,7 +39,7 @@ bash scripts/infer_efficientnet_b2_fp16_accuracy.sh bash scripts/infer_efficientnet_b2_fp16_performance.sh ``` -## Results +## Model Results | Model | BatchSize | Precision | FPS | Top-1(%) | Top-5(%) | | --------------- | --------- | --------- | -------- | -------- | -------- | diff --git a/models/cv/classification/efficientnet_b2/ixrt/README.md b/models/cv/classification/efficientnet_b2/ixrt/README.md index 059c80ba..d5e4c234 100644 --- a/models/cv/classification/efficientnet_b2/ixrt/README.md +++ b/models/cv/classification/efficientnet_b2/ixrt/README.md @@ -1,12 +1,12 @@ # EfficientNet B2 -## Description +## Model Description EfficientNet B2 is a member of the EfficientNet family, a series of convolutional neural network architectures that are designed to achieve excellent accuracy and efficiency. Introduced by researchers at Google, EfficientNets utilize the compound scaling method, which uniformly scales the depth, width, and resolution of the network to improve accuracy and efficiency. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash # Install libGL @@ -18,7 +18,7 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -30,7 +30,7 @@ Dataset: to download the validation dat python3 export.py --weight efficientnet_b2_rwightman-c35c1473.pth --output efficientnet_b2.onnx ``` -## Inference +## Model Inference ```bash export DATASETS_DIR=/Path/to/imagenet_val/ @@ -45,7 +45,7 @@ bash scripts/infer_efficientnet_b2_fp16_accuracy.sh bash scripts/infer_efficientnet_b2_fp16_performance.sh ``` -## Results +## Model Results | Model | BatchSize | Precision | FPS | Top-1(%) | Top-5(%) | | --------------- | --------- | --------- | ------- | -------- | -------- | diff --git a/models/cv/classification/efficientnet_b3/igie/README.md b/models/cv/classification/efficientnet_b3/igie/README.md index ff3b3e31..c4d72df2 100644 --- a/models/cv/classification/efficientnet_b3/igie/README.md +++ b/models/cv/classification/efficientnet_b3/igie/README.md @@ -1,18 +1,18 @@ # EfficientNet B3 -## Description +## Model Description EfficientNet B3 is a member of the EfficientNet family, a series of convolutional neural network architectures that are designed to achieve excellent accuracy and efficiency. Introduced by researchers at Google, EfficientNets utilize the compound scaling method, which uniformly scales the depth, width, and resolution of the network to improve accuracy and efficiency. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -24,7 +24,7 @@ Dataset: to download the validation dat python3 export.py --weight efficientnet_b3_rwightman-b3899882.pth --output efficientnet_b3.onnx ``` -## Inference +## Model Inference ```bash export DATASETS_DIR=/Path/to/imagenet_val/ @@ -39,7 +39,7 @@ bash scripts/infer_efficientnet_b3_fp16_accuracy.sh bash scripts/infer_efficientnet_b3_fp16_performance.sh ``` -## Results +## Model Results | Model | BatchSize | Precision | FPS | Top-1(%) | Top-5(%) | | --------------- | --------- | --------- | -------- | -------- | -------- | diff --git a/models/cv/classification/efficientnet_b3/ixrt/README.md b/models/cv/classification/efficientnet_b3/ixrt/README.md index 1860a5e2..b9861c6b 100644 --- a/models/cv/classification/efficientnet_b3/ixrt/README.md +++ b/models/cv/classification/efficientnet_b3/ixrt/README.md @@ -1,12 +1,12 @@ # EfficientNet B3 -## Description +## Model Description EfficientNet B3 is a member of the EfficientNet family, a series of convolutional neural network architectures that are designed to achieve excellent accuracy and efficiency. Introduced by researchers at Google, EfficientNets utilize the compound scaling method, which uniformly scales the depth, width, and resolution of the network to improve accuracy and efficiency. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash # Install libGL @@ -21,7 +21,7 @@ pip3 install onnxsim pip3 install tabulate ``` -### Download +### Prepare Resources Pretrained model: @@ -33,7 +33,7 @@ Dataset: to download the validation dat python3 export.py --weight efficientnet_b3_rwightman-b3899882.pth --output efficientnet_b3.onnx ``` -## Inference +## Model Inference ```bash export DATASETS_DIR=/Path/to/imagenet_val/ @@ -48,7 +48,7 @@ bash scripts/infer_efficientnet_b3_fp16_accuracy.sh bash scripts/infer_efficientnet_b3_fp16_performance.sh ``` -## Results +## Model Results | Model | BatchSize | Precision | FPS | Top-1(%) | Top-5(%) | | --------------- | --------- | --------- | ------- | -------- | -------- | diff --git a/models/cv/classification/efficientnet_b4/igie/README.md b/models/cv/classification/efficientnet_b4/igie/README.md index bced3cda..403194e3 100644 --- a/models/cv/classification/efficientnet_b4/igie/README.md +++ b/models/cv/classification/efficientnet_b4/igie/README.md @@ -1,18 +1,18 @@ # EfficientNet B4 -## Description +## Model Description EfficientNet B4 is a high-performance convolutional neural network model introduced in Google's paper "EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks." It is part of the EfficientNet family, which leverages compound scaling to balance depth, width, and input resolution for better accuracy and efficiency. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -24,7 +24,7 @@ Dataset: to download the validation dat python3 export.py --weight efficientnet_b4_rwightman-23ab8bcd.pth --output efficientnet_b4.onnx ``` -## Inference +## Model Inference ```bash export DATASETS_DIR=/Path/to/imagenet_val/ @@ -39,7 +39,7 @@ bash scripts/infer_efficientnet_b4_fp16_accuracy.sh bash scripts/infer_efficientnet_b4_fp16_performance.sh ``` -## Results +## Model Results | Model | BatchSize | Precision | FPS | Top-1(%) | Top-5(%) | | --------------- | --------- | --------- | -------- | -------- | -------- | diff --git a/models/cv/classification/efficientnet_v2/igie/README.md b/models/cv/classification/efficientnet_v2/igie/README.md index f483a9ba..0ae45c84 100644 --- a/models/cv/classification/efficientnet_v2/igie/README.md +++ b/models/cv/classification/efficientnet_v2/igie/README.md @@ -1,18 +1,18 @@ # EfficientNetV2-M -## Description +## Model Description EfficientNetV2 M is an optimized model in the EfficientNetV2 series, which was developed by Google researchers. It continues the legacy of the EfficientNet family, focusing on advancing the state-of-the-art in accuracy and efficiency through advanced scaling techniques and architectural innovations. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -24,7 +24,7 @@ Dataset: to download the validation dat python3 export.py --weight efficientnet_v2_m-dc08266a.pth --output efficientnet_v2_m.onnx ``` -## Inference +## Model Inference ```bash export DATASETS_DIR=/Path/to/imagenet_val/ @@ -39,7 +39,7 @@ bash scripts/infer_efficientnet_v2_fp16_accuracy.sh bash scripts/infer_efficientnet_v2_fp16_performance.sh ``` -## Results +## Model Results | Model | BatchSize | Precision | FPS | Top-1(%) | Top-5(%) | | ---------------- | --------- | --------- | -------- | -------- | -------- | diff --git a/models/cv/classification/efficientnet_v2/ixrt/README.md b/models/cv/classification/efficientnet_v2/ixrt/README.md index c83e812f..e4acdd8c 100755 --- a/models/cv/classification/efficientnet_v2/ixrt/README.md +++ b/models/cv/classification/efficientnet_v2/ixrt/README.md @@ -1,12 +1,12 @@ # EfficientNetV2 -## Description +## Model Description EfficientNetV2 is an improved version of the EfficientNet architecture proposed by Google, aiming to enhance model performance and efficiency. Unlike the original EfficientNet, EfficientNetV2 features a simplified design and incorporates a series of enhancement strategies to further boost performance. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash # Install libGL @@ -18,7 +18,7 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -39,7 +39,7 @@ python3 -m models.export_onnx --output_model ../../checkpoints/efficientnet_v2.o cd ../../ ``` -## Inference +## Model Inference ```bash export PROJ_DIR=/Path/to/efficientnet_v2/ixrt @@ -68,7 +68,7 @@ bash scripts/infer_efficientnet_v2_int8_accuracy.sh bash scripts/infer_efficientnet_v2_int8_performance.sh ``` -## Results +## Model Results Model | BatchSize | Precision | FPS | Top-1(%) | Top-5(%) ---------------|-----------|-----------|----------|----------|-------- diff --git a/models/cv/classification/efficientnet_v2_s/igie/README.md b/models/cv/classification/efficientnet_v2_s/igie/README.md index ea32a555..69508ab6 100644 --- a/models/cv/classification/efficientnet_v2_s/igie/README.md +++ b/models/cv/classification/efficientnet_v2_s/igie/README.md @@ -1,18 +1,18 @@ # EfficientNet_v2_s -## Description +## Model Description EfficientNetV2 S is an optimized model in the EfficientNetV2 series, which was developed by Google researchers. It continues the legacy of the EfficientNet family, focusing on advancing the state-of-the-art in accuracy and efficiency through advanced scaling techniques and architectural innovations. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -24,7 +24,7 @@ Dataset: to download the validation dat python3 export.py --weight efficientnet_v2_s-dd5fe13b.pth --output efficientnet_v2_s.onnx ``` -## Inference +## Model Inference ```bash export DATASETS_DIR=/Path/to/imagenet_val/ @@ -39,7 +39,7 @@ bash scripts/infer_efficientnet_v2_s_fp16_accuracy.sh bash scripts/infer_efficientnet_v2_s_fp16_performance.sh ``` -## Results +## Model Results | Model | BatchSize | Precision | FPS | Top-1(%) | Top-5(%) | | ----------------- | --------- | --------- | -------- | -------- | -------- | diff --git a/models/cv/classification/efficientnet_v2_s/ixrt/README.md b/models/cv/classification/efficientnet_v2_s/ixrt/README.md index 3c6baa22..06947aa9 100644 --- a/models/cv/classification/efficientnet_v2_s/ixrt/README.md +++ b/models/cv/classification/efficientnet_v2_s/ixrt/README.md @@ -1,18 +1,18 @@ # EfficientNet_v2_s -## Description +## Model Description EfficientNetV2 S is an optimized model in the EfficientNetV2 series, which was developed by Google researchers. It continues the legacy of the EfficientNet family, focusing on advancing the state-of-the-art in accuracy and efficiency through advanced scaling techniques and architectural innovations. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -24,7 +24,7 @@ Dataset: to download the validation dat python3 export.py --weight efficientnet_v2_s-dd5fe13b.pth --output efficientnet_v2_s.onnx ``` -## Inference +## Model Inference ```bash export DATASETS_DIR=/Path/to/imagenet_val/ @@ -39,7 +39,7 @@ bash scripts/infer_efficientnet_v2_s_fp16_accuracy.sh bash scripts/infer_efficientnet_v2_s_fp16_performance.sh ``` -## Results +## Model Results | Model | BatchSize | Precision | FPS | Top-1(%) | Top-5(%) | | ----------------- | --------- | --------- | -------- | -------- | -------- | diff --git a/models/cv/classification/efficientnetv2_rw_t/igie/README.md b/models/cv/classification/efficientnetv2_rw_t/igie/README.md index 390de644..cec8e84e 100644 --- a/models/cv/classification/efficientnetv2_rw_t/igie/README.md +++ b/models/cv/classification/efficientnetv2_rw_t/igie/README.md @@ -1,18 +1,18 @@ # EfficientNetv2_rw_t -## Description +## Model Description EfficientNetV2_rw_t is an enhanced version of the EfficientNet family of convolutional neural network architectures. It builds upon the success of its predecessors by introducing novel advancements aimed at further improving performance and efficiency in various computer vision tasks. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -24,7 +24,7 @@ Dataset: to download the validation dat python3 export.py --weight efficientnetv2_t_agc-3620981a.pth --output efficientnetv2_rw_t.onnx ``` -## Inference +## Model Inference ```bash export DATASETS_DIR=/Path/to/imagenet_val/ @@ -39,7 +39,7 @@ bash scripts/infer_efficientnetv2_rw_t_fp16_accuracy.sh bash scripts/infer_efficientnetv2_rw_t_fp16_performance.sh ``` -## Results +## Model Results Model |BatchSize |Precision |FPS |Top-1(%) |Top-5(%) --------------------|-----------|----------|---------|---------|-------- diff --git a/models/cv/classification/efficientnetv2_rw_t/ixrt/README.md b/models/cv/classification/efficientnetv2_rw_t/ixrt/README.md index 1e5d56d0..07877330 100644 --- a/models/cv/classification/efficientnetv2_rw_t/ixrt/README.md +++ b/models/cv/classification/efficientnetv2_rw_t/ixrt/README.md @@ -1,12 +1,12 @@ # EfficientNetv2_rw_t -## Description +## Model Description EfficientNetV2_rw_t is an enhanced version of the EfficientNet family of convolutional neural network architectures. It builds upon the success of its predecessors by introducing novel advancements aimed at further improving performance and efficiency in various computer vision tasks. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash # Install libGL @@ -25,7 +25,7 @@ pip3 install tqdm pip3 install cuda-python ``` -### Download +### Prepare Resources Pretrained model: @@ -37,7 +37,7 @@ Dataset: to download the validation dat python3 export.py --weight efficientnetv2_t_agc-3620981a.pth --output efficientnetv2_rw_t.onnx ``` -## Inference +## Model Inference ```bash export DATASETS_DIR=/Path/to/imagenet_val/ @@ -52,7 +52,7 @@ bash scripts/infer_efficientnetv2_rw_t_fp16_accuracy.sh bash scripts/infer_efficientnetv2_rw_t_fp16_performance.sh ``` -## Results +## Model Results Model |BatchSize |Precision |FPS |Top-1(%) |Top-5(%) --------------------|-----------|----------|---------|---------|-------- diff --git a/models/cv/classification/googlenet/igie/README.md b/models/cv/classification/googlenet/igie/README.md index fe903822..3279e311 100644 --- a/models/cv/classification/googlenet/igie/README.md +++ b/models/cv/classification/googlenet/igie/README.md @@ -1,18 +1,18 @@ # GoogleNet -## Description +## Model Description Introduced in 2014, GoogleNet revolutionized image classification models by introducing the concept of inception modules. These modules utilize parallel convolutional filters of different sizes, allowing the network to capture features at various scales efficiently. With its emphasis on computational efficiency and the reduction of parameters, GoogleNet achieved competitive accuracy while maintaining a relatively low computational cost. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -24,7 +24,7 @@ Dataset: to download the validation dat python3 export.py --weight googlenet-1378be20.pth --output googlenet.onnx ``` -## Inference +## Model Inference ```bash export DATASETS_DIR=/Path/to/imagenet_val/ @@ -48,7 +48,7 @@ bash scripts/infer_googlenet_int8_accuracy.sh bash scripts/infer_googlenet_int8_performance.sh ``` -## Results +## Model Results Model |BatchSize |Precision |FPS |Top-1(%) |Top-5(%) ----------|-----------|----------|----------|---------|-------- diff --git a/models/cv/classification/googlenet/ixrt/README.md b/models/cv/classification/googlenet/ixrt/README.md index 31170f0d..bd71b32f 100644 --- a/models/cv/classification/googlenet/ixrt/README.md +++ b/models/cv/classification/googlenet/ixrt/README.md @@ -1,12 +1,12 @@ # GoogLeNet -## Description +## Model Description GoogLeNet is a type of convolutional neural network based on the Inception architecture. It utilises Inception modules, which allow the network to choose between multiple convolutional filter sizes in each block. An Inception network stacks these modules on top of each other, with occasional max-pooling layers with stride 2 to halve the resolution of the grid. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash # Install libGL @@ -18,7 +18,7 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -31,7 +31,7 @@ mkdir checkpoints python3 export_onnx.py --origin_model /path/to/googlenet-1378be20.pth --output_model checkpoints/googlenet.onnx ``` -## Inference +## Model Inference ```bash export PROJ_DIR=./ @@ -59,7 +59,7 @@ bash scripts/infer_googlenet_int8_accuracy.sh bash scripts/infer_googlenet_int8_performance.sh ``` -## Results +## Model Results Model |BatchSize |Precision |FPS |Top-1(%) |Top-5(%) ----------|-----------|----------|----------|----------|-------- diff --git a/models/cv/classification/hrnet_w18/igie/README.md b/models/cv/classification/hrnet_w18/igie/README.md index 5284b949..65625631 100644 --- a/models/cv/classification/hrnet_w18/igie/README.md +++ b/models/cv/classification/hrnet_w18/igie/README.md @@ -1,12 +1,12 @@ # HRNet-W18 -## Description +## Model Description HRNet, short for High-Resolution Network, presents a paradigm shift in handling position-sensitive vision challenges, such as human pose estimation, semantic segmentation, and object detection. The distinctive features of HRNet result in semantically richer and spatially more precise representations. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash # Install libGL @@ -18,7 +18,7 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -38,7 +38,7 @@ onnxsim hrnet_w18.onnx hrnet_w18_opt.onnx ``` -## Inference +## Model Inference ```bash export DATASETS_DIR=/Path/to/imagenet_val/ @@ -53,12 +53,12 @@ bash scripts/infer_hrnet_w18_fp16_accuracy.sh bash scripts/infer_hrnet_w18_fp16_performance.sh ``` -## Results +## Model Results Model |BatchSize |Precision |FPS |Top-1(%) |Top-5(%) ----------|-----------|----------|----------|----------|-------- HRNet_w18 | 32 | FP16 | 954.18 | 76.74 | 93.42 -## Reference +## References HRNet: diff --git a/models/cv/classification/hrnet_w18/ixrt/README.md b/models/cv/classification/hrnet_w18/ixrt/README.md index 93691d2b..fe8f9726 100644 --- a/models/cv/classification/hrnet_w18/ixrt/README.md +++ b/models/cv/classification/hrnet_w18/ixrt/README.md @@ -1,12 +1,12 @@ # HRNet-W18 -## Description +## Model Description HRNet-W18 is a powerful image classification model developed by Jingdong AI Research and released in 2020. It belongs to the HRNet (High-Resolution Network) family of models, known for their exceptional performance in various computer vision tasks. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash # Install libGL @@ -18,7 +18,7 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Dataset: to download the validation dataset. @@ -29,7 +29,7 @@ mkdir checkpoints python3 export_onnx.py --output_model checkpoints/hrnet-w18.onnx ``` -## Inference +## Model Inference ```bash export DATASETS_DIR=/path/to/imagenet_val/ @@ -56,7 +56,7 @@ bash scripts/infer_hrnet_w18_int8_accuracy.sh bash scripts/infer_hrnet_w18_int8_performance.sh ``` -## Results +## Model Results | Model | BatchSize | Precision | FPS | Top-1(%) | Top-5(%) | | -------- | --------- | --------- | ------- | -------- | -------- | diff --git a/models/cv/classification/inception_resnet_v2/ixrt/README.md b/models/cv/classification/inception_resnet_v2/ixrt/README.md index a845e9d6..01c3965b 100755 --- a/models/cv/classification/inception_resnet_v2/ixrt/README.md +++ b/models/cv/classification/inception_resnet_v2/ixrt/README.md @@ -1,12 +1,12 @@ # Inception-ResNet-V2 -## Description +## Model Description Inception-ResNet-V2 is a deep learning model proposed by Google in 2016, which combines the architectures of Inception and ResNet. This model integrates the dense connections of the Inception series with the residual connections of ResNet, aiming to enhance model performance and training efficiency. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash # Install libGL @@ -18,7 +18,7 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -32,7 +32,7 @@ mkdir checkpoints python3 export_model.py --output_model /Path/to/checkpoints/inceptionresnetv2.onnx ``` -## Inference +## Model Inference ```bash export PROJ_DIR=/Path/to/inceptionresnetv2/ixrt @@ -61,7 +61,7 @@ bash scripts/infer_inceptionresnetv2_int8_accuracy.sh bash scripts/infer_inceptionresnetv2_int8_performance.sh ``` -## Results +## Model Results | Model | BatchSize | Precision | FPS | Top-1(%) | Top-5(%) | |---------------------|-----------|-----------|---------|----------|----------| diff --git a/models/cv/classification/inception_v3/igie/README.md b/models/cv/classification/inception_v3/igie/README.md index fe740616..2aeb2e7b 100644 --- a/models/cv/classification/inception_v3/igie/README.md +++ b/models/cv/classification/inception_v3/igie/README.md @@ -1,18 +1,18 @@ # Inception V3 -## Description +## Model Description Inception v3 is a convolutional neural network architecture designed for image recognition and classification tasks. Developed by Google, it represents an evolution of the earlier Inception models. Inception v3 is characterized by its deep architecture, featuring multiple layers with various filter sizes and efficient use of computational resources. The network employs techniques like factorized convolutions and batch normalization to enhance training stability and accelerate convergence. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -24,7 +24,7 @@ Dataset: to download the validation dat python3 export.py --weight inception_v3_google-0cc3c7bd.pth --output inception_v3.onnx ``` -## Inference +## Model Inference ```bash export DATASETS_DIR=/Path/to/imagenet_val/ @@ -48,7 +48,7 @@ bash scripts/infer_inception_v3_int8_accuracy.sh bash scripts/infer_inception_v3_int8_performance.sh ``` -## Results +## Model Results Model |BatchSize |Precision |FPS |Top-1(%) |Top-5(%) -------------|-----------|----------|----------|----------|-------- diff --git a/models/cv/classification/inception_v3/ixrt/README.md b/models/cv/classification/inception_v3/ixrt/README.md index e0d938d3..b795ac9c 100755 --- a/models/cv/classification/inception_v3/ixrt/README.md +++ b/models/cv/classification/inception_v3/ixrt/README.md @@ -1,12 +1,12 @@ # Inception V3 -## Description +## Model Description Inception v3 is a convolutional neural network architecture designed for image recognition and classification tasks. Developed by Google, it represents an evolution of the earlier Inception models. Inception v3 is characterized by its deep architecture, featuring multiple layers with various filter sizes and efficient use of computational resources. The network employs techniques like factorized convolutions and batch normalization to enhance training stability and accelerate convergence. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash # Install libGL @@ -18,7 +18,7 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -32,7 +32,7 @@ mkdir checkpoints python3 export_onnx.py --origin_model inception_v3_google-0cc3c7bd.pth --output_model checkpoints/inception_v3.onnx ``` -## Inference +## Model Inference ```bash export PROJ_DIR=/Path/to/inception_v3/ixrt @@ -61,7 +61,7 @@ bash scripts/infer_inception_v3_int8_accuracy.sh bash scripts/infer_inception_v3_int8_performance.sh ``` -## Results +## Model Results Model |BatchSize |Precision |FPS |Top-1(%) |Top-5(%) -------------|-----------|----------|----------|----------|-------- diff --git a/models/cv/classification/mlp_mixer_base/igie/README.md b/models/cv/classification/mlp_mixer_base/igie/README.md index d82c728b..b9f1008d 100644 --- a/models/cv/classification/mlp_mixer_base/igie/README.md +++ b/models/cv/classification/mlp_mixer_base/igie/README.md @@ -1,12 +1,12 @@ # MLP-Mixer Base -## Description +## Model Description MLP-Mixer Base is a foundational model in the MLP-Mixer family, designed to use only MLP layers for vision tasks like image classification. Unlike CNNs and Vision Transformers, MLP-Mixer replaces both convolution and self-attention mechanisms with simple MLP layers to process spatial and channel-wise information independently. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash # Install libGL @@ -18,7 +18,7 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -38,7 +38,7 @@ onnxsim mlp_mixer_base.onnx mlp_mixer_base_opt.onnx ``` -## Inference +## Model Inference ```bash export DATASETS_DIR=/Path/to/imagenet_val/ @@ -53,12 +53,12 @@ bash scripts/infer_mlp_mixer_base_fp16_accuracy.sh bash scripts/infer_mlp_mixer_base_fp16_performance.sh ``` -## Results +## Model Results | Model | BatchSize | Precision | FPS | Top-1(%) | Top-5(%) | | ----------------| --------- | --------- | -------- | -------- | -------- | | MLP-Mixer-Base | 32 | FP16 | 1477.15 | 72.545 | 90.035 | -## Reference +## References MLP-Mixer-Base: diff --git a/models/cv/classification/mnasnet0_5/igie/README.md b/models/cv/classification/mnasnet0_5/igie/README.md index 86ec2dec..3c3ea3a0 100644 --- a/models/cv/classification/mnasnet0_5/igie/README.md +++ b/models/cv/classification/mnasnet0_5/igie/README.md @@ -1,18 +1,18 @@ # MNASNet0_5 -## Description +## Model Description MNASNet0_5 is a neural network architecture optimized for mobile devices, designed through neural architecture search technology. It is characterized by high efficiency and excellent accuracy, offering 50% higher accuracy than MobileNetV2 while maintaining low latency and memory usage. MNASNet0_5 widely uses depthwise separable convolutions, supports multi-scale inputs, and demonstrates good robustness, making it suitable for real-time image recognition tasks in resource-constrained environments. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -24,7 +24,7 @@ Dataset: to download the validation dat python3 export.py --weight mnasnet0.5_top1_67.823-3ffadce67e.pth --output mnasnet0_5.onnx ``` -## Inference +## Model Inference ```bash export DATASETS_DIR=/Path/to/imagenet_val/ @@ -39,7 +39,7 @@ bash scripts/infer_mnasnet0_5_fp16_accuracy.sh bash scripts/infer_mnasnet0_5_fp16_performance.sh ``` -## Results +## Model Results | Model | BatchSize | Precision | FPS | Top-1(%) | Top-5(%) | | ----------------- | --------- | --------- | -------- | -------- | -------- | diff --git a/models/cv/classification/mnasnet0_75/igie/README.md b/models/cv/classification/mnasnet0_75/igie/README.md index 292ba158..1899cc39 100644 --- a/models/cv/classification/mnasnet0_75/igie/README.md +++ b/models/cv/classification/mnasnet0_75/igie/README.md @@ -1,18 +1,18 @@ # MNASNet0_75 -## Description +## Model Description MNASNet0_75 is a lightweight convolutional neural network designed for mobile devices, introduced in the paper "MNASNet: Multi-Objective Neural Architecture Search for Mobile." The model leverages Multi-Objective Neural Architecture Search (NAS) to achieve a balance between accuracy and efficiency by optimizing both performance and computational cost. With a width multiplier of 0.75, MNASNet0_75 reduces the number of channels compared to the standard MNASNet (width multiplier of 1.0), resulting in fewer parameters. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -24,7 +24,7 @@ Dataset: to download the validation dat python3 export.py --weight mnasnet0_75-7090bc5f.pth --output mnasnet0_75.onnx ``` -## Inference +## Model Inference ```bash export DATASETS_DIR=/Path/to/imagenet_val/ @@ -39,7 +39,7 @@ bash scripts/infer_mnasnet0_75_fp16_accuracy.sh bash scripts/infer_mnasnet0_75_fp16_performance.sh ``` -## Results +## Model Results | Model | BatchSize | Precision | FPS | Top-1(%) | Top-5(%) | | ----------------- | --------- | --------- | -------- | -------- | -------- | diff --git a/models/cv/classification/mobilenet_v2/igie/README.md b/models/cv/classification/mobilenet_v2/igie/README.md index 15b4d95b..07d75bed 100644 --- a/models/cv/classification/mobilenet_v2/igie/README.md +++ b/models/cv/classification/mobilenet_v2/igie/README.md @@ -1,18 +1,18 @@ # MobileNetV2 -## Description +## Model Description MobileNetV2 is an improvement on V1. Its new ideas include Linear Bottleneck and Inverted Residuals, and is based on an inverted residual structure where the input and output of the residual block are thin bottleneck layers. The intermediate expansion layer uses lightweight depthwise convolutions to filter features as a source of non-linearity. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -24,7 +24,7 @@ Dataset: to download the validation dat python3 export.py --weight mobilenet_v2-7ebf99e0.pth --output mobilenet_v2.onnx ``` -## Inference +## Model Inference ```bash export DATASETS_DIR=/Path/to/imagenet_val/ @@ -48,7 +48,7 @@ bash scripts/infer_mobilenet_v2_int8_accuracy.sh bash scripts/infer_mobilenet_v2_int8_performance.sh ``` -## Results +## Model Results Model |BatchSize |Precision |FPS |Top-1(%) |Top-5(%) -------------|-----------|----------|---------|----------|-------- diff --git a/models/cv/classification/mobilenet_v2/ixrt/README.md b/models/cv/classification/mobilenet_v2/ixrt/README.md index de892cf6..f893faa2 100644 --- a/models/cv/classification/mobilenet_v2/ixrt/README.md +++ b/models/cv/classification/mobilenet_v2/ixrt/README.md @@ -1,18 +1,18 @@ # MobileNetV2 -## Description +## Model Description The MobileNetV2 architecture is based on an inverted residual structure where the input and output of the residual block are thin bottleneck layers opposite to traditional residual models which use expanded representations in the input an MobileNetV2 uses lightweight depthwise convolutions to filter features in the intermediate expansion layer. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -25,7 +25,7 @@ mkdir checkpoints python3 export_onnx.py --origin_model /path/to/mobilenet_v2-b0353104 --output_model checkpoints/mobilenet_v2.onnx ``` -## Inference +## Model Inference ```bash export PROJ_DIR=./ @@ -52,7 +52,7 @@ bash script/infer_mobilenet_v2_int8_accuracy.sh bash script/infer_mobilenet_v2_int8_performance.sh ``` -## Results +## Model Results | Model | BatchSize | Precision | FPS | Top-1(%) | Top-5(%) | | ----------- | --------- | --------- | ------- | -------- | -------- | diff --git a/models/cv/classification/mobilenet_v3/igie/README.md b/models/cv/classification/mobilenet_v3/igie/README.md index 501c8be8..77cd08ad 100644 --- a/models/cv/classification/mobilenet_v3/igie/README.md +++ b/models/cv/classification/mobilenet_v3/igie/README.md @@ -1,18 +1,18 @@ # MobileNetV3_Small -## Description +## Model Description MobileNetV3_Small is a lightweight convolutional neural network architecture designed for efficient mobile and embedded devices. It is part of the MobileNet family, renowned for its compact size and high performance, making it ideal for applications with limited computational resources.The key focus of MobileNetV3_Small is to achieve a balance between model size, speed, and accuracy. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -24,7 +24,7 @@ Dataset: to download the validation dat python3 export.py --weight mobilenet_v3_small-047dcff4.pth --output mobilenetv3_small.onnx ``` -## Inference +## Model Inference ```bash export DATASETS_DIR=/Path/to/imagenet_val/ @@ -39,7 +39,7 @@ bash scripts/infer_mobilenet_v3_fp16_accuracy.sh bash scripts/infer_mobilenet_v3_fp16_performance.sh ``` -## Results +## Model Results Model |BatchSize |Precision |FPS |Top-1(%) |Top-5(%) ------------------|-----------|----------|---------|---------|-------- diff --git a/models/cv/classification/mobilenet_v3/ixrt/README.md b/models/cv/classification/mobilenet_v3/ixrt/README.md index 7a80ec49..f044216d 100644 --- a/models/cv/classification/mobilenet_v3/ixrt/README.md +++ b/models/cv/classification/mobilenet_v3/ixrt/README.md @@ -1,12 +1,12 @@ # MobileNetV3 -## Description +## Model Description MobileNetV3 is a convolutional neural network that is tuned to mobile phone CPUs through a combination of hardware-aware network architecture search (NAS) complemented by the NetAdapt algorithm, and then subsequently improved through novel architecture advances. Advances include (1) complementary search techniques, (2) new efficient versions of nonlinearities practical for the mobile setting, (3) new efficient network design. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash # Install libGL @@ -18,7 +18,7 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -31,7 +31,7 @@ mkdir checkpoints python3 export_onnx.py --origin_model /path/to/mobilenet_v3_small-047dcff4.pth --output_model checkpoints/mobilenet_v3.onnx ``` -## Inference +## Model Inference ```bash export PROJ_DIR=./ @@ -50,7 +50,7 @@ bash scripts/infer_mobilenet_v3_fp16_accuracy.sh bash scripts/infer_mobilenet_v3_fp16_performance.sh ``` -## Results +## Model Results Model | BatchSize | Precision| FPS | Top-1(%) | Top-5(%) ------------|-----------|----------|----------|----------|-------- diff --git a/models/cv/classification/mobilenet_v3_large/igie/README.md b/models/cv/classification/mobilenet_v3_large/igie/README.md index b44fd185..2a73312d 100644 --- a/models/cv/classification/mobilenet_v3_large/igie/README.md +++ b/models/cv/classification/mobilenet_v3_large/igie/README.md @@ -1,18 +1,18 @@ # MobileNetV3_Large -## Description +## Model Description MobileNetV3_Large builds upon the success of its predecessors by incorporating several innovative design strategies to enhance performance. It features larger model capacity and computational resources compared to MobileNetV3_Small, allowing for deeper network architectures and more complex feature representations. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -24,7 +24,7 @@ Dataset: to download the validation dat python3 export.py --weight mobilenet_v3_large-8738ca79.pth --output mobilenetv3_large.onnx ``` -## Inference +## Model Inference ```bash export DATASETS_DIR=/Path/to/imagenet_val/ @@ -39,7 +39,7 @@ bash scripts/infer_mobilenet_v3_large_fp16_accuracy.sh bash scripts/infer_mobilenet_v3_large_fp16_performance.sh ``` -## Results +## Model Results Model |BatchSize |Precision |FPS |Top-1(%) |Top-5(%) ------------------|-----------|----------|---------|---------|-------- diff --git a/models/cv/classification/mvitv2_base/igie/README.md b/models/cv/classification/mvitv2_base/igie/README.md index c6a112ae..b2f018fb 100644 --- a/models/cv/classification/mvitv2_base/igie/README.md +++ b/models/cv/classification/mvitv2_base/igie/README.md @@ -1,12 +1,12 @@ # MViTv2-base -## Description +## Model Description MViTv2_base is an efficient multi-scale vision Transformer model designed specifically for image classification tasks. By employing a multi-scale structure and hierarchical representation, it effectively captures both global and local image features while maintaining computational efficiency. The MViTv2_base has demonstrated excellent performance on multiple standard datasets and is suitable for a variety of visual recognition tasks. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash # Install libGL @@ -18,7 +18,7 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -38,7 +38,7 @@ onnxsim mvitv2_base.onnx mvitv2_base_opt.onnx ``` -## Inference +## Model Inference ```bash export DATASETS_DIR=/Path/to/imagenet_val/ @@ -53,12 +53,12 @@ bash scripts/infer_mvitv2_base_fp16_accuracy.sh bash scripts/infer_mvitv2_base_fp16_performance.sh ``` -## Results +## Model Results | Model | BatchSize | Precision | FPS | Top-1(%) | Top-5(%) | | ----------- | --------- | --------- | -------- | -------- | -------- | | MViTv2-base | 16 | FP16 | 58.76 | 84.226 | 96.848 | -## Reference +## References MViTv2-base: diff --git a/models/cv/classification/regnet_x_16gf/igie/README.md b/models/cv/classification/regnet_x_16gf/igie/README.md index a79be028..84b2957c 100644 --- a/models/cv/classification/regnet_x_16gf/igie/README.md +++ b/models/cv/classification/regnet_x_16gf/igie/README.md @@ -1,19 +1,19 @@ # RegNet_x_16gf -## Description +## Model Description RegNet_x_16gf is a deep convolutional neural network from the RegNet family, introduced in the paper "Designing Network Design Spaces" by Facebook AI. RegNet models emphasize simplicity, efficiency, and scalability, and they systematically explore design spaces to achieve optimal performance.The x in RegNet_x_16gf indicates it belongs to the RegNetX series, which focuses on optimizing network width and depth, while 16gf refers to its computational complexity of approximately 16 GFLOPs. The model features linear width scaling, group convolutions, and bottleneck blocks, providing high accuracy while maintaining computational efficiency. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -25,7 +25,7 @@ Dataset: to download the validation dat python3 export.py --weight regnet_x_16gf-2007eb11.pth --output regnet_x_16gf.onnx ``` -## Inference +## Model Inference ```bash export DATASETS_DIR=/Path/to/imagenet_val/ @@ -40,7 +40,7 @@ bash scripts/infer_regnet_x_16gf_fp16_accuracy.sh bash scripts/infer_regnet_x_16gf_fp16_performance.sh ``` -## Results +## Model Results Model |BatchSize |Precision |FPS |Top-1(%) |Top-5(%) ------------------|-----------|----------|---------|---------|-------- diff --git a/models/cv/classification/regnet_x_1_6gf/igie/README.md b/models/cv/classification/regnet_x_1_6gf/igie/README.md index faa39d56..4d4e84bc 100644 --- a/models/cv/classification/regnet_x_1_6gf/igie/README.md +++ b/models/cv/classification/regnet_x_1_6gf/igie/README.md @@ -1,18 +1,18 @@ # RegNet_x_1_6gf -## Description +## Model Description RegNet is a family of models designed for image classification tasks, as described in the paper "Designing Network Design Spaces". The RegNet design space provides simple and fast networks that work well across a wide range of computational budgets.The architecture of RegNet models is based on the principle of designing network design spaces, which allows for a more systematic exploration of possible network architectures. This makes it easier to understand and modify the architecture.RegNet_x_1_6gf is a specific model within the RegNet family, designed for image classification tasks -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -24,7 +24,7 @@ Dataset: to download the validation dat python3 export.py --weight regnet_x_1_6gf-a12f2b72.pth --output regnet_x_1_6gf.onnx ``` -## Inference +## Model Inference ```bash export DATASETS_DIR=/Path/to/imagenet_val/ @@ -39,7 +39,7 @@ bash scripts/infer_regnet_x_1_6gf_fp16_accuracy.sh bash scripts/infer_regnet_x_1_6gf_fp16_performance.sh ``` -## Results +## Model Results Model |BatchSize |Precision |FPS |Top-1(%) |Top-5(%) ------------------|-----------|----------|---------|---------|-------- diff --git a/models/cv/classification/regnet_y_1_6gf/igie/README.md b/models/cv/classification/regnet_y_1_6gf/igie/README.md index 189da9c8..35244009 100644 --- a/models/cv/classification/regnet_y_1_6gf/igie/README.md +++ b/models/cv/classification/regnet_y_1_6gf/igie/README.md @@ -1,18 +1,18 @@ # RegNet_y_1_6gf -## Description +## Model Description RegNet is a family of models designed for image classification tasks, as described in the paper "Designing Network Design Spaces". The RegNet design space provides simple and fast networks that work well across a wide range of computational budgets.The architecture of RegNet models is based on the principle of designing network design spaces, which allows for a more systematic exploration of possible network architectures. This makes it easier to understand and modify the architecture.RegNet_y_1_6gf is a specific model within the RegNet family, designed for image classification tasks. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -24,7 +24,7 @@ Dataset: to download the validation dat python3 export.py --weight regnet_y_1_6gf-b11a554e.pth --output regnet_y_1_6gf.onnx ``` -## Inference +## Model Inference ```bash export DATASETS_DIR=/Path/to/imagenet_val/ @@ -39,7 +39,7 @@ bash scripts/infer_regnet_y_1_6gf_fp16_accuracy.sh bash scripts/infer_regnet_y_1_6gf_fp16_performance.sh ``` -## Results +## Model Results | Model | BatchSize | Precision | FPS | Top-1(%) | Top-5(%) | | -------------- | --------- | --------- | ------- | -------- | -------- | diff --git a/models/cv/classification/repvgg/igie/README.md b/models/cv/classification/repvgg/igie/README.md index 0f02b88d..9ff0b997 100644 --- a/models/cv/classification/repvgg/igie/README.md +++ b/models/cv/classification/repvgg/igie/README.md @@ -1,12 +1,12 @@ # RepVGG -## Description +## Model Description RepVGG is an innovative convolutional neural network architecture that combines the simplicity of VGG-style inference with a multi-branch topology during training. Through structural re-parameterization, RepVGG achieves high accuracy while significantly improving computational efficiency. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash # Install libGL @@ -18,7 +18,7 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -35,7 +35,7 @@ python3 export.py --cfg mmpretrain/configs/repvgg/repvgg-A0_4xb64-coslr-120e_in1 ``` -## Inference +## Model Inference ```bash export DATASETS_DIR=/Path/to/imagenet_val/ @@ -50,12 +50,12 @@ bash scripts/infer_repvgg_fp16_accuracy.sh bash scripts/infer_repvgg_fp16_performance.sh ``` -## Results +## Model Results | Model | BatchSize | Precision | FPS | Top-1(%) | Top-5(%) | | ------ | --------- | --------- | -------- | -------- | -------- | | RepVGG | 32 | FP16 | 7423.035 | 72.345 | 90.543 | -## Reference +## References RepVGG: diff --git a/models/cv/classification/repvgg/ixrt/README.md b/models/cv/classification/repvgg/ixrt/README.md index a1b2a363..f920d3b8 100644 --- a/models/cv/classification/repvgg/ixrt/README.md +++ b/models/cv/classification/repvgg/ixrt/README.md @@ -1,13 +1,13 @@ # RepVGG -## Description +## Model Description REPVGG is a family of convolutional neural network (CNN) architectures designed for image classification tasks. It was developed by researchers at the University of Oxford and introduced in their paper titled "REPVGG: Making VGG-style ConvNets Great Again" in 2021. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash # Install libGL @@ -19,7 +19,7 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Dataset: to download the validation dataset. @@ -35,7 +35,7 @@ python3 export_onnx.py \ --output_model ./checkpoints/repvgg_A0.onnx ``` -## Inference +## Model Inference ```bash export PROJ_DIR=./ @@ -55,7 +55,7 @@ bash scripts/infer_repvgg_fp16_accuracy.sh bash scripts/infer_repvgg_fp16_performance.sh ``` -## Results +## Model Results | Model | BatchSize | Precision | FPS | Top-1(%) | Top-5(%) | | ------ | --------- | --------- | ------- | -------- | -------- | diff --git a/models/cv/classification/res2net50/igie/README.md b/models/cv/classification/res2net50/igie/README.md index eb698705..aad8a6ae 100644 --- a/models/cv/classification/res2net50/igie/README.md +++ b/models/cv/classification/res2net50/igie/README.md @@ -1,12 +1,12 @@ # Res2Net50 -## Description +## Model Description Res2Net50 is a convolutional neural network architecture that introduces the concept of "Residual-Residual Networks" (Res2Nets) to enhance feature representation and model expressiveness, particularly in image recognition tasks.The key innovation of Res2Net50 lies in its hierarchical feature aggregation mechanism, which enables the network to capture multi-scale features more effectively. Unlike traditional ResNet architectures, Res2Net50 incorporates multiple parallel pathways within each residual block, allowing the network to dynamically adjust the receptive field size and aggregate features across different scales. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash # Install libGL @@ -18,7 +18,7 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -38,7 +38,7 @@ onnxsim res2net50.onnx res2net50_opt.onnx ``` -## Inference +## Model Inference ```bash export DATASETS_DIR=/Path/to/imagenet_val/ @@ -53,12 +53,12 @@ bash scripts/infer_res2net50_fp16_accuracy.sh bash scripts/infer_res2net50_fp16_performance.sh ``` -## Results +## Model Results Model |BatchSize |Precision |FPS |Top-1(%) |Top-5(%) ----------|-----------|----------|----------|----------|-------- Res2Net50 | 32 | FP16 | 1641.961 | 78.139 | 93.826 -## Reference +## References Res2Net50: diff --git a/models/cv/classification/res2net50/ixrt/README.md b/models/cv/classification/res2net50/ixrt/README.md index 6700543f..05f3fbc2 100644 --- a/models/cv/classification/res2net50/ixrt/README.md +++ b/models/cv/classification/res2net50/ixrt/README.md @@ -1,12 +1,12 @@ # Res2Net50 -## Description +## Model Description A novel building block for CNNs, namely Res2Net, by constructing hierarchical residual-like connections within one single residual block. The Res2Net represents multi-scale features at a granular level and increases the range of receptive fields for each network layer. The proposed Res2Net block can be plugged into the state-of-the-art backbone CNN models, e.g., ResNet, ResNeXt, and DLA. We evaluate the Res2Net block on all these models and demonstrate consistent performance gains over baseline models on widely-used datasets, e.g., CIFAR-100 and ImageNet. Further ablation studies and experimental results on representative computer vision tasks, i.e., object detection, class activation mapping, and salient object detection, further verify the superiority of the Res2Net over the state-of-the-art baseline methods. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash # Install libGL @@ -18,7 +18,7 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -31,7 +31,7 @@ mkdir checkpoints python3 export_onnx.py --origin_model /path/to/res2net50_14w_8s-6527dddc.pth --output_model checkpoints/res2net50.onnx ``` -## Inference +## Model Inference ```bash export PROJ_DIR=./ @@ -59,7 +59,7 @@ bash scripts/infer_res2net50_int8_accuracy.sh bash scripts/infer_res2net50_int8_performance.sh ``` -## Results +## Model Results Model |BatchSize |Precision |FPS |Top-1(%) |Top-5(%) ----------|-----------|----------|----------|---------|-------- diff --git a/models/cv/classification/resnest50/igie/README.md b/models/cv/classification/resnest50/igie/README.md index 21137c42..c18f7bcb 100644 --- a/models/cv/classification/resnest50/igie/README.md +++ b/models/cv/classification/resnest50/igie/README.md @@ -1,12 +1,12 @@ # ResNeSt50 -## Description +## Model Description ResNeSt50 is a deep convolutional neural network model based on the ResNeSt architecture, specifically designed to enhance performance in visual recognition tasks such as image classification, object detection, instance segmentation, and semantic segmentation. ResNeSt stands for Split-Attention Networks, a modular network architecture that leverages channel-wise attention mechanisms across different network branches to capture cross-feature interactions and learn diverse representations. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash # Install libGL @@ -18,7 +18,7 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -35,7 +35,7 @@ onnxsim resnest50.onnx resnest50_opt.onnx ``` -## Inference +## Model Inference ```bash export DATASETS_DIR=/Path/to/imagenet_val/ @@ -50,12 +50,12 @@ bash scripts/infer_resnest50_fp16_accuracy.sh bash scripts/infer_resnest50_fp16_performance.sh ``` -## Results +## Model Results Model |BatchSize |Precision |FPS |Top-1(%) |Top-5(%) ----------|-----------|----------|----------|----------|-------- ResNeSt50 | 32 | FP16 | 344.453 | 80.93 | 95.347 -## Reference +## References ResNeSt50: diff --git a/models/cv/classification/resnet101/igie/README.md b/models/cv/classification/resnet101/igie/README.md index a992f6b1..7c63ec94 100644 --- a/models/cv/classification/resnet101/igie/README.md +++ b/models/cv/classification/resnet101/igie/README.md @@ -1,18 +1,18 @@ # ResNet101 -## Description +## Model Description ResNet101 is a convolutional neural network architecture that belongs to the ResNet (Residual Network) family.With a total of 101 layers, ResNet101 comprises multiple residual blocks, each containing convolutional layers with batch normalization and rectified linear unit (ReLU) activations. These residual blocks allow the network to effectively capture complex features at different levels of abstraction, leading to superior performance on image recognition tasks. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -24,7 +24,7 @@ Dataset: to download the validation dat python3 export.py --weight resnet101-63fe2227.pth --output resnet101.onnx ``` -## Inference +## Model Inference ```bash export DATASETS_DIR=/Path/to/imagenet_val/ @@ -48,7 +48,7 @@ bash scripts/infer_resnet101_int8_accuracy.sh bash scripts/infer_resnet101_int8_performance.sh ``` -## Results +## Model Results Model |BatchSize |Precision |FPS |Top-1(%) |Top-5(%) ----------|-----------|----------|----------|----------|-------- diff --git a/models/cv/classification/resnet101/ixrt/README.md b/models/cv/classification/resnet101/ixrt/README.md index 3869ea55..a11341db 100644 --- a/models/cv/classification/resnet101/ixrt/README.md +++ b/models/cv/classification/resnet101/ixrt/README.md @@ -1,12 +1,12 @@ # Resnet101 -## Description +## Model Description ResNet-101 is a variant of the ResNet (Residual Network) architecture, and it belongs to a family of deep neural networks introduced by Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun in their 2016 paper, "Deep Residual Learning for Image Recognition." The ResNet architecture is known for its effective use of residual connections, which help in training very deep neural networks. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash # Install libGL @@ -18,7 +18,7 @@ apt install -y libgl1-mesa-glx pip3 install -r reuirements.txt ``` -### Download +### Prepare Resources Dataset: to download the validation dataset. @@ -29,7 +29,7 @@ mkdir checkpoints python3 export_onnx.py --output_model checkpoints/resnet101.onnx ``` -## Inference +## Model Inference ```bash export PROJ_DIR=./ @@ -57,7 +57,7 @@ bash scripts/infer_resnet101_int8_accuracy.sh bash scripts/infer_resnet101_int8_performance.sh ``` -## Results +## Model Results Model |BatchSize |Precision |FPS |Top-1(%) |Top-5(%) ----------|-----------|----------|---------|----------|-------- diff --git a/models/cv/classification/resnet152/igie/README.md b/models/cv/classification/resnet152/igie/README.md index 5066e0ca..774ee6aa 100644 --- a/models/cv/classification/resnet152/igie/README.md +++ b/models/cv/classification/resnet152/igie/README.md @@ -1,18 +1,18 @@ # ResNet152 -## Description +## Model Description ResNet152 is a convolutional neural network architecture that is part of the ResNet (Residual Network) family, Comprising 152 layers, At the core of ResNet152 is the innovative residual learning framework, which addresses the challenges associated with training very deep neural networks. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -24,7 +24,7 @@ Dataset: to download the validation dat python3 export.py --weight resnet152-394f9c45.pth --output resnet152.onnx ``` -## Inference +## Model Inference ```bash export DATASETS_DIR=/Path/to/imagenet_val/ @@ -48,7 +48,7 @@ bash scripts/infer_resnet152_int8_accuracy.sh bash scripts/infer_resnet152_int8_performance.sh ``` -## Results +## Model Results Model |BatchSize |Precision |FPS |Top-1(%) |Top-5(%) ----------|-----------|----------|----------|----------|-------- diff --git a/models/cv/classification/resnet18/igie/README.md b/models/cv/classification/resnet18/igie/README.md index 3cdca0c7..6187c315 100644 --- a/models/cv/classification/resnet18/igie/README.md +++ b/models/cv/classification/resnet18/igie/README.md @@ -1,18 +1,18 @@ # ResNet18 -## Description +## Model Description ResNet-18 is a relatively compact deep neural network.The ResNet-18 architecture consists of 18 layers, including convolutional, pooling, and fully connected layers. It incorporates residual blocks, a key innovation that utilizes shortcut connections to facilitate the flow of information through the network. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -24,7 +24,7 @@ Dataset: to download the validation dat python3 export.py --weight resnet18-f37072fd.pth --output resnet18.onnx ``` -## Inference +## Model Inference ```bash export DATASETS_DIR=/Path/to/imagenet_val/ @@ -48,7 +48,7 @@ bash scripts/infer_resnet18_int8_accuracy.sh bash scripts/infer_resnet18_int8_performance.sh ``` -## Results +## Model Results Model |BatchSize |Precision |FPS |Top-1(%) |Top-5(%) ---------|-----------|----------|----------|----------|-------- diff --git a/models/cv/classification/resnet18/ixrt/README.md b/models/cv/classification/resnet18/ixrt/README.md index 84ce36f6..c385ac35 100644 --- a/models/cv/classification/resnet18/ixrt/README.md +++ b/models/cv/classification/resnet18/ixrt/README.md @@ -1,12 +1,12 @@ # Resnet18 -## Description +## Model Description ResNet-18 is a variant of the ResNet (Residual Network) architecture, which was introduced by Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun in their 2016 paper, "Deep Residual Learning for Image Recognition." The ResNet architecture was pivotal in addressing the challenges of training very deep neural networks by introducing residual blocks. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash # Install libGL @@ -18,7 +18,7 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -31,7 +31,7 @@ mkdir checkpoints python3 export_onnx.py --origin_model /path/to/resnet18-f37072fd.pth --output_model checkpoints/resnet18.onnx ``` -## Inference +## Model Inference ```bash export PROJ_DIR=./ @@ -59,7 +59,7 @@ bash scripts/infer_resnet18_int8_accuracy.sh bash scripts/infer_resnet18_int8_performance.sh ``` -## Results +## Model Results Model |BatchSize |Precision |FPS |Top-1(%) |Top-5(%) ---------|-----------|----------|----------|----------|-------- diff --git a/models/cv/classification/resnet34/ixrt/README.md b/models/cv/classification/resnet34/ixrt/README.md index 48df97d3..8ab2b34a 100644 --- a/models/cv/classification/resnet34/ixrt/README.md +++ b/models/cv/classification/resnet34/ixrt/README.md @@ -1,12 +1,12 @@ # ResNet34 -## Description +## Model Description Residual Networks, or ResNets, learn residual functions with reference to the layer inputs, instead of learning unreferenced functions. Instead of hoping each few stacked layers directly fit a desired underlying mapping, residual nets let these layers fit a residual mapping. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash # Install libGL @@ -18,7 +18,7 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Dataset: to download the validation dataset. @@ -29,7 +29,7 @@ mkdir checkpoints python3 export_onnx.py --output_model checkpoints/resnet34.onnx ``` -## Inference +## Model Inference ```bash export PROJ_DIR=./ @@ -57,7 +57,7 @@ bash scripts/infer_resnet34_int8_accuracy.sh bash scripts/infer_resnet34_int8_performance.sh ``` -## Results +## Model Results Model |BatchSize |Precision |FPS |Top-1(%) |Top-5(%) ---------|-----------|----------|----------|----------|-------- diff --git a/models/cv/classification/resnet50/igie/README.md b/models/cv/classification/resnet50/igie/README.md index 1d670729..6820f2cb 100644 --- a/models/cv/classification/resnet50/igie/README.md +++ b/models/cv/classification/resnet50/igie/README.md @@ -1,18 +1,18 @@ # ResNet50 -## Description +## Model Description ResNet-50 is a convolutional neural network architecture that belongs to the ResNet.The key innovation in ResNet-50 is the introduction of residual blocks, which include shortcut connections (skip connections) to enable the flow of information directly from one layer to another. These shortcut connections help mitigate the vanishing gradient problem and facilitate the training of very deep networks. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -24,7 +24,7 @@ Dataset: to download the validation dat python3 export.py --weight resnet50-0676ba61.pth --output resnet50.onnx ``` -## Inference +## Model Inference ```bash export DATASETS_DIR=/Path/to/imagenet_val/ @@ -48,7 +48,7 @@ bash scripts/infer_resnet50_int8_accuracy.sh bash scripts/infer_resnet50_int8_performance.sh ``` -## Results +## Model Results Model |BatchSize |Precision |FPS |Top-1(%) |Top-5(%) ---------|-----------|----------|----------|----------|-------- diff --git a/models/cv/classification/resnet50/ixrt/README.md b/models/cv/classification/resnet50/ixrt/README.md index 0d5fc9fa..c9e1ae9c 100644 --- a/models/cv/classification/resnet50/ixrt/README.md +++ b/models/cv/classification/resnet50/ixrt/README.md @@ -1,12 +1,12 @@ # ResNet50 -## Description +## Model Description Residual Networks, or ResNets, learn residual functions with reference to the layer inputs, instead of learning unreferenced functions. Instead of hoping each few stacked layers directly fit a desired underlying mapping, residual nets let these layers fit a residual mapping. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash # Install libGL @@ -18,7 +18,7 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -31,7 +31,7 @@ mkdir checkpoints python3 export_onnx.py --origin_model /path/to/resnet50-0676ba61.pth --output_model checkpoints/resnet50.onnx ``` -## Inference +## Model Inference ```bash export DATASETS_DIR=/path/to/imagenet_val/ @@ -58,7 +58,7 @@ bash scripts/infer_resnet50_int8_accuracy.sh bash scripts/infer_resnet50_int8_performance.sh ``` -## Results +## Model Results | Model | BatchSize | Precision | FPS | Top-1(%) | Top-5(%) | | -------- | --------- | --------- | ------- | -------- | -------- | diff --git a/models/cv/classification/resnetv1d50/igie/README.md b/models/cv/classification/resnetv1d50/igie/README.md index f2528479..a5d42f87 100644 --- a/models/cv/classification/resnetv1d50/igie/README.md +++ b/models/cv/classification/resnetv1d50/igie/README.md @@ -1,12 +1,12 @@ # ResNetV1D50 -## Description +## Model Description ResNetV1D50 is an enhanced version of ResNetV1-50 that incorporates changes like dilated convolutions and adjusted downsampling, leading to better performance in large-scale image classification tasks. Its ability to capture richer image features makes it a popular choice in deep learning models. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash # Install libGL @@ -18,7 +18,7 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -35,7 +35,7 @@ python3 export.py --cfg mmpretrain/configs/resnet/resnetv1d50_b32x8_imagenet.py ``` -## Inference +## Model Inference ```bash export DATASETS_DIR=/Path/to/imagenet_val/ @@ -50,12 +50,12 @@ bash scripts/infer_resnetv1d50_fp16_accuracy.sh bash scripts/infer_resnetv1d50_fp16_performance.sh ``` -## Results +## Model Results | Model | BatchSize | Precision | FPS | Top-1(%) | Top-5(%) | | ----------- | --------- | --------- | -------- | -------- | -------- | | ResNetV1D50 | 32 | FP16 | 4017.92 | 77.517 | 93.538 | -## Reference +## References ResNetV1D50: diff --git a/models/cv/classification/resnetv1d50/ixrt/README.md b/models/cv/classification/resnetv1d50/ixrt/README.md index 7445f458..d333342f 100644 --- a/models/cv/classification/resnetv1d50/ixrt/README.md +++ b/models/cv/classification/resnetv1d50/ixrt/README.md @@ -1,12 +1,12 @@ # ResNetV1D50 -## Description +## Model Description Residual Networks, or ResNets, learn residual functions with reference to the layer inputs, instead of learning unreferenced functions. Instead of hoping each few stacked layers directly fit a desired underlying mapping, residual nets let these layers fit a residual mapping. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash # Install libGL @@ -18,7 +18,7 @@ apt install -y libgl1-mesa-glx pip3 install -r requirments.txt ``` -### Download +### Prepare Resources Dataset: to download the validation dataset. @@ -29,7 +29,7 @@ mkdir checkpoints python3 export_onnx.py --output_model checkpoints/resnet_v1_d50.onnx ``` -## Inference +## Model Inference ```bash export DATASETS_DIR=/path/to/imagenet_val/ @@ -56,7 +56,7 @@ bash scripts/infer_resnetv1d50_int8_accuracy.sh bash scripts/infer_resnetv1d50_int8_performance.sh ``` -## Results +## Model Results | Model | BatchSize | Precision | FPS | Top-1(%) | Top-5(%) | | ------------- | --------- | --------- | ------- | -------- | -------- | diff --git a/models/cv/classification/resnext101_32x8d/igie/README.md b/models/cv/classification/resnext101_32x8d/igie/README.md index 84f7a1d3..fad1347d 100644 --- a/models/cv/classification/resnext101_32x8d/igie/README.md +++ b/models/cv/classification/resnext101_32x8d/igie/README.md @@ -1,18 +1,18 @@ # ResNext101_32x8d -## Description +## Model Description ResNeXt101_32x8d is a deep convolutional neural network introduced in the paper "Aggregated Residual Transformations for Deep Neural Networks." It enhances the traditional ResNet architecture by incorporating group convolutions, offering a new dimension for scaling network capacity through "cardinality" (the number of groups) rather than merely increasing depth or width.The model consists of 101 layers and uses a configuration of 32 groups, each with a width of 8 channels. This design improves feature extraction while maintaining computational efficiency. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -24,7 +24,7 @@ Dataset: to download the validation dat python3 export.py --weight resnext101_32x8d-8ba56ff5.pth --output resnext101_32x8d.onnx ``` -## Inference +## Model Inference ```bash export DATASETS_DIR=/Path/to/imagenet_val/ @@ -39,7 +39,7 @@ bash scripts/infer_resnext101_32x8d_fp16_accuracy.sh bash scripts/infer_resnext101_32x8d_fp16_performance.sh ``` -## Results +## Model Results | Model | BatchSize | Precision | FPS | Top-1(%) | Top-5(%) | | ---------------- | --------- | --------- | ------ | -------- | -------- | diff --git a/models/cv/classification/resnext101_64x4d/igie/README.md b/models/cv/classification/resnext101_64x4d/igie/README.md index 3d804238..4504632c 100644 --- a/models/cv/classification/resnext101_64x4d/igie/README.md +++ b/models/cv/classification/resnext101_64x4d/igie/README.md @@ -1,18 +1,18 @@ # ResNext101_64x4d -## Description +## Model Description The ResNeXt101_64x4d is a deep learning model based on the deep residual network architecture, which enhances performance and efficiency through the use of grouped convolutions. With a depth of 101 layers and 64 filter groups, it is particularly suited for complex image recognition tasks. While maintaining excellent accuracy, it can adapt to various input sizes -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -24,7 +24,7 @@ Dataset: to download the validation dat python3 export.py --weight resnext101_64x4d-173b62eb.pth --output resnext101_64x4d.onnx ``` -## Inference +## Model Inference ```bash export DATASETS_DIR=/Path/to/imagenet_val/ @@ -39,7 +39,7 @@ bash scripts/infer_resnext101_64x4d_fp16_accuracy.sh bash scripts/infer_resnext101_64x4d_fp16_performance.sh ``` -## Results +## Model Results | Model | BatchSize | Precision | FPS | Top-1(%) | Top-5(%) | | ---------------- | --------- | --------- | ------ | -------- | -------- | diff --git a/models/cv/classification/resnext50_32x4d/igie/README.md b/models/cv/classification/resnext50_32x4d/igie/README.md index a90b47c7..0ec8da3c 100644 --- a/models/cv/classification/resnext50_32x4d/igie/README.md +++ b/models/cv/classification/resnext50_32x4d/igie/README.md @@ -1,18 +1,18 @@ # ResNext50_32x4d -## Description +## Model Description The ResNeXt50_32x4d model is a convolutional neural network architecture designed for image classification tasks. It is an extension of the ResNet (Residual Network) architecture, incorporating the concept of cardinality to enhance model performance. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -24,7 +24,7 @@ Dataset: to download the validation dat python3 export.py --weight resnext50_32x4d-7cdf4587.pth --output resnext50_32x4d.onnx ``` -## Inference +## Model Inference ```bash export DATASETS_DIR=/Path/to/imagenet_val/ @@ -39,7 +39,7 @@ bash scripts/infer_resnext50_32x4d_fp16_accuracy.sh bash scripts/infer_resnext50_32x4d_fp16_performance.sh ``` -## Results +## Model Results Model |BatchSize |Precision |FPS |Top-1(%) |Top-5(%) ----------------|-----------|----------|---------|----------|-------- diff --git a/models/cv/classification/resnext50_32x4d/ixrt/README.md b/models/cv/classification/resnext50_32x4d/ixrt/README.md index 0c7ed2fe..9a2fc061 100644 --- a/models/cv/classification/resnext50_32x4d/ixrt/README.md +++ b/models/cv/classification/resnext50_32x4d/ixrt/README.md @@ -1,18 +1,18 @@ # ResNext50_32x4d -## Description +## Model Description The ResNeXt50_32x4d model is a convolutional neural network architecture designed for image classification tasks. It is an extension of the ResNet (Residual Network) architecture, incorporating the concept of cardinality to enhance model performance. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -24,7 +24,7 @@ Dataset: to download the validation dat python3 export.py --weight resnext50_32x4d-7cdf4587.pth --output resnext50_32x4d.onnx ``` -## Inference +## Model Inference ```bash export DATASETS_DIR=/Path/to/imagenet_val/ @@ -39,7 +39,7 @@ bash scripts/infer_resnext50_32x4d_fp16_accuracy.sh bash scripts/infer_resnext50_32x4d_fp16_performance.sh ``` -## Results +## Model Results | Model | BatchSize | Precision | FPS | Top-1(%) | Top-5(%) | | --------------- | --------- | --------- | ------ | -------- | -------- | diff --git a/models/cv/classification/seresnet50/igie/README.md b/models/cv/classification/seresnet50/igie/README.md index ddd891ec..a89fdefe 100644 --- a/models/cv/classification/seresnet50/igie/README.md +++ b/models/cv/classification/seresnet50/igie/README.md @@ -1,12 +1,12 @@ # SEResNet50 -## Description +## Model Description SEResNet50 is an enhanced version of the ResNet50 network integrated with Squeeze-and-Excitation (SE) blocks, which strengthens the network's feature expression capability by explicitly emphasizing useful features and suppressing irrelevant ones. This improvement enables SEResNet50 to demonstrate higher accuracy in various visual recognition tasks compared to the standard ResNet50. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash # Install libGL @@ -18,7 +18,7 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -35,7 +35,7 @@ python3 export.py --cfg mmpretrain/configs/seresnet/seresnet50_8xb32_in1k.py --w ``` -## Inference +## Model Inference ```bash export DATASETS_DIR=/Path/to/imagenet_val/ @@ -50,12 +50,12 @@ bash scripts/infer_seresnet_fp16_accuracy.sh bash scripts/infer_seresnet_fp16_performance.sh ``` -## Results +## Model Results | Model | BatchSize | Precision | FPS | Top-1(%) | Top-5(%) | | ---------- | --------- | --------- | -------- | -------- | -------- | | SEResNet50 | 32 | FP16 | 2548.268 | 77.709 | 93.812 | -## Reference +## References SE_ResNet50: diff --git a/models/cv/classification/shufflenet_v1/ixrt/README.md b/models/cv/classification/shufflenet_v1/ixrt/README.md index ae50050c..b863e00a 100644 --- a/models/cv/classification/shufflenet_v1/ixrt/README.md +++ b/models/cv/classification/shufflenet_v1/ixrt/README.md @@ -1,13 +1,13 @@ # ShuffleNetV1 -## Description +## Model Description ShuffleNet V1 is a lightweight neural network architecture primarily used for image classification and object detection tasks. It uses techniques such as deep separable convolution and channel shuffle to reduce the number of parameters and computational complexity of the model, thereby achieving low computational resource consumption while maintaining high accuracy. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash # Install libGL @@ -19,7 +19,7 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -37,7 +37,7 @@ python3 export_onnx.py \ --output_model ./checkpoints/shufflenet_v1.onnx ``` -## Inference +## Model Inference ```bash export PROJ_DIR=./ @@ -57,7 +57,7 @@ bash scripts/infer_shufflenet_v1_fp16_accuracy.sh bash scripts/infer_shufflenet_v1_fp16_performance.sh ``` -## Results +## Model Results Model |BatchSize |Precision |FPS |Top-1(%) |Top-5(%) -------------|-----------|----------|---------|----------|-------- diff --git a/models/cv/classification/shufflenetv2_x0_5/igie/README.md b/models/cv/classification/shufflenetv2_x0_5/igie/README.md index 52d580b4..068b944c 100644 --- a/models/cv/classification/shufflenetv2_x0_5/igie/README.md +++ b/models/cv/classification/shufflenetv2_x0_5/igie/README.md @@ -1,18 +1,18 @@ # ShuffleNetV2_x0_5 -## Description +## Model Description ShuffleNetV2_x0_5 is a lightweight convolutional neural network architecture designed for efficient image classification and feature extraction, it also incorporates other design optimizations such as depthwise separable convolutions, group convolutions, and efficient building blocks to further reduce computational complexity and improve efficiency. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -24,7 +24,7 @@ Dataset: to download the validation dat python3 export.py --weight shufflenetv2_x0.5-f707e7126e.pth --output shufflenetv2_x0_5.onnx ``` -## Inference +## Model Inference ```bash export DATASETS_DIR=/Path/to/imagenet_val/ @@ -39,7 +39,7 @@ bash scripts/infer_shufflenetv2_x0_5_fp16_accuracy.sh bash scripts/infer_shufflenetv2_x0_5_fp16_performance.sh ``` -## Results +## Model Results Model |BatchSize |Precision |FPS |Top-1(%) |Top-5(%) ------------------|-----------|----------|----------|----------|-------- diff --git a/models/cv/classification/shufflenetv2_x1_0/igie/README.md b/models/cv/classification/shufflenetv2_x1_0/igie/README.md index 6ffc7200..20586720 100644 --- a/models/cv/classification/shufflenetv2_x1_0/igie/README.md +++ b/models/cv/classification/shufflenetv2_x1_0/igie/README.md @@ -1,18 +1,18 @@ # ShuffleNetV2_x1_0 -## Description +## Model Description ShuffleNet V2_x1_0 is an efficient convolutional neural network (CNN) architecture that emphasizes a balance between computational efficiency and accuracy, particularly suited for deployment on mobile and embedded devices. The model refines the ShuffleNet series by introducing structural innovations that enhance feature reuse and reduce redundancy, all while maintaining simplicity and performance. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -24,7 +24,7 @@ Dataset: to download the validation dat python3 export.py --weight shufflenetv2_x1-5666bf0f80.pth --output shufflenetv2_x1_0.onnx ``` -## Inference +## Model Inference ```bash export DATASETS_DIR=/Path/to/imagenet_val/ @@ -39,7 +39,7 @@ bash scripts/infer_shufflenetv2_x1_0_fp16_accuracy.sh bash scripts/infer_shufflenetv2_x1_0_fp16_performance.sh ``` -## Results +## Model Results | Model | BatchSize | Precision | FPS | Top-1(%) | Top-5(%) | | ----------------- | --------- | --------- | -------- | -------- | -------- | diff --git a/models/cv/classification/shufflenetv2_x1_5/igie/README.md b/models/cv/classification/shufflenetv2_x1_5/igie/README.md index f882d3b8..7e6dfb38 100644 --- a/models/cv/classification/shufflenetv2_x1_5/igie/README.md +++ b/models/cv/classification/shufflenetv2_x1_5/igie/README.md @@ -1,18 +1,18 @@ # ShuffleNetV2_x1_5 -## Description +## Model Description ShuffleNetV2_x1_5 is a lightweight convolutional neural network specifically designed for efficient image recognition tasks on resource-constrained devices. It achieves high performance and low latency through the introduction of channel shuffling and pointwise group convolutions. Despite its small model size, it offers high accuracy and is suitable for a variety of vision tasks in mobile devices and embedded systems. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -24,7 +24,7 @@ Dataset: to download the validation dat python3 export.py --weight shufflenetv2_x1_5-3c479a10.pth --output shufflenetv2_x1_5.onnx ``` -## Inference +## Model Inference ```bash export DATASETS_DIR=/Path/to/imagenet_val/ @@ -39,7 +39,7 @@ bash scripts/infer_shufflenetv2_x1_5_fp16_accuracy.sh bash scripts/infer_shufflenetv2_x1_5_fp16_performance.sh ``` -## Results +## Model Results | Model | BatchSize | Precision | FPS | Top-1(%) | Top-5(%) | | ----------------- | --------- | --------- | -------- | -------- | -------- | diff --git a/models/cv/classification/shufflenetv2_x2_0/igie/README.md b/models/cv/classification/shufflenetv2_x2_0/igie/README.md index dac24a22..51e4222e 100644 --- a/models/cv/classification/shufflenetv2_x2_0/igie/README.md +++ b/models/cv/classification/shufflenetv2_x2_0/igie/README.md @@ -1,18 +1,18 @@ # ShuffleNetV2_x2_0 -## Description +## Model Description ShuffleNetV2_x2_0 is a lightweight convolutional neural network introduced in the paper "ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design" by Megvii (Face++). It is designed to achieve high performance with low computational cost, making it ideal for mobile and embedded devices.The x2_0 in its name indicates a width multiplier of 2.0, meaning the model has twice as many channels compared to the baseline ShuffleNetV2_x1_0. It employs Channel Shuffle to enable efficient information exchange between grouped convolutions, addressing the limitations of group convolutions. The core building block, the ShuffleNetV2 block, features a split-merge design and channel shuffle mechanism, ensuring both high efficiency and accuracy. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -24,7 +24,7 @@ Dataset: to download the validation dat python3 export.py --weight shufflenetv2_x2_0-8be3c8ee.pth --output shufflenetv2_x2_0.onnx ``` -## Inference +## Model Inference ```bash export DATASETS_DIR=/Path/to/imagenet_val/ @@ -39,7 +39,7 @@ bash scripts/infer_shufflenetv2_x2_0_fp16_accuracy.sh bash scripts/infer_shufflenetv2_x2_0_fp16_performance.sh ``` -## Results +## Model Results | Model | BatchSize | Precision | FPS | Top-1(%) | Top-5(%) | | ----------------- | --------- | --------- | -------- | -------- | -------- | diff --git a/models/cv/classification/squeezenet_v1_0/igie/README.md b/models/cv/classification/squeezenet_v1_0/igie/README.md index a3555dd8..8cb0dd5b 100644 --- a/models/cv/classification/squeezenet_v1_0/igie/README.md +++ b/models/cv/classification/squeezenet_v1_0/igie/README.md @@ -1,18 +1,18 @@ # SqueezeNet1_0 -## Description +## Model Description SqueezeNet1_0 is a lightweight convolutional neural network introduced in the paper "SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size." It was designed to achieve high classification accuracy with significantly fewer parameters, making it highly efficient for resource-constrained environments.The core innovation of SqueezeNet lies in the Fire Module, which reduces parameters using 1x1 convolutions in the "Squeeze layer" and expands feature maps through a mix of 1x1 and 3x3 convolutions in the "Expand layer." Additionally, delayed downsampling improves feature representation and accuracy. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -24,7 +24,7 @@ Dataset: to download the validation dat python3 export.py --weight squeezenet1_0-b66bff10.pth --output squeezenet1_0.onnx ``` -## Inference +## Model Inference ```bash export DATASETS_DIR=/Path/to/imagenet_val/ @@ -39,7 +39,7 @@ bash scripts/infer_squeezenet_v1_0_fp16_accuracy.sh bash scripts/infer_squeezenet_v1_0_fp16_performance.sh ``` -## Results +## Model Results Model |BatchSize |Precision |FPS |Top-1(%) |Top-5(%) ----------------|-----------|----------|----------|----------|-------- diff --git a/models/cv/classification/squeezenet_v1_0/ixrt/README.md b/models/cv/classification/squeezenet_v1_0/ixrt/README.md index faea4b18..c2180f7b 100644 --- a/models/cv/classification/squeezenet_v1_0/ixrt/README.md +++ b/models/cv/classification/squeezenet_v1_0/ixrt/README.md @@ -1,14 +1,14 @@ # SqueezeNet 1.0 -## Description +## Model Description SqueezeNet 1.0 is a deep learning model for image classification, designed to be lightweight and efficient for deployment on resource-constrained devices. It was developed by researchers at DeepScale and released in 2016. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash # Install libGL @@ -20,7 +20,7 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -33,7 +33,7 @@ mkdir checkpoints python3 export_onnx.py --origin_model /path/to/squeezenet1_0-b66bff10.pth --output_model checkpoints/squeezenetv10.onnx ``` -## Inference +## Model Inference ```bash export PROJ_DIR=./ @@ -61,7 +61,7 @@ bash scripts/infer_squeezenet_v1_0_int8_accuracy.sh bash scripts/infer_squeezenet_v1_0_int8_performance.sh ``` -## Results +## Model Results Model |BatchSize |Precision |FPS |Top-1(%) |Top-5(%) ---------------|-----------|----------|---------|----------|-------- diff --git a/models/cv/classification/squeezenet_v1_1/ixrt/README.md b/models/cv/classification/squeezenet_v1_1/ixrt/README.md index ada0742a..c3678a40 100644 --- a/models/cv/classification/squeezenet_v1_1/ixrt/README.md +++ b/models/cv/classification/squeezenet_v1_1/ixrt/README.md @@ -1,14 +1,14 @@ # SqueezeNet 1.1 -## Description +## Model Description SqueezeNet 1.1 is a deep learning model for image classification, designed to be lightweight and efficient for deployment on resource-constrained devices. It was developed by researchers at DeepScale and released in 2016. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash # Install libGL @@ -20,7 +20,7 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -33,7 +33,7 @@ mkdir checkpoints python3 export_onnx.py --origin_model /path/to/squeezenet1_1-b8a52dc0.pth --output_model checkpoints/squeezenet_v1_1.onnx ``` -## Inference +## Model Inference ```bash export PROJ_DIR=./ @@ -62,7 +62,7 @@ bash scripts/infer_squeezenet_v1_1_int8_accuracy.sh bash scripts/infer_squeezenet_v1_1_int8_performance.sh ``` -## Results +## Model Results | Model | BatchSize | Precision | FPS | Top-1(%) | Top-5(%) | | -------------- | --------- | --------- | ----- | -------- | -------- | diff --git a/models/cv/classification/svt_base/igie/README.md b/models/cv/classification/svt_base/igie/README.md index 26d020d0..30739d9a 100644 --- a/models/cv/classification/svt_base/igie/README.md +++ b/models/cv/classification/svt_base/igie/README.md @@ -1,12 +1,12 @@ # SVT Base -## Description +## Model Description SVT Base is a mid-sized variant of the Sparse Vision Transformer (SVT) series, designed to combine the expressive power of Vision Transformers (ViTs) with the efficiency of sparse attention mechanisms. By employing sparse attention and multi-stage feature extraction, SVT-Base reduces computational complexity while retaining global modeling capabilities. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash # Install libGL @@ -18,7 +18,7 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -37,7 +37,7 @@ python3 export.py --cfg mmpretrain/configs/twins/twins-svt-base_8xb128_in1k.py - onnxsim svt_base.onnx svt_base_opt.onnx ``` -## Inference +## Model Inference ```bash export DATASETS_DIR=/Path/to/imagenet_val/ @@ -52,12 +52,12 @@ bash scripts/infer_svt_base_fp16_accuracy.sh bash scripts/infer_svt_base_fp16_performance.sh ``` -## Results +## Model Results | Model | BatchSize | Precision | FPS | Top-1(%) | Top-5(%) | | ----------| --------- | --------- | -------- | -------- | -------- | | SVT Base | 32 | FP16 | 673.165 | 82.865 | 96.213 | -## Reference +## References SVT Base: diff --git a/models/cv/classification/swin_transformer/igie/README.md b/models/cv/classification/swin_transformer/igie/README.md index aafdbc70..17a5b3e9 100644 --- a/models/cv/classification/swin_transformer/igie/README.md +++ b/models/cv/classification/swin_transformer/igie/README.md @@ -1,18 +1,18 @@ # Swin Transformer -## Description +## Model Description Swin Transformer is a pioneering neural network architecture that introduces a novel approach to handling local and global information in computer vision tasks. Departing from traditional self-attention mechanisms, Swin Transformer adopts a hierarchical design, organizing its attention windows in a shifted manner. This innovation enables more efficient modeling of contextual information across different scales, enhancing the model's capability to capture intricate patterns. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -32,7 +32,7 @@ python3 export.py --output swin_transformer.onnx onnxsim swin_transformer.onnx swin_transformer_opt.onnx ``` -## Inference +## Model Inference ```bash export DATASETS_DIR=/Path/to/imagenet_val/ @@ -47,7 +47,7 @@ bash scripts/infer_swin_transformer_fp16_accuracy.sh bash scripts/infer_swin_transformer_fp16_performance.sh ``` -## Results +## Model Results Model |BatchSize |Precision |FPS |Top-1(%) |Top-5(%) -----------------|-----------|----------|----------|----------|-------- diff --git a/models/cv/classification/swin_transformer_large/ixrt/README.md b/models/cv/classification/swin_transformer_large/ixrt/README.md index e6cf19d4..6702a234 100644 --- a/models/cv/classification/swin_transformer_large/ixrt/README.md +++ b/models/cv/classification/swin_transformer_large/ixrt/README.md @@ -1,12 +1,12 @@ # Swin Transformer Large -## Description +## Model Description Swin Transformer-Large is a variant of the Swin Transformer, an architecture designed for computer vision tasks, particularly within the realms of image classification, object detection, and segmentation. The Swin Transformer-Large model represents an expanded version with more layers and parameters compared to its base configuration, aiming for improved performance and deeper processing of visual data. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash export PROJ_ROOT=/PATH/TO/DEEPSPARKINFERENCE @@ -18,7 +18,7 @@ apt install -y libnuma-dev libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -42,7 +42,7 @@ python3 torch2onnx.py --model_path ./general_perf/model_zoo/popular/swin-large/s ``` -## Inference +## Model Inference ```bash git clone https://gitee.com/deep-spark/iluvatar-corex-ixrt.git --depth=1 @@ -83,7 +83,7 @@ wget -O workloads/swin-large-torch-fp32.json https://raw.githubusercontent.com/b python3 core/perf_engine.py --hardware_type ILUVATAR --task swin-large-torch-fp32 ``` -## Results +## Model Results | Model | BatchSize | Precision | QPS | Top-1 Acc | | ---------------------- | --------- | --------- | ----- | --------- | diff --git a/models/cv/classification/vgg11/igie/README.md b/models/cv/classification/vgg11/igie/README.md index 522ff3e7..cf2d5806 100644 --- a/models/cv/classification/vgg11/igie/README.md +++ b/models/cv/classification/vgg11/igie/README.md @@ -1,18 +1,18 @@ # VGG11 -## Description +## Model Description VGG11 is a deep convolutional neural network introduced by the Visual Geometry Group at the University of Oxford in the paper "Very Deep Convolutional Networks for Large-Scale Image Recognition." The model consists of 11 layers with trainable weights, including 8 convolutional layers and 3 fully connected layers. It employs small 3x3 convolutional kernels and 2x2 max-pooling layers to extract hierarchical features from input images. The ReLU activation function is used throughout the network to enhance non-linearity and mitigate the vanishing gradient problem. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -24,7 +24,7 @@ Dataset: to download the validation dat python3 export.py --weight vgg11-8a719046.pth --output vgg11.onnx ``` -## Inference +## Model Inference ```bash export DATASETS_DIR=/Path/to/imagenet_val/ @@ -39,7 +39,7 @@ bash scripts/infer_vgg11_fp16_accuracy.sh bash scripts/infer_vgg11_fp16_performance.sh ``` -## Results +## Model Results Model |BatchSize |Precision |FPS |Top-1(%) |Top-5(%) --------|-----------|----------|----------|----------|-------- diff --git a/models/cv/classification/vgg16/igie/README.md b/models/cv/classification/vgg16/igie/README.md index 292b03ca..4c074f2f 100644 --- a/models/cv/classification/vgg16/igie/README.md +++ b/models/cv/classification/vgg16/igie/README.md @@ -1,18 +1,18 @@ # VGG16 -## Description +## Model Description VGG16 is a convolutional neural network (CNN) architecture designed for image classification tasks.The architecture of VGG16 is characterized by its simplicity and uniform structure. It consists of 16 convolutional and fully connected layers, organized into five blocks, with the convolutional layers using small 3x3 filters. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -24,7 +24,7 @@ Dataset: to download the validation dat python3 export.py --weight vgg16-397923af.pth --output vgg16.onnx ``` -## Inference +## Model Inference ```bash export DATASETS_DIR=/Path/to/imagenet_val/ @@ -48,7 +48,7 @@ bash scripts/infer_vgg16_int8_accuracy.sh bash scripts/infer_vgg16_int8_performance.sh ``` -## Results +## Model Results Model |BatchSize |Precision |FPS |Top-1(%) |Top-5(%) --------|-----------|----------|----------|----------|-------- diff --git a/models/cv/classification/vgg16/ixrt/README.md b/models/cv/classification/vgg16/ixrt/README.md index 7681a924..11e32d7f 100644 --- a/models/cv/classification/vgg16/ixrt/README.md +++ b/models/cv/classification/vgg16/ixrt/README.md @@ -1,13 +1,13 @@ # VGG16 -## Description +## Model Description VGG16 is a deep convolutional neural network model developed by the Visual Geometry Group at the University of Oxford. It finished second in the 2014 ImageNet Massive Visual Identity Challenge (ILSVRC). -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash # Install libGL @@ -19,7 +19,7 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -32,7 +32,7 @@ mkdir checkpoints python3 export_onnx.py --origin_model /path/to/vgg16-397923af.pth --output_model checkpoints/vgg16.onnx ``` -## Inference +## Model Inference ```bash export PROJ_DIR=./ @@ -60,7 +60,7 @@ bash scripts/infer_vgg16_int8_accuracy.sh bash scripts/infer_vgg16_int8_performance.sh ``` -## Results +## Model Results Model |BatchSize |Precision |FPS |Top-1(%) |Top-5(%) ------|-----------|----------|---------|---------|-------- diff --git a/models/cv/classification/wide_resnet101/igie/README.md b/models/cv/classification/wide_resnet101/igie/README.md index 93a5a3b8..96dfc6cd 100644 --- a/models/cv/classification/wide_resnet101/igie/README.md +++ b/models/cv/classification/wide_resnet101/igie/README.md @@ -1,18 +1,18 @@ # Wide ResNet101 -## Description +## Model Description Wide ResNet101 is a variant of the ResNet architecture that focuses on increasing the network's width (number of channels per layer) rather than its depth. This approach, inspired by the paper "Wide Residual Networks," balances model depth and width to achieve better performance while avoiding the drawbacks of overly deep networks, such as vanishing gradients and feature redundancy.Wide ResNet101 builds upon the standard ResNet101 architecture but doubles (or quadruples) the number of channels in each residual block. This results in significantly improved feature representation, making it suitable for complex tasks like image classification, object detection, and segmentation. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -24,7 +24,7 @@ Dataset: to download the validation dat python3 export.py --weight wide_resnet101_2-32ee1156.pth --output wide_resnet101.onnx ``` -## Inference +## Model Inference ```bash export DATASETS_DIR=/Path/to/imagenet_val/ @@ -39,7 +39,7 @@ bash scripts/infer_wide_resnet101_fp16_accuracy.sh bash scripts/infer_wide_resnet101_fp16_performance.sh ``` -## Results +## Model Results | Model | BatchSize | Precision | FPS | Top-1(%) | Top-5(%) | | -------------- | --------- | --------- | -------- | -------- | -------- | diff --git a/models/cv/classification/wide_resnet50/igie/README.md b/models/cv/classification/wide_resnet50/igie/README.md index 3aebe48f..7bcc1ffb 100644 --- a/models/cv/classification/wide_resnet50/igie/README.md +++ b/models/cv/classification/wide_resnet50/igie/README.md @@ -1,18 +1,18 @@ # Wide ResNet50 -## Description +## Model Description The distinguishing feature of Wide ResNet50 lies in its widened architecture compared to traditional ResNet models. By increasing the width of the residual blocks, Wide ResNet50 enhances the capacity of the network to capture richer and more diverse feature representations, leading to improved performance on various visual recognition tasks. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -24,7 +24,7 @@ Dataset: to download the validation dat python3 export.py --weight wide_resnet50_2-95faca4d.pth --output wide_resnet50.onnx ``` -## Inference +## Model Inference ```bash export DATASETS_DIR=/Path/to/imagenet_val/ @@ -48,7 +48,7 @@ bash scripts/infer_wide_resnet50_int8_accuracy.sh bash scripts/infer_wide_resnet50_int8_performance.sh ``` -## Results +## Model Results | Model | BatchSize | Precision | FPS | Top-1(%) | Top-5(%) | | ------------- | --------- | --------- | -------- | -------- | -------- | diff --git a/models/cv/classification/wide_resnet50/ixrt/README.md b/models/cv/classification/wide_resnet50/ixrt/README.md index 72fd5b49..b49b753a 100644 --- a/models/cv/classification/wide_resnet50/ixrt/README.md +++ b/models/cv/classification/wide_resnet50/ixrt/README.md @@ -1,18 +1,18 @@ # Wide ResNet50 -## Description +## Model Description The distinguishing feature of Wide ResNet50 lies in its widened architecture compared to traditional ResNet models. By increasing the width of the residual blocks, Wide ResNet50 enhances the capacity of the network to capture richer and more diverse feature representations, leading to improved performance on various visual recognition tasks. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -25,7 +25,7 @@ mkdir -p checkpoints/ python3 export.py --weight wide_resnet50_2-95faca4d.pth --output checkpoints/wide_resnet50.onnx ``` -## Inference +## Model Inference ```bash export DATASETS_DIR=/Path/to/imagenet_val/ @@ -52,7 +52,7 @@ bash scripts/infer_wide_resnet50_int8_accuracy.sh bash scripts/infer_wide_resnet50_int8_performance.sh ``` -## Results +## Model Results | Model | BatchSize | Precision | FPS | Top-1(%) | Top-5(%) | | ------------- | --------- | --------- | -------- | -------- | -------- | diff --git a/models/cv/face_recognition/facenet/ixrt/README.md b/models/cv/face_recognition/facenet/ixrt/README.md index 36ee33db..9558c3d6 100644 --- a/models/cv/face_recognition/facenet/ixrt/README.md +++ b/models/cv/face_recognition/facenet/ixrt/README.md @@ -1,12 +1,12 @@ # FaceNet -## Description +## Model Description Facenet is a facial recognition system originally proposed and developed by Google. It utilizes deep learning techniques, specifically convolutional neural networks (CNNs), to transform facial images into high-dimensional feature vectors. These feature vectors possess high discriminative power, enabling comparison and identification of different faces. The core idea of Facenet is to map faces into a multi-dimensional space of feature vectors, achieving efficient representation and recognition of faces. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash # Install libGL @@ -18,7 +18,7 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -56,7 +56,7 @@ wget https://raw.githubusercontent.com/lanrax/Project_dataset/master/facenet_dat unzip facenet_datasets.zip ``` -## Inference +## Model Inference Because there are differences in model export, it is necessary to verify the following information before executing inference: In deploy.py, "/last_bn/BatchNormalization_output_0" refers to the output name of the BatchNormalization node in the exported ONNX model, such as "1187". "/avgpool_1a/GlobalAveragePool_output_0" refers to the output name of the GlobalAveragePool node, such as "1178". Additionally, make sure to update "/last_bn/BatchNormalization_output_0" in build_engine.py to the corresponding name, such as "1187". @@ -82,7 +82,7 @@ bash scripts/infer_facenet_int8_accuracy.sh bash scripts/infer_facenet_int8_performance.sh ``` -## Results +## Model Results | Model | BatchSize | Precision | FPS | AUC | ACC | | ------- | --------- | --------- | --------- | ----- | ---------------- | diff --git a/models/cv/instance_segmentation/mask_rcnn/ixrt/README.md b/models/cv/instance_segmentation/mask_rcnn/ixrt/README.md index 3fc83674..4ccad0cc 100644 --- a/models/cv/instance_segmentation/mask_rcnn/ixrt/README.md +++ b/models/cv/instance_segmentation/mask_rcnn/ixrt/README.md @@ -1,6 +1,6 @@ # Mask R-CNN -## Description +## Model Description Mask R-CNN (Mask Region-Based Convolutional Neural Network) is an extension of the Faster R-CNN model, which is itself an improvement over R-CNN and Fast R-CNN. Developed by Kaiming He et al., Mask R-CNN is designed for object instance segmentation tasks, meaning it not only detects objects within an image but also generates high-quality segmentation masks for each instance. @@ -29,7 +29,7 @@ Visit [COCO site](https://cocodataset.org/) and get COCO2017 datasets - images directory: coco/images/val2017/*.jpg - annotations directory: coco/annotations/instances_val2017.json -## Setup +## Model Preparation ```bash cd scripts/ @@ -47,7 +47,7 @@ bash init.sh bash init_nv.sh ``` -## Inference +## Model Inference ### FP16 Performance @@ -59,7 +59,7 @@ bash scripts/infer_mask_rcnn_fp16_performance.sh bash scripts/infer_mask_rcnn_fp16_accuracy.sh ``` -## Results +## Model Results Model | BatchSize | Precision | FPS | ACC ------|-----------|-----------|-----|---- diff --git a/models/cv/instance_segmentation/solov1/ixrt/README.md b/models/cv/instance_segmentation/solov1/ixrt/README.md index 45de0d38..b04a63d1 100644 --- a/models/cv/instance_segmentation/solov1/ixrt/README.md +++ b/models/cv/instance_segmentation/solov1/ixrt/README.md @@ -1,12 +1,12 @@ # SOLOv1 -## Description +## Model Description SOLO (Segmenting Objects by Locations) is a new instance segmentation method that differs from traditional approaches by introducing the concept of “instance categories”. Based on the location and size of each instance, SOLO assigns each pixel to a corresponding instance category. This method transforms the instance segmentation problem into a single-shot classification task, simplifying the overall process. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash yum install mesa-libGL @@ -26,7 +26,7 @@ sh build_mmcv.sh sh install_mmcv.sh ``` -### Download +### Prepare Resources Pretrained model: @@ -40,7 +40,7 @@ python3 solo_torch2onnx.py --cfg /path/to/solo/solo_r50_fpn_3x_coco.py --checkpo mv r50_solo_bs1_800x800.onnx /Path/to/checkpoints/r50_solo_bs1_800x800.onnx ``` -## Inference +## Model Inference ```bash export PROJ_DIR=./ @@ -60,7 +60,7 @@ bash scripts/infer_solov1_fp16_accuracy.sh bash scripts/infer_solov1_fp16_performance.sh ``` -## Results +## Model Results Model |BatchSize |Precision |FPS |MAP@0.5 |MAP@0.5:0.95 --------|-----------|----------|----------|----------|------------ diff --git a/models/cv/multi_object_tracking/deepsort/igie/README.md b/models/cv/multi_object_tracking/deepsort/igie/README.md index 4e143861..dda65e4a 100644 --- a/models/cv/multi_object_tracking/deepsort/igie/README.md +++ b/models/cv/multi_object_tracking/deepsort/igie/README.md @@ -1,18 +1,18 @@ # DeepSort -## Description +## Model Description DeepSort integrates deep neural networks with traditional tracking methods to achieve robust and accurate tracking of objects in video streams. The algorithm leverages a combination of a deep appearance feature extractor and the Hungarian algorithm for data association. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model(ckpt.t7): @@ -27,7 +27,7 @@ python3 export.py --weight ckpt.t7 --output deepsort.onnx onnxsim deepsort.onnx deepsort_opt.onnx ``` -## Inference +## Model Inference ```bash export DATASETS_DIR=/Path/to/market1501/ @@ -51,7 +51,7 @@ bash scripts/infer_deepsort_int8_accuracy.sh bash scripts/infer_deepsort_int8_performance.sh ``` -## Results +## Model Results Model |BatchSize |Precision |FPS |Acc(%) | ---------|-----------|----------|----------|----------| diff --git a/models/cv/multi_object_tracking/fastreid/igie/README.md b/models/cv/multi_object_tracking/fastreid/igie/README.md index 16aaff6d..0353c81a 100644 --- a/models/cv/multi_object_tracking/fastreid/igie/README.md +++ b/models/cv/multi_object_tracking/fastreid/igie/README.md @@ -1,18 +1,18 @@ # FastReID -## Description +## Model Description FastReID is a research platform that implements state-of-the-art re-identification algorithms. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -31,7 +31,7 @@ python3 tools/deploy/onnx_export.py --config-file configs/VehicleID/bagtricks_R5 cd .. ``` -## Inference +## Model Inference ```bash export DATASETS_DIR=/Path/to/VehicleID @@ -46,7 +46,7 @@ bash scripts/infer_fastreid_fp16_accuracy.sh bash scripts/infer_fastreid_fp16_performance.sh ``` -## Results +## Model Results Model |BatchSize |Precision |FPS |Rank-1(%) |Rank-5(%) |mAP | ---------|-----------|----------|----------|----------|----------|--------| diff --git a/models/cv/multi_object_tracking/repnet/igie/README.md b/models/cv/multi_object_tracking/repnet/igie/README.md index 95a18415..28d221a4 100644 --- a/models/cv/multi_object_tracking/repnet/igie/README.md +++ b/models/cv/multi_object_tracking/repnet/igie/README.md @@ -1,18 +1,18 @@ # RepNet-Vehicle-ReID -## Description +## Model Description The paper "Deep Relative Distance Learning: Tell the Difference Between Similar Vehicles" introduces a model named Deep Relative Distance Learning (DRDL), specifically designed for the problem of vehicle re-identification. DRDL employs a dual-branch deep convolutional network architecture, combined with a coupled clusters loss function and a mixed difference network structure, effectively mapping vehicle images into Euclidean space for similarity measurement. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -27,7 +27,7 @@ python3 export.py --weight epoch_14.pth --output repnet.onnx onnxsim repnet.onnx repnet_opt.onnx ``` -## Inference +## Model Inference ```bash export DATASETS_DIR=/Path/to/VehicleID/ @@ -42,12 +42,12 @@ bash scripts/infer_repnet_fp16_accuracy.sh bash scripts/infer_repnet_fp16_performance.sh ``` -## Results +## Model Results Model |BatchSize |Precision |FPS |Acc(%) | --------|-----------|----------|----------|----------| RepNet | 32 | FP16 |1373.579 | 99.88 | -## Reference +## References RepNet-MDNet-VehicleReID: diff --git a/models/cv/object_detection/atss/igie/README.md b/models/cv/object_detection/atss/igie/README.md index 23f0ae94..2fceb8f7 100644 --- a/models/cv/object_detection/atss/igie/README.md +++ b/models/cv/object_detection/atss/igie/README.md @@ -1,12 +1,12 @@ # ATSS -## Description +## Model Description ATSS is an advanced adaptive training sample selection method that effectively enhances the performance of both anchor-based and anchor-free object detectors by dynamically choosing positive and negative samples based on the statistical characteristics of objects. The design of ATSS reduces reliance on hyperparameters, simplifies the sample selection process, and significantly improves detection accuracy without adding extra computational costs. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash # Install libGL @@ -18,7 +18,7 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -38,7 +38,7 @@ python3 export.py --weight atss_r50_fpn_1x_coco_20200209-985f7bd0.pth --cfg atss onnxsim atss.onnx atss_opt.onnx ``` -## Inference +## Model Inference ```bash export DATASETS_DIR=/Path/to/coco/ @@ -53,13 +53,13 @@ bash scripts/infer_atss_fp16_accuracy.sh bash scripts/infer_atss_fp16_performance.sh ``` -## Results +## Model Results Model |BatchSize |Precision |FPS |IOU@0.5 |IOU@0.5:0.95 | -------|-----------|----------|----------|----------|---------------| ATSS | 32 | FP16 | 81.671 | 0.541 | 0.367 | -## Reference +## References mmdetection: diff --git a/models/cv/object_detection/centernet/igie/README.md b/models/cv/object_detection/centernet/igie/README.md index 64156b2e..17429ef7 100644 --- a/models/cv/object_detection/centernet/igie/README.md +++ b/models/cv/object_detection/centernet/igie/README.md @@ -1,12 +1,12 @@ # CenterNet -## Description +## Model Description CenterNet is an efficient object detection model that simplifies the traditional object detection process by representing targets as the center points of their bounding boxes and using keypoint estimation techniques to locate these points. This model not only excels in speed, achieving real-time detection while maintaining high accuracy, but also exhibits good versatility, easily extending to tasks such as 3D object detection and human pose estimation. CenterNet's network architecture employs various optimized fully convolutional networks and combines effective loss functions, making the model training and inference process more efficient. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash # Install libGL @@ -18,7 +18,7 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -31,7 +31,7 @@ Dataset: to download the valida python3 export.py --weight centernet_resnet18_140e_coco_20210705_093630-bb5b3bf7.pth --cfg centernet_r18_8xb16-crop512-140e_coco.py --output centernet.onnx ``` -## Inference +## Model Inference ```bash export DATASETS_DIR=/Path/to/coco/ @@ -46,12 +46,12 @@ bash scripts/infer_centernet_fp16_accuracy.sh bash scripts/infer_centernet_fp16_performance.sh ``` -## Results +## Model Results Model |BatchSize |Precision |FPS |IOU@0.5 |IOU@0.5:0.95 | ----------|-----------|----------|----------|----------|---------------| CenterNet | 32 | FP16 | 799.70 | 0.423 | 0.258 | -## Reference +## References mmdetection: diff --git a/models/cv/object_detection/centernet/ixrt/README.md b/models/cv/object_detection/centernet/ixrt/README.md index 776b54fb..bcb7e55f 100644 --- a/models/cv/object_detection/centernet/ixrt/README.md +++ b/models/cv/object_detection/centernet/ixrt/README.md @@ -1,12 +1,12 @@ # CenterNet -## Description +## Model Description CenterNet is an efficient object detection model that simplifies the traditional object detection process by representing targets as the center points of their bounding boxes and using keypoint estimation techniques to locate these points. This model not only excels in speed, achieving real-time detection while maintaining high accuracy, but also exhibits good versatility, easily extending to tasks such as 3D object detection and human pose estimation. CenterNet's network architecture employs various optimized fully convolutional networks and combines effective loss functions, making the model training and inference process more efficient. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash # Install libGL @@ -19,7 +19,7 @@ pip3 install -r requirements.txt # Contact the Iluvatar administrator to get the mmcv install package. ``` -### Download +### Prepare Resources Pretrained model: @@ -32,7 +32,7 @@ Dataset: to download the valida python3 export.py --weight centernet_resnet18_140e_coco_20210705_093630-bb5b3bf7.pth --cfg centernet_r18_8xb16-crop512-140e_coco.py --output centernet.onnx ``` -## Inference +## Model Inference ```bash export DATASETS_DIR=/Path/to/coco/ @@ -48,12 +48,12 @@ bash scripts/infer_centernet_fp16_accuracy.sh bash scripts/infer_centernet_fp16_performance.sh ``` -## Results +## Model Results | Model | BatchSize | Precision | FPS | IOU@0.5 | IOU@0.5:0.95 | | --------- | --------- | --------- | ------- | ------- | ------------ | | CenterNet | 32 | FP16 | 879.447 | 0.423 | 0.258 | -## Reference +## References mmdetection: diff --git a/models/cv/object_detection/detr/ixrt/README.md b/models/cv/object_detection/detr/ixrt/README.md index cde0acda..2f59fe34 100755 --- a/models/cv/object_detection/detr/ixrt/README.md +++ b/models/cv/object_detection/detr/ixrt/README.md @@ -1,12 +1,12 @@ # DETR -## Description +## Model Description DETR (DEtection TRansformer) is a novel approach that views object detection as a direct set prediction problem. This method streamlines the detection process, eliminating the need for many hand-designed components like non-maximum suppression procedures or anchor generation, which are typically used to explicitly encode prior knowledge about the task. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash # Install libGL @@ -18,7 +18,7 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -31,7 +31,7 @@ mkdir checkpoints python3 export_model.py --torch_file /path/to/detr_r50_8xb2-150e_coco_20221023_153551-436d03e8.pth --onnx_file checkpoints/detr_res50.onnx --bsz 1 ``` -## Inference +## Model Inference ```bash export PROJ_DIR=./ @@ -52,7 +52,7 @@ bash scripts/infer_detr_fp16_accuracy.sh bash scripts/infer_detr_fp16_performance.sh ``` -## Results +## Model Results Model |BatchSize |Precision |FPS |MAP@0.5 |MAP@0.5:0.95 --------|-----------|----------|----------|----------|------------ diff --git a/models/cv/object_detection/fcos/igie/README.md b/models/cv/object_detection/fcos/igie/README.md index 2bcdbee2..0e123d4d 100644 --- a/models/cv/object_detection/fcos/igie/README.md +++ b/models/cv/object_detection/fcos/igie/README.md @@ -1,12 +1,12 @@ # FCOS -## Description +## Model Description FCOS is an innovative one-stage object detection framework that abandons traditional anchor box dependency and uses a fully convolutional network for per-pixel target prediction. By introducing a centerness branch and multi-scale feature fusion, FCOS enhances detection performance while simplifying the model structure, especially in detecting small and overlapping targets. Additionally, FCOS eliminates the need for hyperparameter tuning related to anchor boxes, streamlining the model training and tuning process. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash # Install libGL @@ -18,7 +18,7 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -38,7 +38,7 @@ python3 export.py --weight fcos_r50_caffe_fpn_gn-head_1x_coco-821213aa.pth --cfg onnxsim fcos.onnx fcos_opt.onnx ``` -## Inference +## Model Inference ```bash export DATASETS_DIR=/Path/to/coco/ @@ -53,12 +53,12 @@ bash scripts/infer_fcos_fp16_accuracy.sh bash scripts/infer_fcos_fp16_performance.sh ``` -## Results +## Model Results Model |BatchSize |Precision |FPS |IOU@0.5 |IOU@0.5:0.95 | -------|-----------|----------|----------|----------|---------------| FCOS | 32 | FP16 | 83.09 | 0.522 | 0.339 | -## Reference +## References mmdetection: diff --git a/models/cv/object_detection/fcos/ixrt/README.md b/models/cv/object_detection/fcos/ixrt/README.md index 56b18c69..80b32ad8 100755 --- a/models/cv/object_detection/fcos/ixrt/README.md +++ b/models/cv/object_detection/fcos/ixrt/README.md @@ -1,13 +1,13 @@ # FCOS -## Description +## Model Description FCOS is an anchor-free model based on the Fully Convolutional Network (FCN) architecture for pixel-wise object detection. It implements a proposal-free solution and introduces the concept of centerness. For more details, please refer to our [report on Arxiv](https://arxiv.org/abs/1904.01355). -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash # Install libGL @@ -32,7 +32,7 @@ sh build_mmcv.sh sh install_mmcv.sh ``` -### Download +### Prepare Resources Pretrained model: @@ -65,7 +65,7 @@ python3 tools/deployment/pytorch2onnx.py \ If there are issues such as input parameter mismatch during model export, it may be due to ONNX version. To resolve this, please delete the last parameter (dynamic_slice) from the return value of the_slice_helper function in the /usr/local/lib/python3.10/site-packages/mmcv/onnx/onnx_utils/symbolic_helper.py file. -## Inference +## Model Inference ```bash export PROJ_DIR=./ @@ -83,7 +83,7 @@ bash scripts/infer_fcos_fp16_accuracy.sh bash scripts/infer_fcos_fp16_performance.sh ``` -## Results +## Model Results | Model | BatchSize | Precision | FPS | MAP@0.5 | MAP@0.5:0.95 | | ----- | --------- | --------- | ----- | ------- | ------------ | diff --git a/models/cv/object_detection/foveabox/igie/README.md b/models/cv/object_detection/foveabox/igie/README.md index cbed39fd..f90f39fb 100644 --- a/models/cv/object_detection/foveabox/igie/README.md +++ b/models/cv/object_detection/foveabox/igie/README.md @@ -1,12 +1,12 @@ # FoveaBox -## Description +## Model Description FoveaBox is an advanced anchor-free object detection framework that enhances accuracy and flexibility by directly predicting the existence and bounding box coordinates of objects. Utilizing a Feature Pyramid Network (FPN), it adeptly handles targets of varying scales, particularly excelling with objects of arbitrary aspect ratios. FoveaBox also demonstrates robustness against image deformations. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash # Install libGL @@ -18,7 +18,7 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -34,7 +34,7 @@ python3 export.py --weight fovea_r50_fpn_4x4_1x_coco_20200219-ee4d5303.pth --cfg onnxsim foveabox.onnx foveabox_opt.onnx ``` -## Inference +## Model Inference ```bash export DATASETS_DIR=/Path/to/coco/ @@ -49,12 +49,12 @@ bash scripts/infer_foveabox_fp16_accuracy.sh bash scripts/infer_foveabox_fp16_performance.sh ``` -## Results +## Model Results Model |BatchSize |Precision |FPS |IOU@0.5 |IOU@0.5:0.95 | ---------|-----------|----------|----------|----------|---------------| FoveaBox | 32 | FP16 | 192.496 | 0.531 | 0.346 | -## Reference +## References mmdetection: diff --git a/models/cv/object_detection/foveabox/ixrt/README.md b/models/cv/object_detection/foveabox/ixrt/README.md index 2682a253..b085bc6c 100644 --- a/models/cv/object_detection/foveabox/ixrt/README.md +++ b/models/cv/object_detection/foveabox/ixrt/README.md @@ -1,12 +1,12 @@ # FoveaBox -## Description +## Model Description FoveaBox is an advanced anchor-free object detection framework that enhances accuracy and flexibility by directly predicting the existence and bounding box coordinates of objects. Utilizing a Feature Pyramid Network (FPN), it adeptly handles targets of varying scales, particularly excelling with objects of arbitrary aspect ratios. FoveaBox also demonstrates robustness against image deformations. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash # Install libGL @@ -25,7 +25,7 @@ pip3 install mmdet pip3 install opencv-python==4.6.0.66 ``` -### Download +### Prepare Resources Pretrained model: @@ -41,7 +41,7 @@ python3 export.py --weight fovea_r50_fpn_4x4_1x_coco_20200219-ee4d5303.pth --cfg onnxsim foveabox.onnx foveabox_opt.onnx ``` -## Inference +## Model Inference ```bash export DATASETS_DIR=/Path/to/coco/ @@ -56,12 +56,12 @@ bash scripts/infer_foveabox_fp16_accuracy.sh bash scripts/infer_foveabox_fp16_performance.sh ``` -## Results +## Model Results Model |BatchSize |Precision |FPS |IOU@0.5 |IOU@0.5:0.95 | ---------|-----------|----------|----------|----------|---------------| FoveaBox | 32 | FP16 | 181.304 | 0.531 | 0.346 | -## Reference +## References mmdetection: diff --git a/models/cv/object_detection/fsaf/igie/README.md b/models/cv/object_detection/fsaf/igie/README.md index d6fdbcfd..047d6fad 100644 --- a/models/cv/object_detection/fsaf/igie/README.md +++ b/models/cv/object_detection/fsaf/igie/README.md @@ -1,12 +1,12 @@ # FSAF -## Description +## Model Description The FSAF (Feature Selective Anchor-Free) module is an innovative component for single-shot object detection that enhances performance through online feature selection and anchor-free branches. The FSAF module dynamically selects the most suitable feature level for each object instance, rather than relying on traditional anchor-based heuristic methods. This improvement significantly boosts the accuracy of object detection, especially for small targets and in complex scenes. Moreover, compared to existing anchor-based detectors, the FSAF module maintains high efficiency while adding negligible additional inference overhead. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash # Install libGL @@ -18,7 +18,7 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -38,7 +38,7 @@ python3 export.py --weight fsaf_r50_fpn_1x_coco-94ccc51f.pth --cfg fsaf_r50_fpn_ onnxsim fsaf.onnx fsaf_opt.onnx ``` -## Inference +## Model Inference ```bash export DATASETS_DIR=/Path/to/coco/ @@ -53,12 +53,12 @@ bash scripts/infer_fsaf_fp16_accuracy.sh bash scripts/infer_fsaf_fp16_performance.sh ``` -## Results +## Model Results Model |BatchSize |Precision |FPS |IOU@0.5 |IOU@0.5:0.95 | -------|-----------|----------|----------|----------|---------------| FSAF | 32 | FP16 | 122.35 | 0.530 | 0.345 | -## Reference +## References mmdetection: diff --git a/models/cv/object_detection/fsaf/ixrt/README.md b/models/cv/object_detection/fsaf/ixrt/README.md index 03935e62..e1ecf0b9 100644 --- a/models/cv/object_detection/fsaf/ixrt/README.md +++ b/models/cv/object_detection/fsaf/ixrt/README.md @@ -1,12 +1,12 @@ # FSAF -## Description +## Model Description The FSAF (Feature Selective Anchor-Free) module is an innovative component for single-shot object detection that enhances performance through online feature selection and anchor-free branches. The FSAF module dynamically selects the most suitable feature level for each object instance, rather than relying on traditional anchor-based heuristic methods. This improvement significantly boosts the accuracy of object detection, especially for small targets and in complex scenes. Moreover, compared to existing anchor-based detectors, the FSAF module maintains high efficiency while adding negligible additional inference overhead. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash # Install libGL @@ -18,7 +18,7 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -38,7 +38,7 @@ python3 export.py --weight fsaf_r50_fpn_1x_coco-94ccc51f.pth --cfg fsaf_r50_fpn_ onnxsim fsaf.onnx fsaf_opt.onnx ``` -## Inference +## Model Inference ```bash export DATASETS_DIR=/Path/to/coco/ @@ -53,12 +53,12 @@ bash scripts/infer_fsaf_fp16_accuracy.sh bash scripts/infer_fsaf_fp16_performance.sh ``` -## Results +## Model Results Model |BatchSize |Precision |FPS |IOU@0.5 |IOU@0.5:0.95 | -------|-----------|----------|----------|----------|---------------| FSAF | 32 | FP16 | 133.85 | 0.530 | 0.345 | -## Reference +## References mmdetection: diff --git a/models/cv/object_detection/hrnet/igie/README.md b/models/cv/object_detection/hrnet/igie/README.md index 49fc4dcd..8063bb6e 100644 --- a/models/cv/object_detection/hrnet/igie/README.md +++ b/models/cv/object_detection/hrnet/igie/README.md @@ -1,12 +1,12 @@ # HRNet -## Description +## Model Description HRNet is an advanced deep learning architecture for human pose estimation, characterized by its maintenance of high-resolution representations throughout the entire network process, thereby avoiding the low-to-high resolution recovery step typical of traditional models. The network features parallel multi-resolution subnetworks and enriches feature representation through repeated multi-scale fusion, which enhances the accuracy of keypoint detection. Additionally, HRNet offers computational efficiency and has demonstrated superior performance over previous methods on several standard datasets. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash # Install libGL @@ -18,7 +18,7 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -34,7 +34,7 @@ python3 export.py --weight fcos_hrnetv2p_w18_gn-head_4x4_1x_coco_20201212_100710 onnxsim hrnet.onnx hrnet_opt.onnx ``` -## Inference +## Model Inference ```bash export DATASETS_DIR=/Path/to/coco/ @@ -49,12 +49,12 @@ bash scripts/infer_hrnet_fp16_accuracy.sh bash scripts/infer_hrnet_fp16_performance.sh ``` -## Results +## Model Results Model |BatchSize |Precision |FPS |IOU@0.5 |IOU@0.5:0.95 | -------|-----------|----------|----------|----------|---------------| HRNet | 32 | FP16 | 64.282 | 0.491 | 0.326 | -## Reference +## References mmdetection: diff --git a/models/cv/object_detection/hrnet/ixrt/README.md b/models/cv/object_detection/hrnet/ixrt/README.md index 284faafd..f37e3743 100644 --- a/models/cv/object_detection/hrnet/ixrt/README.md +++ b/models/cv/object_detection/hrnet/ixrt/README.md @@ -1,12 +1,12 @@ # HRNet -## Description +## Model Description HRNet is an advanced deep learning architecture for human pose estimation, characterized by its maintenance of high-resolution representations throughout the entire network process, thereby avoiding the low-to-high resolution recovery step typical of traditional models. The network features parallel multi-resolution subnetworks and enriches feature representation through repeated multi-scale fusion, which enhances the accuracy of keypoint detection. Additionally, HRNet offers computational efficiency and has demonstrated superior performance over previous methods on several standard datasets. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash # Install libGL @@ -18,7 +18,7 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -34,7 +34,7 @@ python3 export.py --weight fcos_hrnetv2p_w18_gn-head_4x4_1x_coco_20201212_100710 onnxsim hrnet.onnx hrnet_opt.onnx ``` -## Inference +## Model Inference ```bash export DATASETS_DIR=/Path/to/coco/ @@ -49,12 +49,12 @@ bash scripts/infer_hrnet_fp16_accuracy.sh bash scripts/infer_hrnet_fp16_performance.sh ``` -## Results +## Model Results Model |BatchSize |Precision |FPS |IOU@0.5 |IOU@0.5:0.95 | -------|-----------|----------|----------|----------|---------------| HRNet | 32 | FP16 | 75.199 | 0.491 | 0.327 | -## Reference +## References mmdetection: diff --git a/models/cv/object_detection/paa/igie/README.md b/models/cv/object_detection/paa/igie/README.md index 5cbc5505..eeaf5615 100644 --- a/models/cv/object_detection/paa/igie/README.md +++ b/models/cv/object_detection/paa/igie/README.md @@ -1,12 +1,12 @@ # PAA -## Description +## Model Description PAA (Probabilistic Anchor Assignment) is an algorithm for object detection that adaptively assigns positive and negative anchor samples using a probabilistic model. It employs a Gaussian mixture model to dynamically select positive and negative samples based on score distribution, avoiding the misassignment issues of traditional IoU threshold-based methods. PAA enhances detection accuracy, particularly in complex scenarios, and is compatible with existing detection frameworks. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash # Install libGL @@ -18,7 +18,7 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -34,7 +34,7 @@ python3 export.py --weight paa_r50_fpn_1x_coco_20200821-936edec3.pth --cfg paa_r onnxsim paa.onnx paa_opt.onnx ``` -## Inference +## Model Inference ```bash export DATASETS_DIR=/Path/to/coco/ @@ -49,12 +49,12 @@ bash scripts/infer_paa_fp16_accuracy.sh bash scripts/infer_paa_fp16_performance.sh ``` -## Results +## Model Results | Model | BatchSize | Precision | FPS | IOU@0.5 | IOU@0.5:0.95 | | ----- | --------- | --------- | ------- | ------- | ------------ | | PAA | 32 | FP16 | 138.414 | 0.555 | 0.381 | -## Reference +## References mmdetection: diff --git a/models/cv/object_detection/retinaface/igie/README.md b/models/cv/object_detection/retinaface/igie/README.md index 3610a8bf..a2928ae7 100755 --- a/models/cv/object_detection/retinaface/igie/README.md +++ b/models/cv/object_detection/retinaface/igie/README.md @@ -1,12 +1,12 @@ # RetinaFace -## Description +## Model Description RetinaFace is an efficient single-stage face detection model that employs a multi-task learning strategy to simultaneously predict facial locations, landmarks, and 3D facial shapes. It utilizes feature pyramids and context modules to extract multi-scale features and employs a self-supervised mesh decoder to enhance detection accuracy. RetinaFace demonstrates excellent performance on datasets like WIDER FACE, supports real-time processing, and its code and datasets are publicly available for researchers. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash # Install libGL @@ -18,7 +18,7 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -38,7 +38,7 @@ python3 export.py --weight mobilenet0.25_Final.pth --output retinaface.onnx onnxsim retinaface.onnx retinaface_opt.onnx ``` -## Inference +## Model Inference ```bash export DATASETS_DIR=/Path/to/widerface/ @@ -53,12 +53,12 @@ bash scripts/infer_retinaface_fp16_accuracy.sh bash scripts/infer_retinaface_fp16_performance.sh ``` -## Results +## Model Results | Model | BatchSize | Precision | FPS | Easy AP(%) | Medium AP (%) | Hard AP(%) | | :--------: | :-------: | :-------: | :------: | :--------: | :-----------: | :--------: | | RetinaFace | 32 | FP16 | 8304.626 | 80.13 | 68.52 | 36.59 | -## Reference +## References Face-Detector-1MB-with-landmark: diff --git a/models/cv/object_detection/retinaface/ixrt/README.md b/models/cv/object_detection/retinaface/ixrt/README.md index 2513eb34..4ac37220 100644 --- a/models/cv/object_detection/retinaface/ixrt/README.md +++ b/models/cv/object_detection/retinaface/ixrt/README.md @@ -1,12 +1,12 @@ # RetinaFace -## Description +## Model Description RetinaFace is an efficient single-stage face detection model that employs a multi-task learning strategy to simultaneously predict facial locations, landmarks, and 3D facial shapes. It utilizes feature pyramids and context modules to extract multi-scale features and employs a self-supervised mesh decoder to enhance detection accuracy. RetinaFace demonstrates excellent performance on datasets like WIDER FACE, supports real-time processing, and its code and datasets are publicly available for researchers. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash # Install libGL @@ -20,7 +20,7 @@ pip3 install -r requirements.txt python3 setup.py build_ext --inplace ``` -### Download +### Prepare Resources Pretrained model: @@ -36,7 +36,7 @@ wget https://github.com/biubug6/Face-Detector-1MB-with-landmark/raw/master/weigh # export onnx model python3 torch2onnx.py --model mobilenet0.25_Final.pth --onnx_model mnetv1_retinaface.onnx -## Inference +## Model Inference ```bash export DATASETS_DIR=/Path/to/widerface/ @@ -52,12 +52,12 @@ bash scripts/infer_retinaface_fp16_accuracy.sh bash scripts/infer_retinaface_fp16_performance.sh ``` -## Results +## Model Results | Model | BatchSize | Precision | FPS | Easy AP(%) | Medium AP (%) | Hard AP(%) | | :--------: | :-------: | :-------: | :------: | :--------: | :-----------: | :--------: | | RetinaFace | 32 | FP16 | 8536.367 | 80.84 | 69.34 | 37.31 | -## Reference +## References Face-Detector-1MB-with-landmark: diff --git a/models/cv/object_detection/retinanet/igie/README.md b/models/cv/object_detection/retinanet/igie/README.md index 18067d85..f8b4fa09 100644 --- a/models/cv/object_detection/retinanet/igie/README.md +++ b/models/cv/object_detection/retinanet/igie/README.md @@ -1,12 +1,12 @@ # RetinaNet -## Description +## Model Description RetinaNet, an innovative object detector, challenges the conventional trade-off between speed and accuracy in the realm of computer vision. Traditionally, two-stage detectors, exemplified by R-CNN, achieve high accuracy by applying a classifier to a limited set of candidate object locations. In contrast, one-stage detectors, like RetinaNet, operate over a dense sampling of possible object locations, aiming for simplicity and speed. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash # Install libGL @@ -18,7 +18,7 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -34,7 +34,7 @@ python3 export.py --weight retinanet_r50_fpn_1x_coco_20200130-c2398f9e.pth --cfg onnxsim retinanet.onnx retinanet_opt.onnx ``` -## Inference +## Model Inference ```bash export DATASETS_DIR=/Path/to/coco/ @@ -49,12 +49,12 @@ bash scripts/infer_retinanet_fp16_accuracy.sh bash scripts/infer_retinanet_fp16_performance.sh ``` -## Results +## Model Results Model |BatchSize |Precision |FPS |IOU@0.5 |IOU@0.5:0.95 | ----------|-----------|----------|----------|----------|---------------| RetinaNet | 32 | FP16 | 160.52 | 0.515 | 0.335 | -## Reference +## References mmdetection: diff --git a/models/cv/object_detection/rtmdet/igie/README.md b/models/cv/object_detection/rtmdet/igie/README.md index 8ed35963..76f47bc0 100644 --- a/models/cv/object_detection/rtmdet/igie/README.md +++ b/models/cv/object_detection/rtmdet/igie/README.md @@ -1,12 +1,12 @@ # RTMDet -## Description +## Model Description RTMDet, presented by the Shanghai AI Laboratory, is a novel framework for real-time object detection that surpasses the efficiency of the YOLO series. The model's architecture is meticulously crafted for optimal efficiency, employing a basic building block consisting of large-kernel depth-wise convolutions in both the backbone and neck, which enhances the model's ability to capture global context. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash # Install libGL @@ -18,7 +18,7 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -38,7 +38,7 @@ python3 export.py --weight rtmdet_nano_8xb32-100e_coco-obj365-person-05d8511e.pt onnxsim rtmdet.onnx rtmdet_opt.onnx ``` -## Inference +## Model Inference ```bash export DATASETS_DIR=/Path/to/coco/ @@ -53,11 +53,11 @@ bash scripts/infer_rtmdet_fp16_accuracy.sh bash scripts/infer_rtmdet_fp16_performance.sh ``` -## Results +## Model Results Model |BatchSize |Precision |FPS |IOU@0.5 |IOU@0.5:0.95 | ----------|-----------|----------|----------|----------|---------------| RTMDet | 32 | FP16 | 2627.15 | 0.619 | 0.403 | -## Reference +## References mmdetection: diff --git a/models/cv/object_detection/sabl/igie/README.md b/models/cv/object_detection/sabl/igie/README.md index 25732e82..3c363a9d 100644 --- a/models/cv/object_detection/sabl/igie/README.md +++ b/models/cv/object_detection/sabl/igie/README.md @@ -1,12 +1,12 @@ # SABL -## Description +## Model Description SABL (Side-Aware Boundary Localization) is an innovative approach in object detection that focuses on improving the precision of bounding box localization. It addresses the limitations of traditional bounding box regression methods, such as boundary ambiguity and asymmetric prediction errors, was first proposed in the paper "Side-Aware Boundary Localization for More Precise Object Detection". -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash # Install libGL @@ -18,7 +18,7 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -38,7 +38,7 @@ python3 export.py --weight sabl_retinanet_r50_fpn_1x_coco-6c54fd4f.pth --cfg sab onnxsim sabl.onnx sabl_opt.onnx ``` -## Inference +## Model Inference ```bash export DATASETS_DIR=/Path/to/coco/ @@ -53,12 +53,12 @@ bash scripts/infer_sabl_fp16_accuracy.sh bash scripts/infer_sabl_fp16_performance.sh ``` -## Results +## Model Results Model |BatchSize |Precision |FPS |IOU@0.5 |IOU@0.5:0.95 | -------|-----------|----------|----------|----------|---------------| SABL | 32 | FP16 | 189.42 | 0.530 | 0.356 | -## Reference +## References mmdetection: diff --git a/models/cv/object_detection/yolov10/igie/README.md b/models/cv/object_detection/yolov10/igie/README.md index fde2e5dc..78e214fc 100644 --- a/models/cv/object_detection/yolov10/igie/README.md +++ b/models/cv/object_detection/yolov10/igie/README.md @@ -1,18 +1,18 @@ # YOLOv10 -## Description +## Model Description YOLOv10, built on the Ultralytics Python package by researchers at Tsinghua University, introduces a new approach to real-time object detection, addressing both the post-processing and model architecture deficiencies found in previous YOLO versions. By eliminating non-maximum suppression (NMS) and optimizing various model components, YOLOv10 achieves state-of-the-art performance with significantly reduced computational overhead. Extensive experiments demonstrate its superior accuracy-latency trade-offs across multiple model scales. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -28,7 +28,7 @@ python3 export.py --weight yolov10s.pt --batch 32 ``` -## Inference +## Model Inference ```bash export DATASETS_DIR=/Path/to/coco/ @@ -43,12 +43,12 @@ bash scripts/infer_yolov10_fp16_accuracy.sh bash scripts/infer_yolov10_fp16_performance.sh ``` -## Results +## Model Results | Model | BatchSize | Precision | FPS | IOU@0.5 | IOU@0.5:0.95 | | ------- | --------- | --------- | ------ | ------- | ------------ | | YOLOv10 | 32 | FP16 | 810.97 | 0.629 | 0.461 | -## Reference +## References YOLOv10: diff --git a/models/cv/object_detection/yolov11/igie/README.md b/models/cv/object_detection/yolov11/igie/README.md index 9db80e45..9b93f426 100644 --- a/models/cv/object_detection/yolov11/igie/README.md +++ b/models/cv/object_detection/yolov11/igie/README.md @@ -1,18 +1,18 @@ # YOLOv11 -## Description +## Model Description YOLOv11 is the latest generation of the YOLO (You Only Look Once) series object detection model released by Ultralytics. Building upon the advancements of previous YOLO models, such as YOLOv5 and YOLOv8, YOLOv11 introduces comprehensive upgrades to further enhance performance, flexibility, and usability. It is a versatile deep learning model designed for multi-task applications, supporting object detection, instance segmentation, image classification, keypoint pose estimation, and rotated object detection. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -22,7 +22,7 @@ Pretrained model: diff --git a/models/cv/object_detection/yolov3/igie/README.md b/models/cv/object_detection/yolov3/igie/README.md index 7e1d769a..fb487dcc 100644 --- a/models/cv/object_detection/yolov3/igie/README.md +++ b/models/cv/object_detection/yolov3/igie/README.md @@ -1,12 +1,12 @@ # YOLOv3 -## Description +## Model Description YOLOv3 is a influential object detection algorithm.The key innovation of YOLOv3 lies in its ability to efficiently detect and classify objects in real-time with a single pass through the neural network. YOLOv3 divides an input image into a grid and predicts bounding boxes, class probabilities, and objectness scores for each grid cell. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash # Install libGL @@ -18,7 +18,7 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -33,7 +33,7 @@ python3 export.py --weight yolov3.pt --output yolov3.onnx onnxsim yolov3.onnx yolov3_opt.onnx ``` -## Inference +## Model Inference ```bash export DATASETS_DIR=/Path/to/coco/ @@ -57,7 +57,7 @@ bash scripts/infer_yolov3_int8_accuracy.sh bash scripts/infer_yolov3_int8_performance.sh ``` -## Results +## Model Results Model |BatchSize |Precision |FPS |MAP@0.5 |MAP@0.5:0.95 | --------|-----------|----------|---------|---------|-------------| diff --git a/models/cv/object_detection/yolov3/ixrt/README.md b/models/cv/object_detection/yolov3/ixrt/README.md index d1f37fec..1f9b85c2 100644 --- a/models/cv/object_detection/yolov3/ixrt/README.md +++ b/models/cv/object_detection/yolov3/ixrt/README.md @@ -1,12 +1,12 @@ # YOLOv3 -## Description +## Model Description YOLOv3 is a influential object detection algorithm.The key innovation of YOLOv3 lies in its ability to efficiently detect and classify objects in real-time with a single pass through the neural network. YOLOv3 divides an input image into a grid and predicts bounding boxes, class probabilities, and objectness scores for each grid cell. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash # Install libGL @@ -18,7 +18,7 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -41,7 +41,7 @@ python3 detect.py --cfg cfg/yolov3.cfg --weights weights/yolov3.weights mv weights/export.onnx /Path/to/checkpoints/yolov3.onnx ``` -## Inference +## Model Inference ```bash export PROJ_DIR=/Path/to/yolov3/ixrt @@ -71,7 +71,7 @@ bash scripts/infer_yolov3_int8_accuracy.sh bash scripts/infer_yolov3_int8_performance.sh ``` -## Results +## Model Results Model |BatchSize |Precision |FPS |MAP@0.5 |MAP@0.5:0.95 | --------|-----------|----------|---------|----------|-------------| diff --git a/models/cv/object_detection/yolov4/igie/README.md b/models/cv/object_detection/yolov4/igie/README.md index f2a0320d..5be19a01 100644 --- a/models/cv/object_detection/yolov4/igie/README.md +++ b/models/cv/object_detection/yolov4/igie/README.md @@ -1,12 +1,12 @@ # YOLOv4 -## Description +## Model Description YOLOv4 employs a two-step process, involving regression for bounding box positioning and classification for object categorization. it amalgamates past YOLO family research contributions with novel features like WRC, CSP, CmBN, SAT, Mish activation, Mosaic data augmentation, DropBlock regularization, and CIoU loss. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash # Install libGL @@ -18,7 +18,7 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained cfg: Pretrained model: @@ -38,7 +38,7 @@ python3 export.py --cfg yolov4/cfg/yolov4.cfg --weight yolov4.weights --output y onnxsim yolov4.onnx yolov4_opt.onnx ``` -## Inference +## Model Inference ```bash export DATASETS_DIR=/Path/to/coco/ @@ -62,14 +62,14 @@ bash scripts/infer_yolov4_int8_accuracy.sh bash scripts/infer_yolov4_int8_performance.sh ``` -## Results +## Model Results Model |BatchSize |Precision |FPS |MAP@0.5 |MAP@0.5:0.95 | --------|-----------|----------|----------|----------|-------------| yolov4 | 32 | FP16 |285.218 | 0.741 | 0.506 | yolov4 | 32 | INT8 |413.320 | 0.721 | 0.463 | -## Reference +## References DarkNet: Pytorch-YOLOv4: diff --git a/models/cv/object_detection/yolov4/ixrt/README.md b/models/cv/object_detection/yolov4/ixrt/README.md index 8b53a752..6bffbbdb 100644 --- a/models/cv/object_detection/yolov4/ixrt/README.md +++ b/models/cv/object_detection/yolov4/ixrt/README.md @@ -1,12 +1,12 @@ # YOLOv4 -## Description +## Model Description YOLOv4 employs a two-step process, involving regression for bounding box positioning and classification for object categorization. it amalgamates past YOLO family research contributions with novel features like WRC, CSP, CmBN, SAT, Mish activation, Mosaic data augmentation, DropBlock regularization, and CIoU loss. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash # Install libGL @@ -18,7 +18,7 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained cfg: Pretrained model: @@ -45,7 +45,7 @@ onnxsim data/yolov4.onnx data/yolov4_sim.onnx # Make sure the dataset path is "data/coco" ``` -## Inference +## Model Inference ### FP16 @@ -65,14 +65,14 @@ bash scripts/infer_yolov4_int8_accuracy.sh bash scripts/infer_yolov4_int8_performance.sh ``` -## Results +## Model Results | Model | BatchSize | Precision | FPS | MAP@0.5 | | ------ | --------- | --------- | ------ | ------- | | YOLOv4 | 32 | FP16 | 303.27 | 0.730 | | YOLOv4 | 32 | INT8 | 682.14 | 0.608 | -## Reference +## References DarkNet: Pytorch-YOLOv4: diff --git a/models/cv/object_detection/yolov5/igie/README.md b/models/cv/object_detection/yolov5/igie/README.md index f71018d4..1465d40b 100644 --- a/models/cv/object_detection/yolov5/igie/README.md +++ b/models/cv/object_detection/yolov5/igie/README.md @@ -1,12 +1,12 @@ # YOLOv5-m -## Description +## Model Description The YOLOv5 architecture is designed for efficient and accurate object detection tasks in real-time scenarios. It employs a single convolutional neural network to simultaneously predict bounding boxes and class probabilities for multiple objects within an image. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash # Install libGL @@ -18,7 +18,7 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -33,7 +33,7 @@ python3 export.py --weight yolov5m.pt --output yolov5m.onnx onnxsim yolov5m.onnx yolov5m_opt.onnx ``` -## Inference +## Model Inference ```bash export DATASETS_DIR=/Path/to/coco/ @@ -57,7 +57,7 @@ bash scripts/infer_yolov5_int8_accuracy.sh bash scripts/infer_yolov5_int8_performance.sh ``` -## Results +## Model Results Model |BatchSize |Precision |FPS |MAP@0.5 |MAP@0.5:0.95 | --------|-----------|----------|---------|----------|-------------| diff --git a/models/cv/object_detection/yolov5/ixrt/README.md b/models/cv/object_detection/yolov5/ixrt/README.md index fd4e7e0b..d55114a5 100644 --- a/models/cv/object_detection/yolov5/ixrt/README.md +++ b/models/cv/object_detection/yolov5/ixrt/README.md @@ -1,12 +1,12 @@ # YOLOv5-m -## Description +## Model Description The YOLOv5 architecture is designed for efficient and accurate object detection tasks in real-time scenarios. It employs a single convolutional neural network to simultaneously predict bounding boxes and class probabilities for multiple objects within an image. The YOLOV5m is a medium-sized model. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash # Install libGL @@ -18,7 +18,7 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -45,7 +45,7 @@ python3 export.py --weights yolov5m.pt --include onnx --opset 11 --batch-size 32 mv yolov5m.onnx /Path/to/checkpoints ``` -## Inference +## Model Inference ```bash export PROJ_DIR=/Path/to/yolov5/ixrt @@ -75,7 +75,7 @@ bash scripts/infer_yolov5_int8_accuracy.sh bash scripts/infer_yolov5_int8_performance.sh ``` -## Results +## Model Results Model |BatchSize |Precision |FPS |MAP@0.5 |MAP@0.5:0.95 | --------|-----------|----------|---------|----------|-------------| diff --git a/models/cv/object_detection/yolov5s/ixrt/README.md b/models/cv/object_detection/yolov5s/ixrt/README.md index cf048372..a1f5cb8e 100755 --- a/models/cv/object_detection/yolov5s/ixrt/README.md +++ b/models/cv/object_detection/yolov5s/ixrt/README.md @@ -1,12 +1,12 @@ # YOLOv5s -## Description +## Model Description The YOLOv5 architecture is designed for efficient and accurate object detection tasks in real-time scenarios. It employs a single convolutional neural network to simultaneously predict bounding boxes and class probabilities for multiple objects within an image. The YOLOV5s is a tiny model. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash # Install libGL @@ -18,7 +18,7 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -44,7 +44,7 @@ mv yolov5s.onnx ../checkpoints popd ``` -## Inference +## Model Inference ```bash export PROJ_DIR=/Path/to/yolov5s/ixrt @@ -74,7 +74,7 @@ bash scripts/infer_yolov5s_int8_accuracy.sh bash scripts/infer_yolov5s_int8_performance.sh ``` -## Results +## Model Results Model |BatchSize |Precision |FPS |MAP@0.5 |MAP@0.5:0.95 | --------|-----------|----------|---------|----------|-------------| diff --git a/models/cv/object_detection/yolov6/igie/README.md b/models/cv/object_detection/yolov6/igie/README.md index af382052..eb186bdd 100644 --- a/models/cv/object_detection/yolov6/igie/README.md +++ b/models/cv/object_detection/yolov6/igie/README.md @@ -1,12 +1,12 @@ # YOLOv6 -## Description +## Model Description YOLOv6 integrates cutting-edge object detection advancements from industry and academia, incorporating recent innovations in network design, training strategies, testing techniques, quantization, and optimization methods. This culmination results in a suite of deployment-ready networks, accommodating varied use cases across different scales. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash # Install libGL @@ -18,7 +18,7 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -38,7 +38,7 @@ python3 deploy/ONNX/export_onnx.py --weights ../yolov6s.pt --img 640 --dynamic-b cd .. ``` -## Inference +## Model Inference ```bash export DATASETS_DIR=/Path/to/coco/ @@ -53,12 +53,12 @@ bash scripts/infer_yolov6_fp16_accuracy.sh bash scripts/infer_yolov6_fp16_performance.sh ``` -## Results +## Model Results Model |BatchSize |Precision |FPS |MAP@0.5 |MAP@0.5:0.95 | ---------|-----------|----------|----------|----------|-------------| yolov6 | 32 | FP16 | 994.902 | 0.617 | 0.448 | -## Reference +## References YOLOv6: diff --git a/models/cv/object_detection/yolov6/ixrt/README.md b/models/cv/object_detection/yolov6/ixrt/README.md index 5d0acbcd..cdcbe306 100644 --- a/models/cv/object_detection/yolov6/ixrt/README.md +++ b/models/cv/object_detection/yolov6/ixrt/README.md @@ -1,12 +1,12 @@ # YOLOv6 -## Description +## Model Description YOLOv6 integrates cutting-edge object detection advancements from industry and academia, incorporating recent innovations in network design, training strategies, testing techniques, quantization, and optimization methods. This culmination results in a suite of deployment-ready networks, accommodating varied use cases across different scales. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash # Install libGL @@ -18,7 +18,7 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -46,7 +46,7 @@ mv ../yolov6s.onnx ../data/ popd ``` -## Inference +## Model Inference ```bash export DATASETS_DIR=/Path/to/coco/ @@ -70,13 +70,13 @@ bash scripts/infer_yolov6_int8_accuracy.sh bash scripts/infer_yolov6_int8_performance.sh ``` -## Results +## Model Results | Model | BatchSize | Precision | FPS | MAP@0.5 | | ------ | --------- | --------- | -------- | ------- | | YOLOv6 | 32 | FP16 | 1107.511 | 0.617 | | YOLOv6 | 32 | INT8 | 2080.475 | 0.583 | -## Reference +## References YOLOv6: diff --git a/models/cv/object_detection/yolov7/igie/README.md b/models/cv/object_detection/yolov7/igie/README.md index d23f22d6..6c97ab60 100644 --- a/models/cv/object_detection/yolov7/igie/README.md +++ b/models/cv/object_detection/yolov7/igie/README.md @@ -1,12 +1,12 @@ # YOLOv7 -## Description +## Model Description YOLOv7 is a state-of-the-art real-time object detector that surpasses all known object detectors in both speed and accuracy in the range from 5 FPS to 160 FPS. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash # Install libGL @@ -18,7 +18,7 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -37,7 +37,7 @@ python3 export.py --weights ../yolov7.pt --simplify --img-size 640 640 --dynamic cd .. ``` -## Inference +## Model Inference ```bash export DATASETS_DIR=/Path/to/coco/ @@ -61,13 +61,13 @@ bash scripts/infer_yolov7_int8_accuracy.sh bash scripts/infer_yolov7_int8_performance.sh ``` -## Results +## Model Results Model |BatchSize |Precision |FPS |MAP@0.5 |MAP@0.5:0.95 | --------|-----------|----------|----------|----------|-------------| yolov7 | 32 | FP16 |341.681 | 0.695 | 0.509 | yolov7 | 32 | INT8 |669.783 | 0.685 | 0.473 | -## Reference +## References YOLOv7: diff --git a/models/cv/object_detection/yolov7/ixrt/README.md b/models/cv/object_detection/yolov7/ixrt/README.md index 2174c199..1ea58544 100644 --- a/models/cv/object_detection/yolov7/ixrt/README.md +++ b/models/cv/object_detection/yolov7/ixrt/README.md @@ -1,12 +1,12 @@ # YOLOv7 -## Description +## Model Description YOLOv7 is an object detection model based on the YOLO (You Only Look Once) series. It is an improved version of YOLOv5 developed by the Ultralytics team. YOLOv7 aims to enhance the performance and efficiency of object detection through a series of improvements including network architecture, training strategies, and data augmentation techniques, in order to achieve more accurate and faster object detection. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash # Install libGL @@ -18,7 +18,7 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -38,7 +38,7 @@ mkdir /Your_Projects/To/checkpoints mv yolov7.onnx /Path/to/checkpoints/yolov7m.onnx ``` -## Inference +## Model Inference ```bash export PROJ_DIR=/Path/to/yolov7/ixrt @@ -68,7 +68,7 @@ bash scripts/infer_yolov7_int8_accuracy.sh bash scripts/infer_yolov7_int8_performance.sh ``` -## Results +## Model Results Model |BatchSize |Precision |FPS |MAP@0.5 |MAP@0.5:0.95 | --------|-----------|----------|---------|----------|-------------| diff --git a/models/cv/object_detection/yolov8/igie/README.md b/models/cv/object_detection/yolov8/igie/README.md index b3ee9d5e..fc8fcaf4 100644 --- a/models/cv/object_detection/yolov8/igie/README.md +++ b/models/cv/object_detection/yolov8/igie/README.md @@ -1,12 +1,12 @@ # YOLOv8 -## Description +## Model Description Yolov8 combines speed and accuracy in real-time object detection tasks. With a focus on simplicity and efficiency, this model employs a single neural network to make predictions, enabling fast and accurate identification of objects in images or video streams. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash # Install libGL @@ -18,7 +18,7 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -30,7 +30,7 @@ Dataset: to download the valida python3 export.py --weight yolov8s.pt --batch 32 ``` -## Inference +## Model Inference ```bash export DATASETS_DIR=/Path/to/coco/ @@ -54,7 +54,7 @@ bash scripts/infer_yolov8_int8_accuracy.sh bash scripts/infer_yolov8_int8_performance.sh ``` -## Results +## Model Results Model |BatchSize |Precision |FPS |MAP@0.5 |MAP@0.5:0.95 | --------|-----------|----------|----------|----------|-------------| diff --git a/models/cv/object_detection/yolov8/ixrt/README.md b/models/cv/object_detection/yolov8/ixrt/README.md index 6ed7ea53..fdf1ef95 100644 --- a/models/cv/object_detection/yolov8/ixrt/README.md +++ b/models/cv/object_detection/yolov8/ixrt/README.md @@ -1,12 +1,12 @@ # YOLOv8 -## Description +## Model Description Yolov8 combines speed and accuracy in real-time object detection tasks. With a focus on simplicity and efficiency, this model employs a single neural network to make predictions, enabling fast and accurate identification of objects in images or video streams. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash # Install libGL @@ -18,7 +18,7 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -33,7 +33,7 @@ python3 export.py --weight yolov8.pt --batch 32 onnxsim yolov8.onnx ./checkpoints/yolov8.onnx ``` -## Inference +## Model Inference ```bash export PROJ_DIR=./ @@ -60,7 +60,7 @@ bash scripts/infer_yolov8_int8_accuracy.sh bash scripts/infer_yolov8_int8_performance.sh ``` -## Results +## Model Results | Model | BatchSize | Precision | FPS | MAP@0.5 | | ------ | --------- | --------- | -------- | ------- | diff --git a/models/cv/object_detection/yolov9/igie/README.md b/models/cv/object_detection/yolov9/igie/README.md index 9b3313e4..c8ef1785 100644 --- a/models/cv/object_detection/yolov9/igie/README.md +++ b/models/cv/object_detection/yolov9/igie/README.md @@ -1,18 +1,18 @@ # YOLOv9 -## Description +## Model Description YOLOv9 represents a major leap in real-time object detection by introducing innovations like Programmable Gradient Information (PGI) and the Generalized Efficient Layer Aggregation Network (GELAN), significantly improving efficiency, accuracy, and adaptability. Developed by an open-source team and building on the YOLOv5 codebase, it sets new benchmarks on the MS COCO dataset. YOLOv9's architecture effectively addresses information loss in deep neural networks, enhancing learning capacity and ensuring higher detection accuracy. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -22,7 +22,7 @@ Pretrained model: diff --git a/models/cv/object_detection/yolox/igie/README.md b/models/cv/object_detection/yolox/igie/README.md index 32c3d638..919f1bc7 100644 --- a/models/cv/object_detection/yolox/igie/README.md +++ b/models/cv/object_detection/yolox/igie/README.md @@ -1,12 +1,12 @@ # YOLOX -## Description +## Model Description YOLOX is an anchor-free version of YOLO, with a simpler design but better performance! It aims to bridge the gap between research and industrial communities. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash # Install libGL @@ -21,7 +21,7 @@ pip3 install -r requirements.txt source /opt/rh/devtoolset-7/enable ``` -### Download +### Prepare Resources Pretrained model: @@ -41,7 +41,7 @@ python3 tools/export_onnx.py -c ../yolox_m.pth -o 13 -n yolox-m --input input -- cd .. ``` -## Inference +## Model Inference ```bash export DATASETS_DIR=/Path/to/coco/ @@ -65,13 +65,13 @@ bash scripts/infer_yolox_int8_accuracy.sh bash scripts/infer_yolox_int8_performance.sh ``` -## Results +## Model Results Model |BatchSize |Precision |FPS |MAP@0.5 | --------|-----------|----------|----------|----------| yolox | 32 | FP16 |409.517 | 0.656 | yolox | 32 | INT8 |844.991 | 0.637 | -## Reference +## References YOLOX: diff --git a/models/cv/object_detection/yolox/ixrt/README.md b/models/cv/object_detection/yolox/ixrt/README.md index 0a19d5bf..42313aa8 100644 --- a/models/cv/object_detection/yolox/ixrt/README.md +++ b/models/cv/object_detection/yolox/ixrt/README.md @@ -1,13 +1,13 @@ # YOLOX -## Description +## Model Description YOLOX is an anchor-free version of YOLO, with a simpler design but better performance! It aims to bridge the gap between research and industrial communities. For more details, please refer to our [report on Arxiv](https://arxiv.org/abs/2107.08430). -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash # Install libGL @@ -19,7 +19,7 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -38,7 +38,7 @@ python3 tools/export_onnx.py --output-name ../yolox.onnx -n yolox-m -c yolox_m.p popd ``` -## Inference +## Model Inference ```bash # Set DATASETS_DIR @@ -73,13 +73,13 @@ bash scripts/infer_yolox_int8_accuracy.sh bash scripts/infer_yolox_int8_performance.sh ``` -## Results +## Model Results Model |BatchSize |Precision |FPS |MAP@0.5 | --------|-----------|----------|----------|----------| yolox | 32 | FP16 | 424.53 | 0.656 | yolox | 32 | INT8 | 832.16 | 0.647 | -## Reference +## References YOLOX: diff --git a/models/cv/ocr/kie_layoutxlm/igie/README.md b/models/cv/ocr/kie_layoutxlm/igie/README.md index 75f79909..c22a573a 100644 --- a/models/cv/ocr/kie_layoutxlm/igie/README.md +++ b/models/cv/ocr/kie_layoutxlm/igie/README.md @@ -1,10 +1,10 @@ # LayoutXLM -## Description +## Model Description LayoutXLM is a groundbreaking multimodal pre-trained model for multilingual document understanding, achieving exceptional performance by integrating text, layout, and image data. -## Setup +## Model Preparation ```shell pip3 install -r requirements.txt @@ -41,7 +41,7 @@ cd .. onnxsim kie_ser.onnx kie_ser_opt.onnx ``` -## Inference +## Model Inference ```shell export DATASETS_DIR=/Path/to/XFUND/ @@ -56,12 +56,12 @@ bash scripts/infer_kie_layoutxlm_fp16_accuracy.sh bash scripts/infer_kie_layoutxlm_fp16_performance.sh ``` -## Results +## Model Results | Model | BatchSize | Precision | FPS | Hmean | | ------- | --------- | --------- | ------ | ------ | | Kie_ser | 8 | FP16 | 107.65 | 93.61% | -## Reference +## References PaddleOCR: diff --git a/models/cv/ocr/svtr/igie/README.md b/models/cv/ocr/svtr/igie/README.md index 47ea9d78..5502ef33 100644 --- a/models/cv/ocr/svtr/igie/README.md +++ b/models/cv/ocr/svtr/igie/README.md @@ -1,8 +1,8 @@ # SVTR -## Description +## Model Description SVTR proposes a single vision model for scene text recognition. This model completely abandons sequence modeling within the patch-wise image tokenization framework. Under the premise of competitive accuracy, the model has fewer parameters and faster speed. -## Setup +## Model Preparation ```shell # Install libGL ## CentOS @@ -38,7 +38,7 @@ cd .. onnxsim SVTR.onnx SVTR_opt.onnx ``` -## Inference +## Model Inference ```shell export DATASETS_DIR=/Path/to/lmdb_evaluation/ ``` @@ -50,10 +50,10 @@ bash scripts/infer_svtr_fp16_accuracy.sh bash scripts/infer_svtr_fp16_performance.sh ``` -## Results +## Model Results Model |BatchSize |Precision |FPS |Acc | --------|-----------|----------|----------|----------| SVTR | 32 | FP16 | 4936.47 | 88.29% | -## Reference +## References PaddleOCR: https://github.com/PaddlePaddle/PaddleOCR/blob/main/docs/algorithm/text_recognition/algorithm_rec_svtr.md diff --git a/models/cv/pose_estimation/hrnetpose/igie/README.md b/models/cv/pose_estimation/hrnetpose/igie/README.md index 09771216..3247e11f 100644 --- a/models/cv/pose_estimation/hrnetpose/igie/README.md +++ b/models/cv/pose_estimation/hrnetpose/igie/README.md @@ -1,12 +1,12 @@ # HRNetPose -## Description +## Model Description HRNetPose (High-Resolution Network for Pose Estimation) is a high-performance human pose estimation model introduced in the paper "Deep High-Resolution Representation Learning for Human Pose Estimation". It is designed to address the limitations of traditional methods by maintaining high-resolution feature representations throughout the network, enabling more accurate detection of human keypoints. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash # Install libGL @@ -18,7 +18,7 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -38,7 +38,7 @@ python3 export.py --weight hrnet_w32_coco_256x192-c78dce93_20200708.pth --cfg td onnxsim hrnetpose.onnx hrnetpose_opt.onnx ``` -## Inference +## Model Inference ```bash export DATASETS_DIR=/Path/to/coco/ @@ -53,12 +53,12 @@ bash scripts/infer_hrnetpose_fp16_accuracy.sh bash scripts/infer_hrnetpose_fp16_performance.sh ``` -## Results +## Model Results | Model | BatchSize | Input Shape | Precision | FPS | mAP@0.5(%) | | :---------: | :-------: | :---------: | :-------: | :-------: | :--------: | | HRNetPose | 32 | 252x196 | FP16 | 1831.20 | 0.926 | -## Reference +## References mmpose: diff --git a/models/cv/pose_estimation/lightweight_openpose/ixrt/README.md b/models/cv/pose_estimation/lightweight_openpose/ixrt/README.md index 4fa8923c..414d6bcd 100644 --- a/models/cv/pose_estimation/lightweight_openpose/ixrt/README.md +++ b/models/cv/pose_estimation/lightweight_openpose/ixrt/README.md @@ -1,12 +1,16 @@ # Lightweight OpenPose -## Description +## Model Description -This work heavily optimizes the OpenPose approach to reach real-time inference on CPU with negliable accuracy drop. It detects a skeleton (which consists of keypoints and connections between them) to identify human poses for every person inside the image. The pose may contain up to 18 keypoints: ears, eyes, nose, neck, shoulders, elbows, wrists, hips, knees, and ankles. On COCO 2017 Keypoint Detection validation set this code achives 40% AP for the single scale inference (no flip or any post-processing done). +This work heavily optimizes the OpenPose approach to reach real-time inference on CPU with negliable accuracy drop. It +detects a skeleton (which consists of keypoints and connections between them) to identify human poses for every person +inside the image. The pose may contain up to 18 keypoints: ears, eyes, nose, neck, shoulders, elbows, wrists, hips, +knees, and ankles. On COCO 2017 Keypoint Detection validation set this code achives 40% AP for the single scale +inference (no flip or any post-processing done). -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash # Install libGL @@ -18,9 +22,10 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Download -- dataset: http://cocodataset.org/#download -- checkpoints: https://download.01.org/opencv/openvino_training_extensions/models/human_pose_estimation/checkpoint_iter_370000.pth +### Prepare Resources + +- dataset: +- checkpoints: ### Model Conversion @@ -35,7 +40,7 @@ mkdir -p checkpoints onnxsim ./lightweight-human-pose-estimation.pytorch/human-pose-estimation.onnx ./checkpoints/lightweight_openpose.onnx ``` -## Inference +## Model Inference ```bash export DATASETS_DIR=/Path/to/coco_pose/ @@ -51,12 +56,12 @@ bash scripts/infer_lightweight_openpose_fp16_accuracy.sh bash scripts/infer_lightweight_openpose_fp16_performance.sh ``` -## Results +## Model Results -Model |BatchSize |Precision |FPS |IOU@0.5 |IOU@0.5:0.95 | -----------|-----------|----------|----------|----------|---------------| -Lightweight OpenPose | 1 | FP16 | 21030.833 | 0.660 | 0.401 | +| Model | BatchSize | Precision | FPS | IOU@0.5 | IOU@0.5:0.95 | +|----------------------|-----------|-----------|-----------|---------|--------------| +| Lightweight OpenPose | 1 | FP16 | 21030.833 | 0.660 | 0.401 | -## Reference +## References -https://github.com/Daniil-Osokin/lightweight-human-pose-estimation.pytorch \ No newline at end of file + diff --git a/models/cv/pose_estimation/rtmpose/igie/README.md b/models/cv/pose_estimation/rtmpose/igie/README.md index 9497dcfd..3681d7a3 100644 --- a/models/cv/pose_estimation/rtmpose/igie/README.md +++ b/models/cv/pose_estimation/rtmpose/igie/README.md @@ -1,12 +1,12 @@ # RTMPose -## Description +## Model Description RTMPose, a state-of-the-art framework developed by Shanghai AI Laboratory, excels in real-time multi-person pose estimation by integrating an innovative model architecture with the efficiency of the MMPose foundation. The framework's architecture is meticulously designed to enhance performance and reduce latency, making it suitable for a variety of applications where real-time analysis is crucial. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash # Install libGL @@ -18,7 +18,7 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -38,7 +38,7 @@ python3 export.py --weight rtmpose-m_simcc-aic-coco_pt-aic-coco_420e-256x192-63e onnxsim rtmpose.onnx rtmpose_opt.onnx ``` -## Inference +## Model Inference ```bash export DATASETS_DIR=/Path/to/coco/ @@ -53,13 +53,13 @@ bash scripts/infer_rtmpose_fp16_accuracy.sh bash scripts/infer_rtmpose_fp16_performance.sh ``` -## Results +## Model Results Model |BatchSize |Precision |FPS |IOU@0.5 |IOU@0.5:0.95 | ----------|-----------|----------|----------|----------|---------------| RTMPose | 32 | FP16 | 2313.33 | 0.936 | 0.773 | -## Reference +## References mmpose: diff --git a/models/cv/pose_estimation/rtmpose/ixrt/README.md b/models/cv/pose_estimation/rtmpose/ixrt/README.md index 51a832a1..529b9fae 100644 --- a/models/cv/pose_estimation/rtmpose/ixrt/README.md +++ b/models/cv/pose_estimation/rtmpose/ixrt/README.md @@ -1,12 +1,12 @@ # RTMPose -## Description +## Model Description RTMPose, a state-of-the-art framework developed by Shanghai AI Laboratory, excels in real-time multi-person pose estimation by integrating an innovative model architecture with the efficiency of the MMPose foundation. The framework's architecture is meticulously designed to enhance performance and reduce latency, making it suitable for a variety of applications where real-time analysis is crucial. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash # Install libGL @@ -18,7 +18,7 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -39,7 +39,7 @@ python3 export.py --weight data/rtmpose/rtmpose-m_simcc-aic-coco_pt-aic-coco_420 onnxsim data/rtmpose/rtmpose.onnx data/rtmpose/rtmpose_opt.onnx ``` -## Inference +## Model Inference ### FP16 diff --git a/models/multimodal/diffusion_model/stable-diffusion/README.md b/models/multimodal/diffusion_model/stable-diffusion/README.md index 93bc5f3d..378081a2 100644 --- a/models/multimodal/diffusion_model/stable-diffusion/README.md +++ b/models/multimodal/diffusion_model/stable-diffusion/README.md @@ -4,9 +4,9 @@ Stable Diffusion is a latent text-to-image diffusion model capable of generating photo-realistic images given any text input. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash # Install libGL @@ -19,7 +19,7 @@ pip3 install http://files.deepspark.org.cn:880/deepspark/add-ons/diffusers-0.31. pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Download the runwayml/stable-diffusion-v1-5 from [huggingface page](https://huggingface.co/runwayml/stable-diffusion-v1-5). @@ -29,13 +29,13 @@ mkdir -p data/ ln -s /path/to/stable-diffusion-v1-5 ./data/ ``` -## Inference +## Model Inference ```bash export ENABLE_IXFORMER_INFERENCE=1 python3 demo.py ``` -## Reference +## References - [diffusers](https://github.com/huggingface/diffusers) diff --git a/models/multimodal/vision_language_model/chameleon_7b/vllm/README.md b/models/multimodal/vision_language_model/chameleon_7b/vllm/README.md index 879367dd..a7ee5fbc 100755 --- a/models/multimodal/vision_language_model/chameleon_7b/vllm/README.md +++ b/models/multimodal/vision_language_model/chameleon_7b/vllm/README.md @@ -1,12 +1,12 @@ # Chameleon -## Description +## Model Description Chameleon, an AI system that mitigates these limitations by augmenting LLMs with plug-and-play modules for compositional reasoning. Chameleon synthesizes programs by composing various tools (e.g., LLMs, off-the-shelf vision models, web search engines, Python functions, and heuristic-based modules) for accomplishing complex reasoning tasks. At the heart of Chameleon is an LLM-based planner that assembles a sequence of tools to execute to generate the final response. We showcase the effectiveness of Chameleon on two multi-modal knowledge-intensive reasoning tasks: ScienceQA and TabMWP. Chameleon, powered by GPT-4, achieves an 86.54% overall accuracy on ScienceQA, improving the best published few-shot result by 11.37%. On TabMWP, GPT-4-powered Chameleon improves the accuracy by 17.0%, lifting the state of the art to 98.78%. Our analysis also shows that the GPT-4-powered planner exhibits more consistent and rational tool selection via inferring potential constraints from instructions, compared to a ChatGPT-powered planner. -## Setup +## Model Preparation -### Install +### Install Dependencies In order to run the model smoothly, you need to get the sdk from [resource center](https://support.iluvatar.com/#/ProductLine?id=2) of Iluvatar CoreX official website. @@ -18,7 +18,7 @@ yum install -y mesa-libGL apt install -y libgl1-mesa-glx ``` -### Download +### Prepare Resources - Model: @@ -27,7 +27,7 @@ apt install -y libgl1-mesa-glx mkdir data ``` -## Inference +## Model Inference ```bash export VLLM_ASSETS_CACHE=../vllm/ diff --git a/models/multimodal/vision_language_model/clip/ixformer/README.md b/models/multimodal/vision_language_model/clip/ixformer/README.md index e8b90f57..2d768606 100644 --- a/models/multimodal/vision_language_model/clip/ixformer/README.md +++ b/models/multimodal/vision_language_model/clip/ixformer/README.md @@ -1,12 +1,12 @@ # CLIP (IxFormer) -## Description +## Model Description CLIP (Contrastive Language-Image Pre-Training) is a neural network trained on a variety of (image, text) pairs. It can be instructed in natural language to predict the most relevant text snippet, given an image, without directly optimizing for the task, similarly to the zero-shot capabilities of GPT-2 and 3. We found CLIP matches the performance of the original ResNet50 on ImageNet zero-shot without using any of the original 1.28M labeled examples, overcoming several major challenges in computer vision. -## Setup +## Model Preparation -### Install +### Install Dependencies In order to run the model smoothly, you need to get the sdk from [resource center](https://support.iluvatar.com/#/ProductLine?id=2) of Iluvatar CoreX official website. @@ -20,7 +20,7 @@ apt install -y libgl1-mesa-glx pip3 install -U transformers==4.27.1 ``` -### Download +### Prepare Resources Pretrained model: Go to the website to find the pre-trained model you need. Here, we choose clip-vit-base-patch32. diff --git a/models/multimodal/vision_language_model/fuyu_8b/vllm/README.md b/models/multimodal/vision_language_model/fuyu_8b/vllm/README.md index 7f2526b9..e0dbfcc0 100755 --- a/models/multimodal/vision_language_model/fuyu_8b/vllm/README.md +++ b/models/multimodal/vision_language_model/fuyu_8b/vllm/README.md @@ -1,14 +1,14 @@ # Fuyu-8B -## Description +## Model Description Fuyu-8B is a multi-modal text and image transformer trained by Adept AI. Architecturally, Fuyu is a vanilla decoder-only transformer - there is no image encoder. Image patches are instead linearly projected into the first layer of the transformer, bypassing the embedding lookup. We simply treat the transformer decoder like an image transformer (albeit with no pooling and causal attention). -## Setup +## Model Preparation -### Install +### Install Dependencies In order to run the model smoothly, you need to get the sdk from [resource center](https://support.iluvatar.com/#/ProductLine?id=2) of Iluvatar CoreX official website. @@ -20,7 +20,7 @@ yum install -y mesa-libGL apt install -y libgl1-mesa-glx ``` -### Download +### Prepare Resources - Model: @@ -29,7 +29,7 @@ apt install -y libgl1-mesa-glx mkdir data ``` -## Inference +## Model Inference ```bash export VLLM_ASSETS_CACHE=../vllm/ diff --git a/models/multimodal/vision_language_model/intern_vl/vllm/README.md b/models/multimodal/vision_language_model/intern_vl/vllm/README.md index c8a52779..033860af 100644 --- a/models/multimodal/vision_language_model/intern_vl/vllm/README.md +++ b/models/multimodal/vision_language_model/intern_vl/vllm/README.md @@ -1,12 +1,12 @@ # InternVL2-4B -## Description +## Model Description InternVL2-4B is a large-scale multimodal model developed by WeTab AI, designed to handle a wide range of tasks involving both text and visual data. With 4 billion parameters, it is capable of understanding and generating complex patterns in data, making it suitable for applications such as image recognition, natural language processing, and multimodal learning. -## Setup +## Model Preparation -### Install +### Install Dependencies In order to run the model smoothly, you need to get the sdk from [resource center](https://support.iluvatar.com/#/ProductLine?id=2) of Iluvatar CoreX official website. @@ -23,7 +23,7 @@ pip3 install triton pip3 install ixformer ``` -### Download +### Prepare Resources - Model: @@ -33,7 +33,7 @@ mkdir -p data/intern_vl ln -s /path/to/InternVL2-4B ./data/intern_vl ``` -## Inference +## Model Inference ```bash export CUDA_VISIBLE_DEVICES=0,1 diff --git a/models/multimodal/vision_language_model/llava/vllm/README.md b/models/multimodal/vision_language_model/llava/vllm/README.md index 2ceeaed8..db7639e6 100644 --- a/models/multimodal/vision_language_model/llava/vllm/README.md +++ b/models/multimodal/vision_language_model/llava/vllm/README.md @@ -1,12 +1,12 @@ # LLava -## Description +## Model Description LLaVA is an open-source chatbot trained by fine-tuning LLaMA/Vicuna on GPT-generated multimodal instruction-following data. It is an auto-regressive language model, based on the transformer architecture.The LLaVA-NeXT model was proposed in LLaVA-NeXT: Improved reasoning, OCR, and world knowledge by Haotian Liu, Chunyuan Li, Yuheng Li, Bo Li, Yuanhan Zhang, Sheng Shen, Yong Jae Lee. LLaVa-NeXT (also called LLaVa-1.6) improves upon LLaVa-1.5 by increasing the input image resolution and training on an improved visual instruction tuning dataset to improve OCR and common sense reasoning. -## Setup +## Model Preparation -### Install +### Install Dependencies In order to run the model smoothly, you need to get the sdk from [resource center](https://support.iluvatar.com/#/ProductLine?id=2) of Iluvatar CoreX official website. @@ -19,7 +19,7 @@ apt install -y libgl1-mesa-glx pip3 install transformers ``` -### Download +### Prepare Resources -llava-v1.6-vicuna-7b-hf: @@ -29,7 +29,7 @@ mkdir data ``` -## Inference +## Model Inference ```bash export PT_SDPA_ENABLE_HEAD_DIM_PADDING=1 diff --git a/models/multimodal/vision_language_model/llava_next_video_7b/vllm/README.md b/models/multimodal/vision_language_model/llava_next_video_7b/vllm/README.md index 4fb09f4f..b860fbc8 100755 --- a/models/multimodal/vision_language_model/llava_next_video_7b/vllm/README.md +++ b/models/multimodal/vision_language_model/llava_next_video_7b/vllm/README.md @@ -1,12 +1,12 @@ # LLaVA-Next-Video-7B -## Description +## Model Description LLaVA-Next-Video is an open-source chatbot trained by fine-tuning LLM on multimodal instruction-following data. The model is buit on top of LLaVa-NeXT by tuning on a mix of video and image data to achieves better video understanding capabilities. The videos were sampled uniformly to be 32 frames per clip. The model is a current SOTA among open-source models on VideoMME bench. Base LLM: lmsys/vicuna-7b-v1.5 -## Setup +## Model Preparation -### Install +### Install Dependencies In order to run the model smoothly, you need to get the sdk from [resource center](https://support.iluvatar.com/#/ProductLine?id=2) of Iluvatar CoreX official website. @@ -18,7 +18,7 @@ yum install -y mesa-libGL apt install -y libgl1-mesa-glx ``` -### Download +### Prepare Resources - Model: @@ -27,7 +27,7 @@ apt install -y libgl1-mesa-glx mkdir data ``` -## Inference +## Model Inference ```bash export VLLM_ASSETS_CACHE=../vllm/ diff --git a/models/multimodal/vision_language_model/minicpm_v_2/vllm/README.md b/models/multimodal/vision_language_model/minicpm_v_2/vllm/README.md index d2b2dd86..50f17266 100644 --- a/models/multimodal/vision_language_model/minicpm_v_2/vllm/README.md +++ b/models/multimodal/vision_language_model/minicpm_v_2/vllm/README.md @@ -1,12 +1,12 @@ # MiniCPM V2 -## Description +## Model Description MiniCPM V2 is a compact and efficient language model designed for various natural language processing (NLP) tasks. Building on its predecessor, MiniCPM-V-1, this model integrates advancements in architecture and optimization techniques, making it suitable for deployment in resource-constrained environments.s -## Setup +## Model Preparation -### Install +### Install Dependencies In order to run the model smoothly, you need to get the sdk from [resource center](https://support.iluvatar.com/#/ProductLine?id=2) of Iluvatar CoreX official website. @@ -21,7 +21,7 @@ pip3 install transformers pip3 install --user --upgrade pillow -i https://pypi.tuna.tsinghua.edu.cn/simple ``` -### Download +### Prepare Resources - Model: Note: Due to the official weights missing some necessary files for vllm execution, you can download the additional files from here: to ensure that the file directory matches the structure shown here: . @@ -32,7 +32,7 @@ mkdir data ``` -## Inference +## Model Inference ```bash export PT_SDPA_ENABLE_HEAD_DIM_PADDING=1 diff --git a/models/nlp/llm/baichuan2-7b/vllm/README.md b/models/nlp/llm/baichuan2-7b/vllm/README.md index 9a8cb1ec..930e7662 100755 --- a/models/nlp/llm/baichuan2-7b/vllm/README.md +++ b/models/nlp/llm/baichuan2-7b/vllm/README.md @@ -1,15 +1,15 @@ # Baichuan2-7B (vLLM) -## Description +## Model Description Baichuan 2 is a new generation open-source large language model launched by Baichuan Intelligence. It is trained on high-quality data with 26 trillion tokens, which sounds like a substantial dataset. Baichuan 2 achieves state-of-the-art performance on various authoritative Chinese, multilingual, and domain-specific benchmarks of similar size, indicating its excellent capabilities in language understanding and generation.This release includes Base and Chat versions of 7B. -## Setup +## Model Preparation -### Install +### Install Dependencies In order to run the model smoothly, you need to get the sdk from [resource center](https://support.iluvatar.com/#/ProductLine?id=2) of Iluvatar CoreX official website. @@ -24,7 +24,7 @@ apt install -y libgl1-mesa-glx pip3 install transformers ``` -### Download +### Prepare Resources Pretrained model: [https://huggingface.co/baichuan-inc/Baichuan2-7B-Base/tree/main](https://huggingface.co/baichuan-inc/Baichuan2-7B-Base/tree/main) @@ -56,7 +56,7 @@ python3 convert2int8.py --model-path /data/baichuan/Baichuan2-7B-Base/ python3 offline_inference.py --model /data/baichuan/Baichuan2-7B-Base/int8/ --chat_template template_baichuan.jinja --quantization w8a16 --max-num-seqs 1 --max-model-len 256 --trust-remote-code --temperature 0.0 --max-tokens 256 ``` -## Results +## Model Results | Model | Precision | tokens | QPS | |--------------|-----------|--------|--------| diff --git a/models/nlp/llm/chatglm3-6b-32k/vllm/README.md b/models/nlp/llm/chatglm3-6b-32k/vllm/README.md index c74b04fe..ff3f125b 100644 --- a/models/nlp/llm/chatglm3-6b-32k/vllm/README.md +++ b/models/nlp/llm/chatglm3-6b-32k/vllm/README.md @@ -1,6 +1,6 @@ # ChatGLM3-6B-32K (vLLM) -## Description +## Model Description ChatGLM3-6B-32K further enhances the understanding of long text capabilities based on ChatGLM3-6B, enabling better handling of contexts up to 32K in length. Specifically, we have updated the positional encoding and designed more @@ -8,9 +8,9 @@ targeted long text training methods, using a 32K context length during the train context length is mostly within 8K, we recommend using ChatGLM3-6B; if you need to handle context lengths exceeding 8K, we recommend using ChatGLM3-6B-32K. -## Setup +## Model Preparation -### Install +### Install Dependencies In order to run the model smoothly, you need to get the sdk from [resource center](https://support.iluvatar.com/#/ProductLine?id=2) of Iluvatar CoreX official website. @@ -25,7 +25,7 @@ apt install -y libgl1-mesa-glx pip3 install transformers ``` -### Download +### Prepare Resources Pretrained model: @@ -55,7 +55,7 @@ python3 -m vllm.entrypoints.openai.api_server --model /data/chatglm/chatglm3-6b- python3 server_inference.py --host 127.0.0.1 --port 12345 --model_path /data/chatglm/chatglm3-6b-32k ``` -## Results +## Model Results | Model | Precision | tokens | QPS | |-----------------|-----------|--------|--------| diff --git a/models/nlp/llm/chatglm3-6b/vllm/README.md b/models/nlp/llm/chatglm3-6b/vllm/README.md index 5dc17403..0a5ee9a0 100644 --- a/models/nlp/llm/chatglm3-6b/vllm/README.md +++ b/models/nlp/llm/chatglm3-6b/vllm/README.md @@ -1,14 +1,14 @@ # ChatGLM3-6B (vLLM) -## Description +## Model Description ChatGLM3-6B is trained on large-scale natural language text data, enabling it to understand and generate text. It can be applied to various natural language processing tasks such as dialogue generation, text summarization, and language translation. -## Setup +## Model Preparation -### Install +### Install Dependencies In order to run the model smoothly, you need to get the sdk from [resource center](https://support.iluvatar.com/#/ProductLine?id=2) of Iluvatar CoreX official website. @@ -24,7 +24,7 @@ pip3 install vllm pip3 install transformers ``` -### Download +### Prepare Resources Pretrained model: diff --git a/models/nlp/llm/deepseek-r1-distill-llama-70b/vllm/README.md b/models/nlp/llm/deepseek-r1-distill-llama-70b/vllm/README.md index 5b475134..1191913f 100644 --- a/models/nlp/llm/deepseek-r1-distill-llama-70b/vllm/README.md +++ b/models/nlp/llm/deepseek-r1-distill-llama-70b/vllm/README.md @@ -1,14 +1,14 @@ # DeepSeek-R1-Distill-Llama-70B -## Description +## Model Description DeepSeek-R1-Distill models are fine-tuned based on open-source models, using samples generated by DeepSeek-R1. We slightly change their configs and tokenizers. We open-source distilled 1.5B, 7B, 8B, 14B, 32B, and 70B checkpoints based on Qwen2.5 and Llama3 series to the community. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash # Install libGL @@ -18,7 +18,7 @@ yum install -y mesa-libGL apt install -y libgl1-mesa-glx ``` -### Download +### Prepare Resources - Model: @@ -40,6 +40,6 @@ python3 offline_inference.py --model ./data/DeepSeek-R1-Distill-Llama-70B --max- vllm serve data/DeepSeek-R1-Distill-Llama-70B --tensor-parallel-size 8 --max-model-len 32768 --enforce-eager --trust-remote-code ``` -## Reference +## References [DeepSeek-R1](https://github.com/deepseek-ai/DeepSeek-R1) diff --git a/models/nlp/llm/deepseek-r1-distill-llama-8b/vllm/README.md b/models/nlp/llm/deepseek-r1-distill-llama-8b/vllm/README.md index 45f29110..96dd42d0 100644 --- a/models/nlp/llm/deepseek-r1-distill-llama-8b/vllm/README.md +++ b/models/nlp/llm/deepseek-r1-distill-llama-8b/vllm/README.md @@ -1,14 +1,14 @@ # DeepSeek-R1-Distill-Llama-8B -## Description +## Model Description DeepSeek-R1-Distill models are fine-tuned based on open-source models, using samples generated by DeepSeek-R1. We slightly change their configs and tokenizers. We open-source distilled 1.5B, 7B, 8B, 14B, 32B, and 70B checkpoints based on Qwen2.5 and Llama3 series to the community. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash # Install libGL @@ -18,7 +18,7 @@ yum install -y mesa-libGL apt install -y libgl1-mesa-glx ``` -### Download +### Prepare Resources - Model: @@ -40,12 +40,12 @@ python3 offline_inference.py --model ./data/DeepSeek-R1-Distill-Llama-8B --max-t vllm serve data/DeepSeek-R1-Distill-Llama-8B --tensor-parallel-size 2 --max-model-len 32768 --enforce-eager --trust-remote-code ``` -## Results +## Model Results | Model | QPS | |------------------------------|--------| | DeepSeek-R1-Distill-Llama-8B | 105.33 | -## Reference +## References [DeepSeek-R1](https://github.com/deepseek-ai/DeepSeek-R1) diff --git a/models/nlp/llm/deepseek-r1-distill-qwen-1.5b/vllm/README.md b/models/nlp/llm/deepseek-r1-distill-qwen-1.5b/vllm/README.md index e10d0045..1c711cbb 100644 --- a/models/nlp/llm/deepseek-r1-distill-qwen-1.5b/vllm/README.md +++ b/models/nlp/llm/deepseek-r1-distill-qwen-1.5b/vllm/README.md @@ -1,14 +1,14 @@ # DeepSeek-R1-Distill-Qwen-1.5B -## Description +## Model Description DeepSeek-R1-Distill models are fine-tuned based on open-source models, using samples generated by DeepSeek-R1. We slightly change their configs and tokenizers. We open-source distilled 1.5B, 7B, 8B, 14B, 32B, and 70B checkpoints based on Qwen2.5 and Llama3 series to the community. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash # Install libGL @@ -18,7 +18,7 @@ yum install -y mesa-libGL apt install -y libgl1-mesa-glx ``` -### Download +### Prepare Resources - Model: @@ -40,12 +40,12 @@ python3 offline_inference.py --model ./data/DeepSeek-R1-Distill-Qwen-1.5B --max- vllm serve data/DeepSeek-R1-Distill-Qwen-1.5B --tensor-parallel-size 2 --max-model-len 32768 --enforce-eager --trust-remote-code ``` -## Results +## Model Results | Model | QPS | |-------------------------------|--------| | DeepSeek-R1-Distill-Qwen-1.5B | 259.42 | -## Reference +## References [DeepSeek-R1](https://github.com/deepseek-ai/DeepSeek-R1) diff --git a/models/nlp/llm/deepseek-r1-distill-qwen-14b/vllm/README.md b/models/nlp/llm/deepseek-r1-distill-qwen-14b/vllm/README.md index 27cade52..b3307bcc 100644 --- a/models/nlp/llm/deepseek-r1-distill-qwen-14b/vllm/README.md +++ b/models/nlp/llm/deepseek-r1-distill-qwen-14b/vllm/README.md @@ -1,14 +1,14 @@ # DeepSeek-R1-Distill-Qwen-14B -## Description +## Model Description DeepSeek-R1-Distill models are fine-tuned based on open-source models, using samples generated by DeepSeek-R1. We slightly change their configs and tokenizers. We open-source distilled 1.5B, 7B, 8B, 14B, 32B, and 70B checkpoints based on Qwen2.5 and Llama3 series to the community. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash # Install libGL @@ -18,7 +18,7 @@ yum install -y mesa-libGL apt install -y libgl1-mesa-glx ``` -### Download +### Prepare Resources - Model: @@ -40,12 +40,12 @@ python3 offline_inference.py --model ./data/DeepSeek-R1-Distill-Qwen-14B --max-t vllm serve data/DeepSeek-R1-Distill-Qwen-14B --tensor-parallel-size 2 --max-model-len 32768 --enforce-eager --trust-remote-code ``` -## Results +## Model Results | Model | QPS | |------------------------------|-------| | DeepSeek-R1-Distill-Qwen-14B | 88.01 | -## Reference +## References [DeepSeek-R1](https://github.com/deepseek-ai/DeepSeek-R1) diff --git a/models/nlp/llm/deepseek-r1-distill-qwen-32b/vllm/README.md b/models/nlp/llm/deepseek-r1-distill-qwen-32b/vllm/README.md index bc3fab89..75e9eb2d 100644 --- a/models/nlp/llm/deepseek-r1-distill-qwen-32b/vllm/README.md +++ b/models/nlp/llm/deepseek-r1-distill-qwen-32b/vllm/README.md @@ -1,14 +1,14 @@ # DeepSeek-R1-Distill-Qwen-32B -## Description +## Model Description DeepSeek-R1-Distill models are fine-tuned based on open-source models, using samples generated by DeepSeek-R1. We slightly change their configs and tokenizers. We open-source distilled 1.5B, 7B, 8B, 14B, 32B, and 70B checkpoints based on Qwen2.5 and Llama3 series to the community. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash # Install libGL @@ -18,7 +18,7 @@ yum install -y mesa-libGL apt install -y libgl1-mesa-glx ``` -### Download +### Prepare Resources - Model: @@ -40,12 +40,12 @@ python3 offline_inference.py --model ./data/DeepSeek-R1-Distill-Qwen-32B --max-t vllm serve data/DeepSeek-R1-Distill-Qwen-32B --tensor-parallel-size 4 --max-model-len 32768 --enforce-eager --trust-remote-code ``` -## Results +## Model Results | Model | QPS | |------------------------------|-------| | DeepSeek-R1-Distill-Qwen-32B | 68.30 | -## Reference +## References [DeepSeek-R1](https://github.com/deepseek-ai/DeepSeek-R1) diff --git a/models/nlp/llm/deepseek-r1-distill-qwen-7b/vllm/README.md b/models/nlp/llm/deepseek-r1-distill-qwen-7b/vllm/README.md index 8cab93a6..d50cb9e4 100644 --- a/models/nlp/llm/deepseek-r1-distill-qwen-7b/vllm/README.md +++ b/models/nlp/llm/deepseek-r1-distill-qwen-7b/vllm/README.md @@ -1,14 +1,14 @@ # DeepSeek-R1-Distill-Qwen-7B -## Description +## Model Description DeepSeek-R1-Distill models are fine-tuned based on open-source models, using samples generated by DeepSeek-R1. We slightly change their configs and tokenizers. We open-source distilled 1.5B, 7B, 8B, 14B, 32B, and 70B checkpoints based on Qwen2.5 and Llama3 series to the community. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash # Install libGL @@ -18,7 +18,7 @@ yum install -y mesa-libGL apt install -y libgl1-mesa-glx ``` -### Download +### Prepare Resources - Model: @@ -40,12 +40,12 @@ python3 offline_inference.py --model ./data/DeepSeek-R1-Distill-Qwen-7B --max-to vllm serve data/DeepSeek-R1-Distill-Qwen-7B --tensor-parallel-size 2 --max-model-len 32768 --enforce-eager --trust-remote-code ``` -## Results +## Model Results | Model | QPS | |-----------------------------|-------| | DeepSeek-R1-Distill-Qwen-7B | 90.48 | -## Reference +## References [DeepSeek-R1](https://github.com/deepseek-ai/DeepSeek-R1) diff --git a/models/nlp/llm/llama2-13b/trtllm/README.md b/models/nlp/llm/llama2-13b/trtllm/README.md index d525ad9f..003d90bb 100755 --- a/models/nlp/llm/llama2-13b/trtllm/README.md +++ b/models/nlp/llm/llama2-13b/trtllm/README.md @@ -1,15 +1,15 @@ # Llama2 13B (TensorRT-LLM) -## Description +## Model Description The Llama2 model is part of the Llama project which aims to unlock the power of large language models. The latest version of the Llama model is now accessible to individuals, creators, researchers, and businesses of all sizes. It includes model weights and starting code for pre-trained and fine-tuned Llama language models with parameters ranging from 7B to 70B. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash # Install libGL @@ -21,7 +21,7 @@ apt install -y libgl1-mesa-glx bash scripts/set_environment.sh . ``` -### Download +### Prepare Resources - Model: - Dataset: @@ -36,7 +36,7 @@ mkdir -p rouge/ wget --no-check-certificate https://raw.githubusercontent.com/huggingface/evaluate/main/metrics/rouge/rouge.py -P rouge ``` -## Inference +## Model Inference ```bash export CUDA_VISIBLE_DEVICES=0,1 @@ -52,7 +52,7 @@ bash scripts/test_trtllm_llama2_13b_gpu2_build.sh bash scripts/test_trtllm_llama2_13b_gpu2.sh ``` -## Results +## Model Results | Model | tokens | tokens per second | | ---------- | ------ | ----------------- | diff --git a/models/nlp/llm/llama2-70b/trtllm/README.md b/models/nlp/llm/llama2-70b/trtllm/README.md index 628ee896..080fe85d 100644 --- a/models/nlp/llm/llama2-70b/trtllm/README.md +++ b/models/nlp/llm/llama2-70b/trtllm/README.md @@ -1,6 +1,6 @@ # LlaMa2 70B (TensorRT-LLM) -## Description +## Model Description we develop and release Llama 2, a collection of pretrained and fine-tuned large language models (LLMs) ranging in scale from 7 billion to 70 billion parameters. Our fine-tuned LLMs, called Llama 2-Chat, are optimized for dialogue use cases. @@ -9,9 +9,9 @@ helpfulness and safety, may be a suitable substitute for closed-source models. W approach to fine-tuning and safety improvements of Llama 2-Chat in order to enable the community to build on our work and contribute to the responsible development of LLMs. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash # Install libGL @@ -23,7 +23,7 @@ apt install -y libgl1-mesa-glx bash scripts/set_environment.sh . ``` -### Download +### Prepare Resources - Model: @@ -39,7 +39,7 @@ mkdir -p rouge/ wget --no-check-certificate https://raw.githubusercontent.com/huggingface/evaluate/main/metrics/rouge/rouge.py -P rouge ``` -## Inference +## Model Inference ### FP16 diff --git a/models/nlp/llm/llama2-7b/trtllm/README.md b/models/nlp/llm/llama2-7b/trtllm/README.md index 3be201f1..bde69ca7 100644 --- a/models/nlp/llm/llama2-7b/trtllm/README.md +++ b/models/nlp/llm/llama2-7b/trtllm/README.md @@ -1,6 +1,6 @@ # LlaMa2 7B (TensorRT-LLM) -## Description +## Model Description we develop and release Llama 2, a collection of pretrained and fine-tuned large language models (LLMs) ranging in scale from 7 billion to 70 billion parameters. Our fine-tuned LLMs, called Llama 2-Chat, are optimized for dialogue use cases. @@ -9,9 +9,9 @@ helpfulness and safety, may be a suitable substitute for closed-source models. W approach to fine-tuning and safety improvements of Llama 2-Chat in order to enable the community to build on our work and contribute to the responsible development of LLMs. -## Setup +## Model Preparation -### Install +### Install Dependencies In order to run the model smoothly, you need to get the sdk from [resource center](https://support.iluvatar.com/#/ProductLine?id=2) of Iluvatar CoreX official website. @@ -26,7 +26,7 @@ apt install -y libgl1-mesa-glx bash scripts/set_environment.sh . ``` -### Download +### Prepare Resources - Model: @@ -42,7 +42,7 @@ mkdir -p rouge/ wget --no-check-certificate https://raw.githubusercontent.com/huggingface/evaluate/main/metrics/rouge/rouge.py -P rouge ``` -## Inference +## Model Inference ### FP16 diff --git a/models/nlp/llm/llama2-7b/vllm/README.md b/models/nlp/llm/llama2-7b/vllm/README.md index 44e6db71..71e37bff 100755 --- a/models/nlp/llm/llama2-7b/vllm/README.md +++ b/models/nlp/llm/llama2-7b/vllm/README.md @@ -1,6 +1,6 @@ # Llama2 7B (vLLM) -## Description +## Model Description we develop and release Llama 2, a collection of pretrained and fine-tuned large language models (LLMs) ranging in scale from 7 billion to 70 billion parameters. Our fine-tuned LLMs, called Llama 2-Chat, are optimized for dialogue use cases. @@ -9,9 +9,9 @@ helpfulness and safety, may be a suitable substitute for closed-source models. W approach to fine-tuning and safety improvements of Llama 2-Chat in order to enable the community to build on our work and contribute to the responsible development of LLMs. -## Setup +## Model Preparation -### Install +### Install Dependencies In order to run the model smoothly, you need to get the sdk from [resource center](https://support.iluvatar.com/#/ProductLine?id=2) of Iluvatar CoreX official website. @@ -29,7 +29,7 @@ pip3 install triton pip3 install ixformer ``` -### Download +### Prepare Resources - Model: @@ -39,7 +39,7 @@ mkdir -p data/llama2 ln -s /path/to/llama2-7b ./data/llama2 ``` -## Inference +## Model Inference ```bash python3 offline_inference.py --model ./data/llama2/llama2-7b --max-tokens 256 -tp 1 --temperature 0.0 diff --git a/models/nlp/llm/llama3-70b/vllm/README.md b/models/nlp/llm/llama3-70b/vllm/README.md index a6c4f488..96cc8c50 100644 --- a/models/nlp/llm/llama3-70b/vllm/README.md +++ b/models/nlp/llm/llama3-70b/vllm/README.md @@ -1,6 +1,6 @@ # LlaMa3 70B (vLLM) -## Description +## Model Description This model is the Meta Llama 3 large language model series (LLMs) released by Meta, which is a series of pre-trained and instruction-tuned generative text models, available in 8B and 70B models. The model is 70B in size and is designed for @@ -18,9 +18,9 @@ Llama 3 is a major improvement over Llama 2 and other publicly available models: --Encode the language more efficiently using a larger token vocabulary with 128K tokens -## Setup +## Model Preparation -### Install +### Install Dependencies In order to run the model smoothly, you need to get the sdk from [resource center](https://support.iluvatar.com/#/ProductLine?id=2) of Iluvatar CoreX official website. @@ -33,7 +33,7 @@ yum install -y mesa-libGL apt install -y libgl1-mesa-glx ``` -### Download +### Prepare Resources - Model: @@ -43,7 +43,7 @@ mkdir data ``` -## Inference +## Model Inference ```bash export CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 diff --git a/models/nlp/llm/qwen-7b/vllm/README.md b/models/nlp/llm/qwen-7b/vllm/README.md index 7b2433b6..ca2d482d 100644 --- a/models/nlp/llm/qwen-7b/vllm/README.md +++ b/models/nlp/llm/qwen-7b/vllm/README.md @@ -1,6 +1,6 @@ # Qwen-7B (vLLM) -## Description +## Model Description Large language models (LLMs) have revolutionized the field of artificial intelligence, enabling natural language processing tasks that were previously thought to be exclusive to humans. In this work, we introduce Qwen, the first @@ -15,9 +15,9 @@ Code-Qwen-Chat, as well as mathematics-focused models, Math-Qwen-Chat, which are models demonstrate significantly improved performance in comparison with open-source models, and slightly fall behind the proprietary models. -## Setup +## Model Preparation -### Install +### Install Dependencies In order to run the model smoothly, you need to get the sdk from [resource center](https://support.iluvatar.com/#/ProductLine?id=2) of Iluvatar CoreX official website. @@ -35,7 +35,7 @@ pip3 install triton pip3 install ixformer ``` -### Download +### Prepare Resources - Model: - Model: @@ -45,7 +45,7 @@ mkdir -p data/qwen ln -s /path/to/Qwen-7B ./data/qwen ``` -## Inference +## Model Inference ```bash export CUDA_VISIBLE_DEVICES=0,1 diff --git a/models/nlp/llm/qwen1.5-14b/vllm/README.md b/models/nlp/llm/qwen1.5-14b/vllm/README.md index 07741c3f..a08adf77 100644 --- a/models/nlp/llm/qwen1.5-14b/vllm/README.md +++ b/models/nlp/llm/qwen1.5-14b/vllm/README.md @@ -1,6 +1,6 @@ # Qwen1.5-14B (vLLM) -## Description +## Model Description Qwen1.5 is a language model series including decoder language models of different model sizes. For each size, we release the base language model and the aligned chat model. It is based on the Transformer architecture with SwiGLU activation, @@ -8,9 +8,9 @@ attention QKV bias, group query attention, mixture of sliding window attention a have an improved tokenizer adaptive to multiple natural languages and codes. For the beta version, temporarily we did not include GQA (except for 32B) and the mixture of SWA and full attention. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash # Install libGL @@ -20,7 +20,7 @@ yum install -y mesa-libGL apt install -y libgl1-mesa-glx ``` -### Download +### Prepare Resources - Model: @@ -30,13 +30,13 @@ mkdir data/qwen1.5 ln -s /path/to/Qwen1.5-14B ./data/qwen1.5 ``` -## Inference +## Model Inference ```bash python3 offline_inference.py --model ./data/qwen1.5/Qwen1.5-14B --max-tokens 256 -tp 1 --temperature 0.0 --max-model-len 896 ``` -## Results +## Model Results | Model | QPS | |-------------|-------| diff --git a/models/nlp/llm/qwen1.5-32b/vllm/README.md b/models/nlp/llm/qwen1.5-32b/vllm/README.md index 97fdeca8..634ce9e7 100755 --- a/models/nlp/llm/qwen1.5-32b/vllm/README.md +++ b/models/nlp/llm/qwen1.5-32b/vllm/README.md @@ -1,15 +1,15 @@ # Qwen1.5-32B-Chat (vLLM) -## Description +## Model Description Qwen1.5 is a language model series including decoder language models of different model sizes. For each size, we release the base language model and the aligned chat model. It is based on the Transformer architecture with SwiGLU activation, attention QKV bias, group query attention, mixture of sliding window attention and full attention, etc. Additionally, we have an improved tokenizer adaptive to multiple natural languages and codes. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash # Install libGL @@ -24,7 +24,7 @@ pip3 install triton pip3 install ixformer ``` -### Download +### Prepare Resources - Model: @@ -34,7 +34,7 @@ mkdir -p data/qwen1.5 ln -s /path/to/Qwen1.5-32B ./data/qwen1.5 ``` -## Inference +## Model Inference ```bash export CUDA_VISIBLE_DEVICES=0,1,2,3 diff --git a/models/nlp/llm/qwen1.5-72b/vllm/README.md b/models/nlp/llm/qwen1.5-72b/vllm/README.md index 340eb83d..d1a3108c 100644 --- a/models/nlp/llm/qwen1.5-72b/vllm/README.md +++ b/models/nlp/llm/qwen1.5-72b/vllm/README.md @@ -1,6 +1,6 @@ # Qwen1.5-72B (vLLM) -## Description +## Model Description Qwen1.5 is a language model series including decoder language models of different model sizes. For each size, we release the base language model and the aligned chat model. It is based on the Transformer architecture with SwiGLU activation, @@ -8,9 +8,9 @@ attention QKV bias, group query attention, mixture of sliding window attention a have an improved tokenizer adaptive to multiple natural languages and codes. For the beta version, temporarily we did not include GQA (except for 32B) and the mixture of SWA and full attention. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash # Install libGL @@ -20,7 +20,7 @@ yum install -y mesa-libGL apt install -y libgl1-mesa-glx ``` -### Download +### Prepare Resources - Model: @@ -30,14 +30,14 @@ mkdir data/qwen1.5 ln -s /path/to/Qwen1.5-72B ./data/qwen1.5 ``` -## Inference +## Model Inference ```bash export CUDA_VISIBLE_DEVICES=0,1 python3 offline_inference.py --model ./data/qwen1.5/Qwen1.5-72B --max-tokens 256 -tp 8 --temperature 0.0 --max-model-len 3096 ``` -## Results +## Model Results | Model | QPS | |-------------|-------| diff --git a/models/nlp/llm/qwen1.5-7b/tgi/README.md b/models/nlp/llm/qwen1.5-7b/tgi/README.md index 3ca81f60..198d7438 100644 --- a/models/nlp/llm/qwen1.5-7b/tgi/README.md +++ b/models/nlp/llm/qwen1.5-7b/tgi/README.md @@ -1,6 +1,6 @@ # Qwen1.5-7B (Text Generation Inference) -## Description +## Model Description Qwen1.5 is a language model series including decoder language models of different model sizes. For each size, we release the base language model and the aligned chat model. It is based on the Transformer architecture with SwiGLU activation, @@ -8,9 +8,9 @@ attention QKV bias, group query attention, mixture of sliding window attention a have an improved tokenizer adaptive to multiple natural languages and codes. For the beta version, temporarily we did not include GQA (except for 32B) and the mixture of SWA and full attention. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash # Install libGL @@ -20,7 +20,7 @@ yum install -y mesa-libGL apt install -y libgl1-mesa-glx ``` -### Download +### Prepare Resources - Model: @@ -30,7 +30,7 @@ mkdir -p data/qwen1.5 ln -s /path/to/Qwen1.5-7B ./data/qwen1.5 ``` -## Inference +## Model Inference ### Start webserver @@ -54,7 +54,7 @@ export CUDA_VISIBLE_DEVICES=1 python3 offline_inference.py --model2path ./data/qwen1.5/Qwen1.5-7B ``` -## Results +## Model Results | Model | QPS | |------------|-------| diff --git a/models/nlp/llm/qwen1.5-7b/vllm/README.md b/models/nlp/llm/qwen1.5-7b/vllm/README.md index d991b2d4..e30773cb 100644 --- a/models/nlp/llm/qwen1.5-7b/vllm/README.md +++ b/models/nlp/llm/qwen1.5-7b/vllm/README.md @@ -1,6 +1,6 @@ # Qwen1.5-7B (vLLM) -## Description +## Model Description Qwen1.5 is a language model series including decoder language models of different model sizes. For each size, we release the base language model and the aligned chat model. It is based on the Transformer architecture with SwiGLU activation, @@ -8,9 +8,9 @@ attention QKV bias, group query attention, mixture of sliding window attention a have an improved tokenizer adaptive to multiple natural languages and codes. For the beta version, temporarily we did not include GQA (except for 32B) and the mixture of SWA and full attention. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash # Install libGL @@ -20,7 +20,7 @@ yum install -y mesa-libGL apt install -y libgl1-mesa-glx ``` -### Download +### Prepare Resources - Model: @@ -30,13 +30,13 @@ mkdir -p data/qwen1.5 ln -s /path/to/Qwen1.5-7B ./data/qwen1.5 ``` -## Inference +## Model Inference ```bash python3 offline_inference.py --model ./data/qwen1.5/Qwen1.5-7B --max-tokens 256 -tp 1 --temperature 0.0 --max-model-len 3096 ``` -## Results +## Model Results | Model | QPS | |------------|--------| diff --git a/models/nlp/llm/qwen2-72b/vllm/README.md b/models/nlp/llm/qwen2-72b/vllm/README.md index 08859625..d28c55ab 100755 --- a/models/nlp/llm/qwen2-72b/vllm/README.md +++ b/models/nlp/llm/qwen2-72b/vllm/README.md @@ -1,6 +1,6 @@ # Qwen2-72B-Instruct (vLLM) -## Description +## Model Description Qwen2 is the new series of Qwen large language models. For Qwen2, we release a number of base language models and instruction-tuned language models ranging from 0.5 to 72 billion parameters, including a Mixture-of-Experts model. This @@ -14,9 +14,9 @@ reasoning, etc. Qwen2-72B-Instruct supports a context length of up to 131,072 tokens, enabling the processing of extensive inputs. Please refer to this section for detailed instructions on how to deploy Qwen2 for handling long texts. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash # Install libGL @@ -31,7 +31,7 @@ pip3 install triton pip3 install ixformer ``` -### Download +### Prepare Resources - Model: @@ -41,7 +41,7 @@ mkdir -p data/qwen2 ln -s /path/to/Qwen2-72B ./data/qwen2 ``` -## Inference +## Model Inference ```bash export CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 diff --git a/models/nlp/llm/qwen2-7b/vllm/README.md b/models/nlp/llm/qwen2-7b/vllm/README.md index fb1556b0..419bfd4f 100755 --- a/models/nlp/llm/qwen2-7b/vllm/README.md +++ b/models/nlp/llm/qwen2-7b/vllm/README.md @@ -1,6 +1,6 @@ # Qwen2-7B Instruct (vLLM) -## Description +## Model Description Qwen2 is the new series of Qwen large language models. For Qwen2, we release a number of base language models and instruction-tuned language models ranging from 0.5 to 72 billion parameters, including a Mixture-of-Experts model. This @@ -13,9 +13,9 @@ reasoning, etc. Qwen2-7B-Instruct supports a context length of up to 131,072 tokens, enabling the processing of extensive inputs. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash # Install libGL @@ -30,7 +30,7 @@ pip3 install triton pip3 install ixformer ``` -### Download +### Prepare Resources - Model: https://modelscope.cn/models/Qwen/Qwen2-7B-Instruct @@ -40,7 +40,7 @@ mkdir -p data/qwen2 ln -s /path/to/Qwen2-7B-Instruct ./data/qwen2 ``` -## Inference +## Model Inference ```bash export CUDA_VISIBLE_DEVICES=0 diff --git a/models/nlp/llm/stablelm/vllm/README.md b/models/nlp/llm/stablelm/vllm/README.md index bea23654..0ea5b1a5 100644 --- a/models/nlp/llm/stablelm/vllm/README.md +++ b/models/nlp/llm/stablelm/vllm/README.md @@ -1,6 +1,6 @@ # StableLM2-1.6B (vLLM) -## Description +## Model Description Stable LM 2 1.6B is a decoder-only language model with 1.6 billion parameters. It has been pre-trained on a diverse multilingual and code dataset, comprising 2 trillion tokens, for two epochs. This model is designed for various natural @@ -8,9 +8,9 @@ language processing tasks, including text generation and dialogue systems. Due t and diverse dataset, Stable LM 2 1.6B can effectively capture the nuances of language, including grammar, semantics, and contextual relationships, which enhances the quality and accuracy of the generated text. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash # Install libGL @@ -21,7 +21,7 @@ apt install -y libgl1-mesa-glx pip3 install transformers ``` -### Download +### Prepare Resources - Model: @@ -30,14 +30,14 @@ pip3 install transformers mkdir -p data/stablelm/stablelm-2-1_6b ``` -## Inference +## Model Inference ```bash export CUDA_VISIBLE_DEVICES=0,1 python3 offline_inference.py --model ./data/stablelm/stablelm-2-1_6b --max-tokens 256 -tp 1 --temperature 0.0 ``` -## Results +## Model Results | Model | QPS | |----------|-------| diff --git a/models/nlp/plm/albert/ixrt/README.md b/models/nlp/plm/albert/ixrt/README.md index 2af14b2b..8b032619 100644 --- a/models/nlp/plm/albert/ixrt/README.md +++ b/models/nlp/plm/albert/ixrt/README.md @@ -1,12 +1,12 @@ # ALBERT -## Description +## Model Description Albert (A Lite BERT) is a variant of the BERT (Bidirectional Encoder Representations from Transformers) model that focuses on efficiency and scalability while maintaining strong performance in natural language processing tasks. The AlBERT model introduces parameter reduction techniques and incorporates self-training strategies to enhance its effectiveness. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash apt install -y libnuma-dev @@ -14,7 +14,7 @@ apt install -y libnuma-dev pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -39,7 +39,7 @@ python3 torch2onnx.py --model_path ./general_perf/model_zoo/popular/open_albert/ onnxsim albert-torch-fp32.onnx albert-torch-fp32-sim.onnx ``` -## Inference +## Model Inference ```bash git clone https://gitee.com/deep-spark/iluvatar-corex-ixrt.git --depth=1 @@ -89,7 +89,7 @@ sed -i 's/tensorrt_legacy/tensorrt/' ./backends/ILUVATAR/runtime_backend_iluvata python3 core/perf_engine.py --hardware_type ILUVATAR --task albert-torch-fp32 ``` -## Results +## Model Results | Model | BatchSize | Precision | QPS | Exact Match | F1 Score | | ------ | --------- | --------- | ----- | ----------- | -------- | diff --git a/models/nlp/plm/bert_base_ner/igie/README.md b/models/nlp/plm/bert_base_ner/igie/README.md index 558dce76..b4511ba5 100644 --- a/models/nlp/plm/bert_base_ner/igie/README.md +++ b/models/nlp/plm/bert_base_ner/igie/README.md @@ -1,18 +1,18 @@ # BERT Base NER -## Description +## Model Description BERT is designed to pre-train deep bidirectional representations from unlabeled text by jointly conditioning on both left and right context in all layers. As a result, the pre-trained BERT model can be fine-tuned with just one additional output layer to create state-of-the-art models for a wide range of tasks, such as question answering and language inference, without substantial task-specific architecture modifications. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -34,7 +34,7 @@ cd .. ``` -## Inference +## Model Inference ### INT8 @@ -45,7 +45,7 @@ bash scripts/infer_bert_base_ner_int8_accuracy.sh bash scripts/infer_bert_base_ner_int8_performance.sh ``` -## Results +## Model Results Model |BatchSize |SeqLength |Precision |FPS | F1 Score -----------------|-----------|----------|----------|----------|-------- diff --git a/models/nlp/plm/bert_base_squad/igie/README.md b/models/nlp/plm/bert_base_squad/igie/README.md index 16d9e4e9..3114a1c0 100644 --- a/models/nlp/plm/bert_base_squad/igie/README.md +++ b/models/nlp/plm/bert_base_squad/igie/README.md @@ -1,18 +1,18 @@ # BERT Base SQuAD -## Description +## Model Description BERT is designed to pre-train deep bidirectional representations from unlabeled text by jointly conditioning on both left and right context in all layers. As a result, the pre-trained BERT model can be fine-tuned with just one additional output layer to create state-of-the-art models for a wide range of tasks, such as question answering and language inference, without substantial task-specific architecture modifications. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -24,7 +24,7 @@ Dataset: python3 export.py --output bert-base-uncased-squad-v1.onnx ``` -## Inference +## Model Inference ```bash export DATASETS_DIR=/Path/to/SQuAD/ @@ -39,7 +39,7 @@ bash scripts/infer_bert_base_squad_fp16_accuracy.sh bash scripts/infer_bert_base_squad_fp16_performance.sh ``` -## Results +## Model Results | Model | BatchSize | SeqLength | Precision | FPS | F1 Score | | --------------- | --------- | --------- | --------- | ------ | -------- | diff --git a/models/nlp/plm/bert_base_squad/ixrt/README.md b/models/nlp/plm/bert_base_squad/ixrt/README.md index 240c62bf..3ba12c02 100644 --- a/models/nlp/plm/bert_base_squad/ixrt/README.md +++ b/models/nlp/plm/bert_base_squad/ixrt/README.md @@ -1,10 +1,10 @@ # BERT Base SQuAD -## Description +## Model Description BERT is designed to pre-train deep bidirectional representations from unlabeled text by jointly conditioning on both left and right context in all layers. As a result, the pre-trained BERT model can be fine-tuned with just one additional output layer to create state-of-the-art models for a wide range of tasks, such as question answering and language inference, without substantial task-specific architecture modifications. -## Setup +## Model Preparation ### T4 requirement(tensorrt_version >= 8.6) @@ -39,7 +39,7 @@ cd python bash script/prepare.sh v1_1 ``` -## Inference +## Model Inference ### On Iluvatar @@ -68,7 +68,7 @@ bash script/build_engine.sh --bs 32 --int8 bash script/inference_squad.sh --bs 32 --int8 ``` -## Results +## Model Results | Model | BatchSize | Precision | Latency QPS | exact_match | f1 | | --------------- | --------- | --------- | ----------- | ----------- | ----- | diff --git a/models/nlp/plm/bert_large_squad/igie/README.md b/models/nlp/plm/bert_large_squad/igie/README.md index 7302c3f0..96efec50 100644 --- a/models/nlp/plm/bert_large_squad/igie/README.md +++ b/models/nlp/plm/bert_large_squad/igie/README.md @@ -1,18 +1,18 @@ # BERT Large SQuAD -## Description +## Model Description BERT is designed to pre-train deep bidirectional representations from unlabeled text by jointly conditioning on both left and right context in all layers. As a result, the pre-trained BERT model can be fine-tuned with just one additional output layer to create state-of-the-art models for a wide range of tasks, such as question answering and language inference, without substantial task-specific architecture modifications. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -44,7 +44,7 @@ cd .. ``` -## Inference +## Model Inference ```bash export DATASETS_DIR=/Path/to/SQuAD/ @@ -68,7 +68,7 @@ bash scripts/infer_bert_large_squad_int8_accuracy.sh bash scripts/infer_bert_large_squad_int8_performance.sh ``` -## Results +## Model Results Model |BatchSize |SeqLength |Precision |FPS | F1 Score -----------------|-----------|----------|----------|----------|-------- diff --git a/models/nlp/plm/bert_large_squad/ixrt/README.md b/models/nlp/plm/bert_large_squad/ixrt/README.md index a8bcf5b7..e15a1345 100644 --- a/models/nlp/plm/bert_large_squad/ixrt/README.md +++ b/models/nlp/plm/bert_large_squad/ixrt/README.md @@ -1,10 +1,10 @@ # BERT Large SQuAD -## Description +## Model Description BERT is designed to pre-train deep bidirectional representations from unlabeled text by jointly conditioning on both left and right context in all layers. As a result, the pre-trained BERT model can be fine-tuned with just one additional output layer to create state-of-the-art models for a wide range of tasks, such as question answering and language inference, without substantial task-specific architecture modifications. -## Setup +## Model Preparation Get `bert-large-uncased.zip` from [Google Drive](https://drive.google.com/file/d/1eD8QBkbK6YN-_YXODp3tmpp3cZKlrPTA/view?usp=drive_link) @@ -42,7 +42,7 @@ cd python bash script/prepare.sh v1_1 ``` -## Inference +## Model Inference ### FP16 diff --git a/models/nlp/plm/deberta/ixrt/README.md b/models/nlp/plm/deberta/ixrt/README.md index 3026d51d..b2b5bf0a 100644 --- a/models/nlp/plm/deberta/ixrt/README.md +++ b/models/nlp/plm/deberta/ixrt/README.md @@ -1,6 +1,6 @@ # DeBERTa -## Description +## Model Description DeBERTa (Decoding-enhanced BERT with disentangled attention) is an enhanced version of the BERT (Bidirectional Encoder Representations from Transformers) model. It improves text representation learning by introducing disentangled attention @@ -9,9 +9,9 @@ self-attention matrix into different parts, focusing on different semantic infor capture relationships between texts.By incorporating decoding enhancement techniques, DeBERTa adjusts the decoder during fine-tuning to better suit specific downstream tasks, thereby improving the model’s performance on those tasks. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash export PROJ_ROOT=/PATH/TO/DEEPSPARKINFERENCE @@ -23,7 +23,7 @@ apt install -y libnuma-dev pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: < > @@ -43,7 +43,7 @@ python3 remove_clip_and_cast.py ``` -## Inference +## Model Inference ```bash git clone https://gitee.com/deep-spark/iluvatar-corex-ixrt.git --depth=1 @@ -96,7 +96,7 @@ sed -i 's/tensorrt_legacy/tensorrt/g' backends/ILUVATAR/common.py python3 core/perf_engine.py --hardware_type ILUVATAR --task deberta-torch-fp32 ``` -## Results +## Model Results | Model | BatchSize | Precision | QPS | Exact Match | F1 Score | |---------|-----------|-----------|-------|-------------|----------| diff --git a/models/nlp/plm/roberta/ixrt/README.md b/models/nlp/plm/roberta/ixrt/README.md index 4e45bfa8..246b9079 100644 --- a/models/nlp/plm/roberta/ixrt/README.md +++ b/models/nlp/plm/roberta/ixrt/README.md @@ -1,6 +1,6 @@ # RoBERTa -## Description +## Model Description Language model pretraining has led to significant performance gains but careful comparison between different approaches is challenging. Training is computationally expensive, often done on private datasets of different sizes, and, as we @@ -11,9 +11,9 @@ it. Our best model achieves state-of-the-art results on GLUE, RACE and SQuAD. Th previously overlooked design choices, and raise questions about the source of recently reported improvements. We release our models and code. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash export PROJ_ROOT=/PATH/TO/DEEPSPARKINFERENCE @@ -23,7 +23,7 @@ cd ${MODEL_PATH} pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -48,7 +48,7 @@ python3 export_onnx.py --model_path open_roberta/roberta-base-squad.pt --output_ onnxsim open_roberta/roberta-torch-fp32.onnx open_roberta/roberta-torch-fp32_sim.onnx ``` -## Inference +## Model Inference ```bash git clone https://gitee.com/deep-spark/iluvatar-corex-ixrt.git --depth=1 @@ -103,7 +103,7 @@ wget -O workloads/roberta-torch-fp32.json https://raw.githubusercontent.com/byte python3 core/perf_engine.py --hardware_type ILUVATAR --task roberta-torch-fp32 ``` -## Results +## Model Results | Model | BatchSize | Precision | FPS | F1 | Exact Match | |---------|-----------|-----------|--------|----------|-------------| diff --git a/models/nlp/plm/roformer/ixrt/README.md b/models/nlp/plm/roformer/ixrt/README.md index 6d125955..20d3938a 100644 --- a/models/nlp/plm/roformer/ixrt/README.md +++ b/models/nlp/plm/roformer/ixrt/README.md @@ -1,6 +1,6 @@ # RoFormer -## Description +## Model Description Position encoding recently has shown effective in the transformer architecture. It enables valuable supervision for dependency modeling between elements at different positions of the sequence. In this paper, we first investigate various @@ -13,9 +13,9 @@ the capability of equipping the linear self-attention with relative position enc transformer with rotary position embedding, also called RoFormer, on various long text classification benchmark datasets. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash apt install -y libnuma-dev @@ -24,7 +24,7 @@ pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -56,7 +56,7 @@ onnxsim ./data/open_roformer/roformer-frozen_org.onnx ./data/open_roformer/rofor python3 deploy.py --model_path ./data/open_roformer/roformer-frozen.onnx --output_path ./data/open_roformer/roformer-frozen.onnx ``` -## Inference +## Model Inference ```bash git clone https://gitee.com/deep-spark/iluvatar-corex-ixrt.git --depth=1 @@ -110,7 +110,7 @@ sed -i 's/segment:0/segment0/g; s/token:0/token0/g' model_zoo/roformer-tf-fp32.j python3 core/perf_engine.py --hardware_type ILUVATAR --task roformer-tf-fp32 ``` -## Results +## Model Results | Model | BatchSize | Precision | FPS | ACC | |----------|-----------|-----------|---------|---------| diff --git a/models/nlp/plm/videobert/ixrt/README.md b/models/nlp/plm/videobert/ixrt/README.md index cb368384..3a00c0c7 100644 --- a/models/nlp/plm/videobert/ixrt/README.md +++ b/models/nlp/plm/videobert/ixrt/README.md @@ -1,14 +1,14 @@ # VideoBERT -## Description +## Model Description VideoBERT is a model designed for video understanding tasks, extending the capabilities of BERT (Bidirectional Encoder Representations from Transformers) to video data. It enhances video representation learning by integrating both visual and textual information into a unified framework. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash apt install -y libnuma-dev @@ -16,7 +16,7 @@ apt install -y libnuma-dev pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -31,7 +31,7 @@ cd ${MODEL_PATH} bash ./scripts/prepare_model_and_dataset.sh ``` -## Inference +## Model Inference ```bash git clone https://gitee.com/deep-spark/iluvatar-corex-ixrt.git --depth=1 @@ -72,7 +72,7 @@ wget -O workloads/videobert-onnx-fp32.json https://raw.githubusercontent.com/byt python3 core/perf_engine.py --hardware_type ILUVATAR --task videobert-onnx-fp32 ``` -## Results +## Model Results | Model | BatchSize | Precision | QPS | Top-1 ACC | |-----------|-----------|-----------|-------|-----------| diff --git a/models/others/recommendation/wide_and_deep/ixrt/README.md b/models/others/recommendation/wide_and_deep/ixrt/README.md index c6653cab..2482b5ed 100644 --- a/models/others/recommendation/wide_and_deep/ixrt/README.md +++ b/models/others/recommendation/wide_and_deep/ixrt/README.md @@ -1,12 +1,12 @@ # Wide&Deep -## Description +## Model Description Generalized linear models with nonlinear feature transformations are widely used for large-scale regression and classification problems with sparse inputs. Memorization of feature interactions through a wide set of cross-product feature transformations are effective and interpretable, while generalization requires more feature engineering effort. With less feature engineering, deep neural networks can generalize better to unseen feature combinations through low-dimensional dense embeddings learned for the sparse features. However, deep neural networks with embeddings can over-generalize and recommend less relevant items when the user-item interactions are sparse and high-rank. In this paper, we present Wide & Deep learning---jointly trained wide linear models and deep neural networks---to combine the benefits of memorization and generalization for recommender systems. We productionized and evaluated the system on Google Play, a commercial mobile app store with over one billion active users and over one million apps. Online experiment results show that Wide & Deep significantly increased app acquisitions compared with wide-only and deep-only models. We have also open-sourced our implementation in TensorFlow. -## Setup +## Model Preparation -### Install +### Install Dependencies ```bash apt install -y libnuma-dev @@ -14,7 +14,7 @@ apt install -y libnuma-dev pip3 install -r requirements.txt ``` -### Download +### Prepare Resources Pretrained model: @@ -35,7 +35,7 @@ python3 deploy.py --model_path open_wide_deep_saved_model/widedeep_sim.onnx --ou python3 change2dynamic.py --model_path open_wide_deep_saved_model/widedeep_sim.onnx --output_path open_wide_deep_saved_model/widedeep_sim.onnx ``` -## Inference +## Model Inference ```bash export ORIGIN_ONNX_NAME=./open_wide_deep_saved_model/widedeep_sim @@ -80,7 +80,7 @@ wget -O workloads/widedeep-tf-fp32.json https://raw.githubusercontent.com/byteda python3 core/perf_engine.py --hardware_type ILUVATAR --task widedeep-tf-fp32 ``` -## Results +## Model Results | Model | BatchSize | Precision | FPS | ACC | | --------- | --------- | --------- | -------- | ------- | -- Gitee From c3799eafed93f5eceac5d452a30edd8ce0a1752f Mon Sep 17 00:00:00 2001 From: "mingjiang.li" Date: Wed, 5 Mar 2025 13:23:13 +0800 Subject: [PATCH 3/3] format model readme base on template --- .../conformer/igie/README.md | 14 ++--- .../conformer/ixrt/README.md | 37 ++++++------- .../transformer_asr/ixrt/README.md | 14 ++--- .../cv/classification/alexnet/igie/README.md | 14 ++--- .../cv/classification/alexnet/ixrt/README.md | 14 ++--- models/cv/classification/clip/igie/README.md | 20 +++---- .../conformer_base/igie/README.md | 20 +++---- .../convnext_base/igie/README.md | 14 ++--- .../convnext_base/ixrt/README.md | 22 +++----- .../convnext_base/ixrt/requirements.txt | 7 +++ .../classification/convnext_s/igie/README.md | 16 +++--- .../convnext_small/igie/README.md | 14 ++--- .../convnext_small/ixrt/README.md | 14 ++--- .../cspdarknet53/igie/README.md | 17 +++--- .../cspdarknet53/ixrt/README.md | 16 +++--- .../classification/cspresnet50/igie/README.md | 20 +++---- .../classification/cspresnet50/ixrt/README.md | 19 ++++--- .../classification/deit_tiny/igie/README.md | 17 +++--- .../classification/deit_tiny/ixrt/README.md | 24 ++++----- .../deit_tiny/ixrt/requirements.txt | 7 +++ .../classification/densenet121/igie/README.md | 20 +++---- .../classification/densenet121/ixrt/README.md | 10 ++-- .../classification/densenet161/igie/README.md | 14 ++--- .../classification/densenet161/ixrt/README.md | 12 ++--- .../classification/densenet169/igie/README.md | 14 ++--- .../classification/densenet169/ixrt/README.md | 18 +++---- .../classification/densenet201/igie/README.md | 14 ++--- .../classification/densenet201/ixrt/README.md | 22 +++----- .../densenet201/ixrt/requirements.txt | 7 +++ .../efficientnet_b0/igie/README.md | 20 +++---- .../efficientnet_b0/ixrt/README.md | 16 +++--- .../efficientnet_b1/igie/README.md | 20 +++---- .../efficientnet_b1/ixrt/README.md | 18 +++---- .../efficientnet_b2/igie/README.md | 16 +++--- .../efficientnet_b2/ixrt/README.md | 14 ++--- .../efficientnet_b3/igie/README.md | 14 ++--- .../efficientnet_b3/ixrt/README.md | 19 +++---- .../efficientnet_b3/ixrt/requirements.txt | 4 ++ .../efficientnet_b4/igie/README.md | 14 ++--- .../efficientnet_v2/igie/README.md | 14 ++--- .../efficientnet_v2/ixrt/README.md | 26 ++++----- .../efficientnet_v2_s/igie/README.md | 14 ++--- .../efficientnet_v2_s/ixrt/README.md | 14 ++--- .../efficientnetv2_rw_t/igie/README.md | 20 +++---- .../efficientnetv2_rw_t/ixrt/README.md | 29 ++++------ .../efficientnetv2_rw_t/ixrt/requirements.txt | 8 +++ .../classification/googlenet/igie/README.md | 22 ++++---- .../classification/googlenet/ixrt/README.md | 22 ++++---- .../classification/hrnet_w18/igie/README.md | 17 +++--- .../classification/hrnet_w18/ixrt/README.md | 12 ++--- .../inception_resnet_v2/ixrt/README.md | 14 ++--- .../inception_v3/igie/README.md | 22 ++++---- .../inception_v3/ixrt/README.md | 22 ++++---- .../mlp_mixer_base/igie/README.md | 16 +++--- .../classification/mnasnet0_5/igie/README.md | 14 ++--- .../classification/mnasnet0_75/igie/README.md | 14 ++--- .../mobilenet_v2/igie/README.md | 22 ++++---- .../mobilenet_v2/ixrt/README.md | 19 ++++--- .../mobilenet_v3/igie/README.md | 20 +++---- .../mobilenet_v3/ixrt/README.md | 20 +++---- .../mobilenet_v3_large/igie/README.md | 20 +++---- .../classification/mvitv2_base/igie/README.md | 16 +++--- .../regnet_x_16gf/igie/README.md | 20 +++---- .../regnet_x_1_6gf/igie/README.md | 20 +++---- .../regnet_y_1_6gf/igie/README.md | 14 ++--- .../cv/classification/repvgg/igie/README.md | 16 +++--- .../cv/classification/repvgg/ixrt/README.md | 10 ++-- .../classification/res2net50/igie/README.md | 22 ++++---- .../classification/res2net50/ixrt/README.md | 22 ++++---- .../classification/resnest50/igie/README.md | 22 ++++---- .../classification/resnet101/igie/README.md | 22 ++++---- .../classification/resnet101/ixrt/README.md | 18 +++---- .../classification/resnet152/igie/README.md | 22 ++++---- .../cv/classification/resnet18/igie/README.md | 22 ++++---- .../cv/classification/resnet18/ixrt/README.md | 22 ++++---- .../cv/classification/resnet34/ixrt/README.md | 18 +++---- .../cv/classification/resnet50/igie/README.md | 22 ++++---- .../cv/classification/resnet50/ixrt/README.md | 16 +++--- .../classification/resnetv1d50/igie/README.md | 16 +++--- .../classification/resnetv1d50/ixrt/README.md | 10 ++-- .../resnext101_32x8d/igie/README.md | 14 ++--- .../resnext101_64x4d/igie/README.md | 14 ++--- .../resnext50_32x4d/igie/README.md | 20 +++---- .../resnext50_32x4d/ixrt/README.md | 14 ++--- .../classification/seresnet50/igie/README.md | 17 +++--- .../shufflenet_v1/ixrt/README.md | 20 +++---- .../shufflenetv2_x0_5/igie/README.md | 20 +++---- .../shufflenetv2_x1_0/igie/README.md | 14 ++--- .../shufflenetv2_x1_5/igie/README.md | 14 ++--- .../shufflenetv2_x2_0/igie/README.md | 14 ++--- .../squeezenet_v1_0/igie/README.md | 20 +++---- .../squeezenet_v1_0/ixrt/README.md | 22 ++++---- .../squeezenet_v1_1/ixrt/README.md | 14 ++--- .../cv/classification/svt_base/igie/README.md | 16 +++--- .../swin_transformer/igie/README.md | 20 +++---- .../swin_transformer_large/ixrt/README.md | 25 +++++---- models/cv/classification/vgg11/igie/README.md | 20 +++---- models/cv/classification/vgg16/igie/README.md | 22 ++++---- models/cv/classification/vgg16/ixrt/README.md | 22 ++++---- .../wide_resnet101/igie/README.md | 14 ++--- .../wide_resnet50/igie/README.md | 16 +++--- .../wide_resnet50/ixrt/README.md | 14 ++--- .../face_recognition/facenet/ixrt/README.md | 27 +++++----- .../mask_rcnn/ixrt/README.md | 31 +++++------ .../solov1/ixrt/README.md | 30 ++++++----- .../deepsort/igie/README.md | 22 ++++---- .../fastreid/igie/README.md | 20 +++---- .../repnet/igie/README.md | 22 ++++---- .../cv/object_detection/atss/igie/README.md | 31 ++++++----- .../object_detection/centernet/igie/README.md | 22 ++++---- .../object_detection/centernet/ixrt/README.md | 16 +++--- .../cv/object_detection/detr/ixrt/README.md | 20 +++---- .../cv/object_detection/fcos/igie/README.md | 30 +++++------ .../cv/object_detection/fcos/ixrt/README.md | 24 ++++----- .../object_detection/foveabox/igie/README.md | 22 ++++---- .../object_detection/foveabox/ixrt/README.md | 31 +++++------ .../foveabox/ixrt/requirements.txt | 8 +++ .../cv/object_detection/fsaf/igie/README.md | 30 +++++------ .../cv/object_detection/fsaf/ixrt/README.md | 30 +++++------ .../cv/object_detection/hrnet/igie/README.md | 22 ++++---- .../cv/object_detection/hrnet/ixrt/README.md | 22 ++++---- models/cv/object_detection/paa/igie/README.md | 16 +++--- .../retinaface/igie/README.md | 22 ++++---- .../retinaface/ixrt/README.md | 31 +++++------ .../object_detection/retinanet/igie/README.md | 22 ++++---- .../cv/object_detection/rtmdet/igie/README.md | 31 +++++------ .../cv/object_detection/sabl/igie/README.md | 30 +++++------ .../object_detection/yolov10/igie/README.md | 16 +++--- .../object_detection/yolov11/igie/README.md | 10 ++-- .../cv/object_detection/yolov3/igie/README.md | 22 ++++---- .../cv/object_detection/yolov3/ixrt/README.md | 28 +++++----- .../cv/object_detection/yolov4/igie/README.md | 28 +++++----- .../cv/object_detection/yolov4/ixrt/README.md | 20 +++---- .../cv/object_detection/yolov5/igie/README.md | 22 ++++---- .../cv/object_detection/yolov5/ixrt/README.md | 28 +++++----- .../object_detection/yolov5s/ixrt/README.md | 22 ++++---- .../cv/object_detection/yolov6/igie/README.md | 22 ++++---- .../cv/object_detection/yolov6/ixrt/README.md | 18 +++---- .../cv/object_detection/yolov7/igie/README.md | 24 ++++----- .../cv/object_detection/yolov7/ixrt/README.md | 32 ++++++----- .../cv/object_detection/yolov8/igie/README.md | 22 ++++---- .../cv/object_detection/yolov8/ixrt/README.md | 16 +++--- .../cv/object_detection/yolov9/igie/README.md | 12 ++--- .../cv/object_detection/yolox/igie/README.md | 28 +++++----- .../cv/object_detection/yolox/ixrt/README.md | 24 ++++----- models/cv/ocr/kie_layoutxlm/igie/README.md | 21 ++++---- models/cv/ocr/svtr/igie/README.md | 44 +++++++++------ .../pose_estimation/hrnetpose/igie/README.md | 30 +++++------ .../lightweight_openpose/ixrt/README.md | 14 ++--- .../cv/pose_estimation/rtmpose/igie/README.md | 31 ++++++----- .../cv/pose_estimation/rtmpose/ixrt/README.md | 14 ++--- .../stable-diffusion/README.md | 20 +++---- .../chameleon_7b/vllm/README.md | 18 +++---- .../clip/ixformer/README.md | 22 ++++---- .../fuyu_8b/vllm/README.md | 18 +++---- .../intern_vl/vllm/README.md | 20 +++---- .../llava/vllm/README.md | 19 ++++--- .../llava_next_video_7b/vllm/README.md | 18 +++---- .../minicpm_v_2/vllm/README.md | 21 ++++---- models/nlp/llm/baichuan2-7b/vllm/README.md | 28 +++++----- models/nlp/llm/chatglm3-6b-32k/vllm/README.md | 26 ++++----- models/nlp/llm/chatglm3-6b/vllm/README.md | 40 ++++++-------- .../vllm/README.md | 28 +++++----- .../vllm/README.md | 28 +++++----- .../vllm/README.md | 28 +++++----- .../vllm/README.md | 28 +++++----- .../vllm/README.md | 28 +++++----- .../vllm/README.md | 28 +++++----- models/nlp/llm/llama2-13b/trtllm/README.md | 27 +++++----- models/nlp/llm/llama2-70b/trtllm/README.md | 24 ++++----- models/nlp/llm/llama2-7b/trtllm/README.md | 30 +++++------ models/nlp/llm/llama2-7b/vllm/README.md | 20 +++---- models/nlp/llm/llama3-70b/vllm/README.md | 36 +++++-------- models/nlp/llm/qwen-7b/vllm/README.md | 38 ++++++------- models/nlp/llm/qwen1.5-14b/vllm/README.md | 20 +++---- models/nlp/llm/qwen1.5-32b/vllm/README.md | 20 +++---- models/nlp/llm/qwen1.5-72b/vllm/README.md | 20 +++---- models/nlp/llm/qwen1.5-7b/tgi/README.md | 20 +++---- models/nlp/llm/qwen1.5-7b/vllm/README.md | 20 +++---- models/nlp/llm/qwen2-72b/vllm/README.md | 20 +++---- models/nlp/llm/qwen2-7b/vllm/README.md | 20 +++---- models/nlp/llm/stablelm/vllm/README.md | 18 +++---- models/nlp/plm/albert/ixrt/README.md | 19 ++++--- models/nlp/plm/bert_base_ner/igie/README.md | 25 +++++---- models/nlp/plm/bert_base_squad/igie/README.md | 14 ++--- models/nlp/plm/bert_base_squad/ixrt/README.md | 36 +++++++------ .../nlp/plm/bert_large_squad/igie/README.md | 26 +++++---- .../nlp/plm/bert_large_squad/ixrt/README.md | 53 ++++++++++--------- models/nlp/plm/deberta/ixrt/README.md | 22 ++++---- models/nlp/plm/roberta/ixrt/README.md | 14 ++--- models/nlp/plm/roformer/ixrt/README.md | 22 ++++---- models/nlp/plm/videobert/ixrt/README.md | 18 +++---- .../wide_and_deep/ixrt/README.md | 20 +++---- 193 files changed, 1969 insertions(+), 1974 deletions(-) create mode 100644 models/cv/classification/convnext_base/ixrt/requirements.txt create mode 100644 models/cv/classification/deit_tiny/ixrt/requirements.txt create mode 100644 models/cv/classification/densenet201/ixrt/requirements.txt create mode 100644 models/cv/classification/efficientnet_b3/ixrt/requirements.txt create mode 100644 models/cv/classification/efficientnetv2_rw_t/ixrt/requirements.txt create mode 100644 models/cv/object_detection/foveabox/ixrt/requirements.txt diff --git a/models/audio/speech_recognition/conformer/igie/README.md b/models/audio/speech_recognition/conformer/igie/README.md index 54255769..4db0cbd6 100644 --- a/models/audio/speech_recognition/conformer/igie/README.md +++ b/models/audio/speech_recognition/conformer/igie/README.md @@ -1,4 +1,4 @@ -# Conformer +# Conformer (IGIE) ## Model Description @@ -9,6 +9,12 @@ Conformer applies convolution to the Encoder layer of Transformer, enhancing the ## Model Preparation +### Prepare Resources + +Pretrained model: + +Dataset: to download the Aishell dataset. + ### Install Dependencies ```bash @@ -17,12 +23,6 @@ cd ctc_decoder/swig && bash setup.sh cd ../../ ``` -### Prepare Resources - -Pretrained model: - -Dataset: to download the Aishell dataset. - ### Model Conversion ```bash diff --git a/models/audio/speech_recognition/conformer/ixrt/README.md b/models/audio/speech_recognition/conformer/ixrt/README.md index bea43b9b..16ee0079 100644 --- a/models/audio/speech_recognition/conformer/ixrt/README.md +++ b/models/audio/speech_recognition/conformer/ixrt/README.md @@ -1,4 +1,4 @@ -# Conformer +# Conformer (IxRT) ## Model Description @@ -6,40 +6,35 @@ Conformer is a speech recognition model proposed by Google in 2020. It combines ## Model Preparation -### Install Dependencies - -```bash -# Install libGL -## CentOS -yum install -y mesa-libGL -## Ubuntu -apt install -y libgl1-mesa-glx - -pip3 install -r requirements.txt -``` - ### Prepare Resources Pretrained model: Dataset: to download the Aishell dataset. -Download and put model in conformer_checkpoints. - ```bash +# Download and put model in conformer_checkpoints ln -s /home/deepspark/datasets/INFER/conformer/20210601_u2++_conformer_exp_aishell ./conformer_checkpoints -``` - -### Prepare Data -```bash -# Accuracy +# Prepare AISHELL Data DATA_DIR=/PATH/to/aishell_test_data TOOL_DIR="$(pwd)/tools" bash scripts/aishell_data_prepare.sh ${DATA_DIR} ${TOOL_DIR} ``` -## Model Conversion And Inference +### Install Dependencies + +```bash +# Install libGL +## CentOS +yum install -y mesa-libGL +## Ubuntu +apt install -y libgl1-mesa-glx + +pip3 install -r requirements.txt +``` + +## Model Inference ### FP16 diff --git a/models/audio/speech_recognition/transformer_asr/ixrt/README.md b/models/audio/speech_recognition/transformer_asr/ixrt/README.md index f7e9f24b..a759fdcd 100644 --- a/models/audio/speech_recognition/transformer_asr/ixrt/README.md +++ b/models/audio/speech_recognition/transformer_asr/ixrt/README.md @@ -1,4 +1,4 @@ -# Transformer ASR（BeamSearch） +# Transformer ASR (IxRT) ## Model Description @@ -8,12 +8,6 @@ must be included in the final translation with a dictionary lookup. ## Model Preparation -### Install Dependencies - -```bash -pip3 install -r requirements.txt -``` - ### Prepare Resources Pretrained model: @@ -51,6 +45,12 @@ ln -s /PATH/to/data_aishell /home/data/speechbrain/aishell/ cp results/transformer/8886/*.csv /home/data/speechbrain/aishell/csv_data ``` +### Install Dependencies + +```bash +pip3 install -r requirements.txt +``` + ## Model Inference ### Build faster kernels diff --git a/models/cv/classification/alexnet/igie/README.md b/models/cv/classification/alexnet/igie/README.md index 686248aa..f6662bcb 100644 --- a/models/cv/classification/alexnet/igie/README.md +++ b/models/cv/classification/alexnet/igie/README.md @@ -1,4 +1,4 @@ -# AlexNet +# AlexNet （IGIE) ## Model Description @@ -10,18 +10,18 @@ non-linearity, allowing the model to learn complex features from input images. ## Model Preparation -### Install Dependencies - -```bash -pip3 install -r requirements.txt -``` - ### Prepare Resources Pretrained model: Dataset: to download the validation dataset. +### Install Dependencies + +```bash +pip3 install -r requirements.txt +``` + ### Model Conversion ```bash diff --git a/models/cv/classification/alexnet/ixrt/README.md b/models/cv/classification/alexnet/ixrt/README.md index 8284d2ab..daae7a09 100644 --- a/models/cv/classification/alexnet/ixrt/README.md +++ b/models/cv/classification/alexnet/ixrt/README.md @@ -1,4 +1,4 @@ -# AlexNet +# AlexNet (IxRT) ## Model Description @@ -7,6 +7,12 @@ layers as the basic building blocks. ## Model Preparation +### Prepare Resources + +Pretrained model: + +Dataset: to download the validation dataset. + ### Install Dependencies ```bash @@ -19,12 +25,6 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Prepare Resources - -Pretrained model: - -Dataset: to download the validation dataset. - ### Model Conversion ```bash diff --git a/models/cv/classification/clip/igie/README.md b/models/cv/classification/clip/igie/README.md index 57cc7042..0e41a1e2 100644 --- a/models/cv/classification/clip/igie/README.md +++ b/models/cv/classification/clip/igie/README.md @@ -1,4 +1,4 @@ -# CLIP +# CLIP (IGIE) ## Model Description @@ -6,12 +6,6 @@ CLIP (Contrastive Language-Image Pre-Training) is a neural network trained on a ## Model Preparation -### Install Dependencies - -```bash -pip3 install -r requirements.txt -``` - ### Prepare Resources Pretrained model: @@ -23,6 +17,12 @@ git clone https://huggingface.co/openai/clip-vit-base-patch32 clip-vit-base-patc Dataset: to download the validation dataset. +### Install Dependencies + +```bash +pip3 install -r requirements.txt +``` + ### Model Conversion ```bash @@ -49,6 +49,6 @@ bash scripts/infer_clip_fp16_performance.sh ## Model Results -Model |BatchSize |Precision |FPS |Top-1(%) |Top-5(%) -------|-----------|----------|----------|----------|-------- -CLIP | 32 | FP16 | 496.91 | 59.68 | 86.16 +| Model | BatchSize | Precision | FPS | Top-1(%) | Top-5(%) | +|-------|-----------|-----------|--------|----------|----------| +| CLIP | 32 | FP16 | 496.91 | 59.68 | 86.16 | diff --git a/models/cv/classification/conformer_base/igie/README.md b/models/cv/classification/conformer_base/igie/README.md index a3b1f5bd..cf5c3e27 100644 --- a/models/cv/classification/conformer_base/igie/README.md +++ b/models/cv/classification/conformer_base/igie/README.md @@ -1,4 +1,4 @@ -# Conformer Base +# Conformer Base (IGIE) ## Model Description @@ -6,18 +6,18 @@ Conformer is a novel network architecture that addresses the limitations of conv ## Model Preparation -### Install Dependencies - -```bash -pip3 install -r requirements.txt -``` - ### Prepare Resources Pretrained model: Dataset: to download the validation dataset. +### Install Dependencies + +```bash +pip3 install -r requirements.txt +``` + ### Model Conversion ```bash @@ -45,9 +45,9 @@ bash scripts/infer_conformer_base_fp16_performance.sh ## Model Results -Model |BatchSize |Precision |FPS |Top-1(%) |Top-5(%) -----------|-----------|----------|----------|----------|-------- -Conformer Base | 32 | FP16 | 428.73 | 83.83 | 96.59 +| Model | BatchSize | Precision | FPS | Top-1(%) | Top-5(%) | +|----------------|-----------|-----------|--------|----------|----------| +| Conformer Base | 32 | FP16 | 428.73 | 83.83 | 96.59 | ## References diff --git a/models/cv/classification/convnext_base/igie/README.md b/models/cv/classification/convnext_base/igie/README.md index b0b6812a..4d4676cd 100644 --- a/models/cv/classification/convnext_base/igie/README.md +++ b/models/cv/classification/convnext_base/igie/README.md @@ -1,4 +1,4 @@ -# ConvNext Base +# ConvNext Base (IGIE) ## Model Description @@ -6,18 +6,18 @@ The ConvNeXt Base model represents a significant stride in the evolution of conv ## Model Preparation -### Install Dependencies - -```bash -pip3 install -r requirements.txt -``` - ### Prepare Resources Pretrained model: Dataset: to download the validation dataset. +### Install Dependencies + +```bash +pip3 install -r requirements.txt +``` + ### Model Conversion ```bash diff --git a/models/cv/classification/convnext_base/ixrt/README.md b/models/cv/classification/convnext_base/ixrt/README.md index 4dc0adab..fbb66069 100644 --- a/models/cv/classification/convnext_base/ixrt/README.md +++ b/models/cv/classification/convnext_base/ixrt/README.md @@ -1,4 +1,4 @@ -# ConvNeXt Base +# ConvNeXt Base (IxRT) ## Model Description @@ -6,6 +6,12 @@ The ConvNeXt Base model represents a significant stride in the evolution of conv ## Model Preparation +### Prepare Resources + +Pretrained model: + +Dataset: to download the validation dataset. + ### Install Dependencies ```bash @@ -15,21 +21,9 @@ yum install -y mesa-libGL ## Ubuntu apt install -y libgl1-mesa-glx -pip3 install tqdm -pip3 install onnx -pip3 install onnxsim -pip3 install tabulate -pip3 install ppq -pip3 install tqdm -pip3 install cuda-python +pip3 install -r requirements.txt ``` -### Prepare Resources - -Pretrained model: - -Dataset: to download the validation dataset. - ### Model Conversion ```bash diff --git a/models/cv/classification/convnext_base/ixrt/requirements.txt b/models/cv/classification/convnext_base/ixrt/requirements.txt new file mode 100644 index 00000000..520130b7 --- /dev/null +++ b/models/cv/classification/convnext_base/ixrt/requirements.txt @@ -0,0 +1,7 @@ +tqdm +onnx +onnxsim +tabulate +ppq +tqdm +cuda-python \ No newline at end of file diff --git a/models/cv/classification/convnext_s/igie/README.md b/models/cv/classification/convnext_s/igie/README.md index 8bedb4b1..3a4a0b36 100644 --- a/models/cv/classification/convnext_s/igie/README.md +++ b/models/cv/classification/convnext_s/igie/README.md @@ -1,4 +1,4 @@ -# ConvNext-S (OpenMMLab) +# ConvNext-S (IGIE) ## Model Description @@ -6,6 +6,12 @@ ConvNeXt-S is a small-sized model in the ConvNeXt family, designed to balance pe ## Model Preparation +### Prepare Resources + +Pretrained model: + +Dataset: to download the validation dataset. + ### Install Dependencies ```bash @@ -18,12 +24,6 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Prepare Resources - -Pretrained model: - -Dataset: to download the validation dataset. - ### Model Conversion ```bash @@ -61,4 +61,4 @@ bash scripts/infer_convnext_s_fp16_performance.sh ## References -ConvNext-S: +- [ConvNext-S](https://github.com/open-mmlab/mmpretrain) diff --git a/models/cv/classification/convnext_small/igie/README.md b/models/cv/classification/convnext_small/igie/README.md index 44713c53..fc8a0f5e 100644 --- a/models/cv/classification/convnext_small/igie/README.md +++ b/models/cv/classification/convnext_small/igie/README.md @@ -1,4 +1,4 @@ -# ConvNeXt Small +# ConvNeXt Small (IGIE) ## Model Description @@ -6,18 +6,18 @@ The ConvNeXt Small model represents a significant stride in the evolution of con ## Model Preparation -### Install Dependencies - -```bash -pip3 install -r requirements.txt -``` - ### Prepare Resources Pretrained model: Dataset: to download the validation dataset. +### Install Dependencies + +```bash +pip3 install -r requirements.txt +``` + ### Model Conversion ```bash diff --git a/models/cv/classification/convnext_small/ixrt/README.md b/models/cv/classification/convnext_small/ixrt/README.md index ff84232f..b47d5f12 100644 --- a/models/cv/classification/convnext_small/ixrt/README.md +++ b/models/cv/classification/convnext_small/ixrt/README.md @@ -1,4 +1,4 @@ -# ConvNeXt Small +# ConvNeXt Small (IxRT) ## Model Description @@ -6,6 +6,12 @@ The ConvNeXt Small model represents a significant stride in the evolution of con ## Model Preparation +### Prepare Resources + +Pretrained model: + +Dataset: to download the validation dataset. + ### Install Dependencies ```bash @@ -18,12 +24,6 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Prepare Resources - -Pretrained model: - -Dataset: to download the validation dataset. - ### Model Conversion ```bash diff --git a/models/cv/classification/cspdarknet53/igie/README.md b/models/cv/classification/cspdarknet53/igie/README.md index f409b0a0..0cdd89a2 100644 --- a/models/cv/classification/cspdarknet53/igie/README.md +++ b/models/cv/classification/cspdarknet53/igie/README.md @@ -1,4 +1,4 @@ -# CSPDarkNet53 +# CSPDarkNet53 (IGIE) ## Model Description @@ -6,6 +6,12 @@ CSPDarkNet53 is an enhanced convolutional neural network architecture that reduc ## Model Preparation +### Prepare Resources + +Pretrained model: + +Dataset: to download the validation dataset. + ### Install Dependencies ```bash @@ -18,12 +24,6 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Prepare Resources - -Pretrained model: - -Dataset: to download the validation dataset. - ### Model Conversion ```bash @@ -38,7 +38,6 @@ python3 export.py --cfg mmpretrain/configs/cspnet/cspdarknet50_8xb32_in1k.py --w # Use onnxsim optimize onnx model onnxsim cspdarknet53.onnx cspdarknet53_opt.onnx - ``` ## Model Inference @@ -64,4 +63,4 @@ bash scripts/infer_cspdarknet53_fp16_performance.sh ## References -CSPDarkNet53: +- [mmpretrain](https://github.com/open-mmlab/mmpretrain) diff --git a/models/cv/classification/cspdarknet53/ixrt/README.md b/models/cv/classification/cspdarknet53/ixrt/README.md index b0dbdd06..90652858 100644 --- a/models/cv/classification/cspdarknet53/ixrt/README.md +++ b/models/cv/classification/cspdarknet53/ixrt/README.md @@ -1,4 +1,4 @@ -# CSPDarkNet53 +# CSPDarkNet53 (IxRT) ## Model Description @@ -6,6 +6,12 @@ CSPDarkNet53 is an enhanced convolutional neural network architecture that reduc ## Model Preparation +### Prepare Resources + +Pretrained model: + +Dataset: to download the validation dataset. + ### Install Dependencies ```bash @@ -18,12 +24,6 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Prepare Resources - -Pretrained model: - -Dataset: to download the validation dataset. - ### Model Conversion ```bash @@ -77,4 +77,4 @@ bash scripts/infer_cspdarknet53_int8_performance.sh ## References -CSPDarkNet53: +- [mmpretrain](https://github.com/open-mmlab/mmpretrain) diff --git a/models/cv/classification/cspresnet50/igie/README.md b/models/cv/classification/cspresnet50/igie/README.md index 3d5c62f2..8abb227c 100644 --- a/models/cv/classification/cspresnet50/igie/README.md +++ b/models/cv/classification/cspresnet50/igie/README.md @@ -1,11 +1,19 @@ -# CSPResNet50 +# CSPResNet50 (IGIE) ## Model Description -CSPResNet50 combines the strengths of ResNet50 and CSPNet (Cross-Stage Partial Network) to create a more efficient and high-performing architecture. By splitting and fusing feature maps across stages, CSPResNet50 reduces redundant computations, optimizes gradient flow, and enhances feature representation. +CSPResNet50 combines the strengths of ResNet50 and CSPNet (Cross-Stage Partial Network) to create a more efficient and +high-performing architecture. By splitting and fusing feature maps across stages, CSPResNet50 reduces redundant +computations, optimizes gradient flow, and enhances feature representation. ## Model Preparation +### Prepare Resources + +Pretrained model: + +Dataset: to download the validation dataset. + ### Install Dependencies ```bash @@ -18,12 +26,6 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Prepare Resources - -Pretrained model: - -Dataset: to download the validation dataset. - ### Model Conversion ```bash @@ -61,4 +63,4 @@ bash scripts/infer_cspresnet50_fp16_performance.sh ## References -CSPResNet50: +- [mmpretrain](https://github.com/open-mmlab/mmpretrain) diff --git a/models/cv/classification/cspresnet50/ixrt/README.md b/models/cv/classification/cspresnet50/ixrt/README.md index abc1094d..2e14d060 100644 --- a/models/cv/classification/cspresnet50/ixrt/README.md +++ b/models/cv/classification/cspresnet50/ixrt/README.md @@ -1,4 +1,4 @@ -# CSPResNet50 +# CSPResNet50 (IxRT) ## Model Description @@ -7,6 +7,10 @@ CSPResNet50 is the one of best models. ## Model Preparation +### Prepare Resources + +Dataset: to download the validation dataset. + ### Install Dependencies ```bash @@ -19,10 +23,6 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Prepare Resources - -Dataset: to download the validation dataset. - ### Model Conversion ```bash @@ -43,7 +43,6 @@ export DATASETS_DIR=/path/to/imagenet_val export CHECKPOINTS_DIR=./checkpoints export RUN_DIR=./ export CONFIG_DIR=config/CSPRESNET50_CONFIG - ``` ### FP16 @@ -66,7 +65,7 @@ bash scripts/infer_cspresnet50_int8_performance.sh ## Model Results -Model |BatchSize |Precision |FPS |Top-1(%) |Top-5(%) -------------|-----------|----------|---------|----------|-------- -CSPResNet50 | 32 | FP16 | 4555.95 | 78.51 | 94.17 -CSPResNet50 | 32 | INT8 | 8801.94 | 78.15 | 93.95 +| Model | BatchSize | Precision | FPS | Top-1(%) | Top-5(%) | +|-------------|-----------|-----------|---------|----------|----------| +| CSPResNet50 | 32 | FP16 | 4555.95 | 78.51 | 94.17 | +| CSPResNet50 | 32 | INT8 | 8801.94 | 78.15 | 93.95 | diff --git a/models/cv/classification/deit_tiny/igie/README.md b/models/cv/classification/deit_tiny/igie/README.md index 0e705a42..374b665d 100644 --- a/models/cv/classification/deit_tiny/igie/README.md +++ b/models/cv/classification/deit_tiny/igie/README.md @@ -1,4 +1,4 @@ -# DeiT-tiny +# DeiT-tiny (IGIE) ## Model Description @@ -6,6 +6,12 @@ DeiT Tiny is a lightweight vision transformer designed for data-efficient learni ## Model Preparation +### Prepare Resources + +Pretrained model: + +Dataset: to download the validation dataset. + ### Install Dependencies ```bash @@ -18,12 +24,6 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Prepare Resources - -Pretrained model: - -Dataset: to download the validation dataset. - ### Model Conversion ```bash @@ -35,7 +35,6 @@ python3 export.py --cfg mmpretrain/configs/deit/deit-tiny_pt-4xb256_in1k.py --we # Use onnxsim optimize onnx model onnxsim deit_tiny.onnx deit_tiny_opt.onnx - ``` ## Model Inference @@ -61,4 +60,4 @@ bash scripts/infer_deit_tin_fp16_performance.sh ## References -Deit_tiny: +- [mmpretrain](https://github.com/open-mmlab/mmpretrain) diff --git a/models/cv/classification/deit_tiny/ixrt/README.md b/models/cv/classification/deit_tiny/ixrt/README.md index 813acbfb..1b5b42b2 100644 --- a/models/cv/classification/deit_tiny/ixrt/README.md +++ b/models/cv/classification/deit_tiny/ixrt/README.md @@ -1,4 +1,4 @@ -# DeiT-tiny +# DeiT-tiny (IxRT) ## Model Description @@ -6,6 +6,12 @@ DeiT Tiny is a lightweight vision transformer designed for data-efficient learni ## Model Preparation +### Prepare Resources + +Pretrained model: + +Dataset: to download the validation dataset. + ### Install Dependencies ```bash @@ -15,21 +21,9 @@ yum install -y mesa-libGL ## Ubuntu apt install -y libgl1-mesa-glx -pip3 install tqdm -pip3 install onnx -pip3 install onnxsim -pip3 install tabulate -pip3 install ppq -pip3 install tqdm -pip3 install cuda-python +pip3 install -r requirements.txt ``` -### Prepare Resources - -Pretrained model: - -Dataset: to download the validation dataset. - ### Model Conversion ```bash @@ -70,4 +64,4 @@ bash scripts/infer_deit_tiny_fp16_performance.sh ## References -Deit_tiny: +- [mmpretrain](https://github.com/open-mmlab/mmpretrain) diff --git a/models/cv/classification/deit_tiny/ixrt/requirements.txt b/models/cv/classification/deit_tiny/ixrt/requirements.txt new file mode 100644 index 00000000..520130b7 --- /dev/null +++ b/models/cv/classification/deit_tiny/ixrt/requirements.txt @@ -0,0 +1,7 @@ +tqdm +onnx +onnxsim +tabulate +ppq +tqdm +cuda-python \ No newline at end of file diff --git a/models/cv/classification/densenet121/igie/README.md b/models/cv/classification/densenet121/igie/README.md index f93055b1..2ca0d81e 100644 --- a/models/cv/classification/densenet121/igie/README.md +++ b/models/cv/classification/densenet121/igie/README.md @@ -1,4 +1,4 @@ -# DenseNet121 +# DenseNet121 (IGIE) ## Model Description @@ -6,18 +6,18 @@ DenseNet-121 is a convolutional neural network architecture that belongs to the ## Model Preparation -### Install Dependencies - -```bash -pip3 install -r requirements.txt -``` - ### Prepare Resources Pretrained model: Dataset: to download the validation dataset. +### Install Dependencies + +```bash +pip3 install -r requirements.txt +``` + ### Model Conversion ```bash @@ -41,6 +41,6 @@ bash scripts/infer_densenet121_fp16_performance.sh ## Model Results -Model |BatchSize |Precision |FPS |Top-1(%) |Top-5(%) -------------|-----------|----------|---------|---------|-------- -DenseNet121 | 32 | FP16 | 2199.75 | 74.40 | 91.931 +| Model | BatchSize | Precision | FPS | Top-1(%) | Top-5(%) | +|-------------|-----------|-----------|---------|----------|----------| +| DenseNet121 | 32 | FP16 | 2199.75 | 74.40 | 91.931 | diff --git a/models/cv/classification/densenet121/ixrt/README.md b/models/cv/classification/densenet121/ixrt/README.md index 1d3dbfd3..d683c422 100644 --- a/models/cv/classification/densenet121/ixrt/README.md +++ b/models/cv/classification/densenet121/ixrt/README.md @@ -1,4 +1,4 @@ -# DenseNet +# DenseNet (IxRT) ## Model Description @@ -6,6 +6,10 @@ Dense Convolutional Network (DenseNet), connects each layer to every other layer ## Model Preparation +### Prepare Resources + +Dataset: to download the validation dataset. + ### Install Dependencies ```bash @@ -18,10 +22,6 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Prepare Resources - -Dataset: to download the validation dataset. - ### Model Conversion ```bash diff --git a/models/cv/classification/densenet161/igie/README.md b/models/cv/classification/densenet161/igie/README.md index 3add49cc..4b736b3f 100644 --- a/models/cv/classification/densenet161/igie/README.md +++ b/models/cv/classification/densenet161/igie/README.md @@ -1,4 +1,4 @@ -# DenseNet161 +# DenseNet161 (IGIE) ## Model Description @@ -6,18 +6,18 @@ DenseNet161 is a convolutional neural network architecture that belongs to the f ## Model Preparation -### Install Dependencies - -```bash -pip3 install -r requirements.txt -``` - ### Prepare Resources Pretrained model: Dataset: to download the validation dataset. +### Install Dependencies + +```bash +pip3 install -r requirements.txt +``` + ### Model Conversion ```bash diff --git a/models/cv/classification/densenet161/ixrt/README.md b/models/cv/classification/densenet161/ixrt/README.md index d3bf9c29..70dba728 100644 --- a/models/cv/classification/densenet161/ixrt/README.md +++ b/models/cv/classification/densenet161/ixrt/README.md @@ -1,4 +1,4 @@ -# DenseNet161 +# DenseNet161 (IxRT) ## Model Description @@ -6,6 +6,11 @@ DenseNet161 is a convolutional neural network architecture that belongs to the f ## Model Preparation +### Prepare Resources + +Pretrained model: +Dataset: to download the validation dataset. + ### Install Dependencies ```bash @@ -18,11 +23,6 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Prepare Resources - -Pretrained model: -Dataset: to download the validation dataset. - ### Model Conversion ```bash diff --git a/models/cv/classification/densenet169/igie/README.md b/models/cv/classification/densenet169/igie/README.md index 9e95b177..6560fdb9 100644 --- a/models/cv/classification/densenet169/igie/README.md +++ b/models/cv/classification/densenet169/igie/README.md @@ -1,4 +1,4 @@ -# DenseNet169 +# DenseNet169 (IGIE) ## Model Description @@ -6,18 +6,18 @@ DenseNet-169 is a variant of the Dense Convolutional Network (DenseNet) architec ## Model Preparation -### Install Dependencies - -```bash -pip3 install -r requirements.txt -``` - ### Prepare Resources Pretrained model: Dataset: to download the validation dataset. +### Install Dependencies + +```bash +pip3 install -r requirements.txt +``` + ### Model Conversion ```bash diff --git a/models/cv/classification/densenet169/ixrt/README.md b/models/cv/classification/densenet169/ixrt/README.md index a8ce1435..c60b673a 100644 --- a/models/cv/classification/densenet169/ixrt/README.md +++ b/models/cv/classification/densenet169/ixrt/README.md @@ -1,4 +1,4 @@ -# DenseNet169 +# DenseNet169 (IxRT) ## Model Description @@ -6,6 +6,12 @@ Dense Convolutional Network (DenseNet), connects each layer to every other layer ## Model Preparation +### Prepare Resources + +Pretrained model: + +Dataset: to download the validation dataset. + ### Install Dependencies ```bash @@ -18,12 +24,6 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Prepare Resources - -Pretrained model: - -Dataset: to download the validation dataset. - ### Model Conversion ```bash @@ -47,6 +47,6 @@ bash scripts/infer_densenet169_fp16_performance.sh ## Model Results -| Model | BatchSize | Precision | FPS | Top-1(%) | Top-5(%) | -| -------- | --------- | --------- | ------- | -------- | -------- | +| Model | BatchSize | Precision | FPS | Top-1(%) | Top-5(%) | +|-------------|-----------|-----------|---------|----------|----------| | DenseNet169 | 32 | FP16 | 1119.69 | 0.7558 | 0.9284 | diff --git a/models/cv/classification/densenet201/igie/README.md b/models/cv/classification/densenet201/igie/README.md index 1fc6b13f..a21fd44b 100644 --- a/models/cv/classification/densenet201/igie/README.md +++ b/models/cv/classification/densenet201/igie/README.md @@ -1,4 +1,4 @@ -# DenseNet201 +# DenseNet201 (IGIE) ## Model Description @@ -6,18 +6,18 @@ DenseNet201 is a deep convolutional neural network that stands out for its uniqu ## Model Preparation -### Install Dependencies - -```bash -pip3 install -r requirements.txt -``` - ### Prepare Resources Pretrained model: Dataset: to download the validation dataset. +### Install Dependencies + +```bash +pip3 install -r requirements.txt +``` + ### Model Conversion ```bash diff --git a/models/cv/classification/densenet201/ixrt/README.md b/models/cv/classification/densenet201/ixrt/README.md index 185c08ef..1fc3594f 100644 --- a/models/cv/classification/densenet201/ixrt/README.md +++ b/models/cv/classification/densenet201/ixrt/README.md @@ -1,4 +1,4 @@ -# DenseNet201 +# DenseNet201 (IxRT) ## Model Description @@ -6,6 +6,12 @@ DenseNet201 is a deep convolutional neural network that stands out for its uniqu ## Model Preparation +### Prepare Resources + +Pretrained model: + +Dataset: to download the validation dataset. + ### Install Dependencies ```bash @@ -15,21 +21,9 @@ yum install -y mesa-libGL ## Ubuntu apt install -y libgl1-mesa-glx -pip3 install tqdm -pip3 install onnx -pip3 install onnxsim -pip3 install tabulate -pip3 install ppq -pip3 install tqdm -pip3 install cuda-python +pip3 install -r requirements.txt ``` -### Prepare Resources - -Pretrained model: - -Dataset: to download the validation dataset. - ### Model Conversion ```bash diff --git a/models/cv/classification/densenet201/ixrt/requirements.txt b/models/cv/classification/densenet201/ixrt/requirements.txt new file mode 100644 index 00000000..520130b7 --- /dev/null +++ b/models/cv/classification/densenet201/ixrt/requirements.txt @@ -0,0 +1,7 @@ +tqdm +onnx +onnxsim +tabulate +ppq +tqdm +cuda-python \ No newline at end of file diff --git a/models/cv/classification/efficientnet_b0/igie/README.md b/models/cv/classification/efficientnet_b0/igie/README.md index 03ab87d2..20001680 100644 --- a/models/cv/classification/efficientnet_b0/igie/README.md +++ b/models/cv/classification/efficientnet_b0/igie/README.md @@ -1,4 +1,4 @@ -# EfficientNet B0 +# EfficientNet B0 (IGIE) ## Model Description @@ -6,18 +6,18 @@ EfficientNet-B0 is a lightweight yet highly efficient convolutional neural netwo ## Model Preparation -### Install Dependencies - -```bash -pip3 install -r requirements.txt -``` - ### Prepare Resources Pretrained model: Dataset: to download the validation dataset. +### Install Dependencies + +```bash +pip3 install -r requirements.txt +``` + ### Model Conversion ```bash @@ -41,6 +41,6 @@ bash scripts/infer_efficientnet_b0_fp16_performance.sh ## Model Results -Model |BatchSize |Precision |FPS |Top-1(%) |Top-5(%) -----------------|-----------|----------|----------|----------|-------- -EfficientNet_B0 | 32 | FP16 | 2596.60 | 77.639 | 93.540 +| Model | BatchSize | Precision | FPS | Top-1(%) | Top-5(%) | +|-----------------|-----------|-----------|---------|----------|----------| +| EfficientNet_B0 | 32 | FP16 | 2596.60 | 77.639 | 93.540 | diff --git a/models/cv/classification/efficientnet_b0/ixrt/README.md b/models/cv/classification/efficientnet_b0/ixrt/README.md index 61b87328..c7a7448b 100644 --- a/models/cv/classification/efficientnet_b0/ixrt/README.md +++ b/models/cv/classification/efficientnet_b0/ixrt/README.md @@ -1,4 +1,4 @@ -# EfficientNet B0 +# EfficientNet B0 (IxRT) ## Model Description @@ -6,6 +6,12 @@ EfficientNet B0 is a convolutional neural network architecture that belongs to t ## Model Preparation +### Prepare Resources + +Pretrained model: + +Dataset: to download the validation dataset. + ### Install Dependencies ```bash @@ -18,12 +24,6 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Prepare Resources - -Pretrained model: - -Dataset: to download the validation dataset. - ### Model Conversion ```bash @@ -57,6 +57,6 @@ bash scripts/infer_efficientnet_b0_int8_performance.sh ## Model Results | Model | BatchSize | Precision | FPS | Top-1(%) | Top-5(%) | -| --------------- | --------- | --------- | ------- | -------- | -------- | +|-----------------|-----------|-----------|---------|----------|----------| | EfficientNet B0 | 32 | FP16 | 2325.54 | 77.66 | 93.58 | | EfficientNet B0 | 32 | INT8 | 2666.00 | 74.27 | 91.85 | diff --git a/models/cv/classification/efficientnet_b1/igie/README.md b/models/cv/classification/efficientnet_b1/igie/README.md index 44864622..1a36f8aa 100644 --- a/models/cv/classification/efficientnet_b1/igie/README.md +++ b/models/cv/classification/efficientnet_b1/igie/README.md @@ -1,4 +1,4 @@ -# EfficientNet B1 +# EfficientNet B1 (IGIE) ## Model Description @@ -6,18 +6,18 @@ EfficientNet B1 is a convolutional neural network architecture that falls under ## Model Preparation -### Install Dependencies - -```bash -pip3 install -r requirements.txt -``` - ### Prepare Resources Pretrained model: Dataset: to download the validation dataset. +### Install Dependencies + +```bash +pip3 install -r requirements.txt +``` + ### Model Conversion ```bash @@ -41,6 +41,6 @@ bash scripts/infer_efficientnet_b1_fp16_performance.sh ## Model Results -Model |BatchSize |Precision |FPS |Top-1(%) |Top-5(%) -----------------|-----------|----------|---------|---------|-------- -EfficientNet B1 | 32 | FP16 | 1292.31 | 78.823 | 94.494 +| Model | BatchSize | Precision | FPS | Top-1(%) | Top-5(%) | +|-----------------|-----------|-----------|---------|----------|----------| +| EfficientNet B1 | 32 | FP16 | 1292.31 | 78.823 | 94.494 | diff --git a/models/cv/classification/efficientnet_b1/ixrt/README.md b/models/cv/classification/efficientnet_b1/ixrt/README.md index ae95d1d7..0fc5a210 100644 --- a/models/cv/classification/efficientnet_b1/ixrt/README.md +++ b/models/cv/classification/efficientnet_b1/ixrt/README.md @@ -1,4 +1,4 @@ -# EfficientNet B1 +# EfficientNet B1 (IxRT) ## Model Description @@ -6,6 +6,10 @@ EfficientNet B1 is one of the variants in the EfficientNet family of neural netw ## Model Preparation +### Prepare Resources + +Dataset: to download the validation dataset. + ### Install Dependencies ```bash @@ -18,10 +22,6 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Prepare Resources - -Dataset: to download the validation dataset. - ### Model Conversion ```bash @@ -59,7 +59,7 @@ bash scripts/infer_efficientnet_b1_int8_performance.sh ## Model Results -Model |BatchSize |Precision |FPS |Top-1(%) |Top-5(%) -----------------|-----------|----------|---------|----------|-------- -EfficientNet_B1 | 32 | FP16 | 1517.84 | 77.60 | 93.60 -EfficientNet_B1 | 32 | INT8 | 1817.88 | 75.32 | 92.46 +| Model | BatchSize | Precision | FPS | Top-1(%) | Top-5(%) | +|-----------------|-----------|-----------|---------|----------|----------| +| EfficientNet_B1 | 32 | FP16 | 1517.84 | 77.60 | 93.60 | +| EfficientNet_B1 | 32 | INT8 | 1817.88 | 75.32 | 92.46 | diff --git a/models/cv/classification/efficientnet_b2/igie/README.md b/models/cv/classification/efficientnet_b2/igie/README.md index ab138a37..efdb3274 100644 --- a/models/cv/classification/efficientnet_b2/igie/README.md +++ b/models/cv/classification/efficientnet_b2/igie/README.md @@ -1,4 +1,4 @@ -# EfficientNet B2 +# EfficientNet B2 (IGIE) ## Model Description @@ -6,18 +6,18 @@ EfficientNet B2 is a member of the EfficientNet family, a series of convolutiona ## Model Preparation -### Install Dependencies - -```bash -pip3 install -r requirements.txt -``` - ### Prepare Resources Pretrained model: Dataset: to download the validation dataset. +### Install Dependencies + +```bash +pip3 install -r requirements.txt +``` + ### Model Conversion ```bash @@ -42,5 +42,5 @@ bash scripts/infer_efficientnet_b2_fp16_performance.sh ## Model Results | Model | BatchSize | Precision | FPS | Top-1(%) | Top-5(%) | -| --------------- | --------- | --------- | -------- | -------- | -------- | +|-----------------|-----------|-----------|----------|----------|----------| | EfficientNet B2 | 32 | FP16 | 1527.044 | 77.739 | 93.702 | diff --git a/models/cv/classification/efficientnet_b2/ixrt/README.md b/models/cv/classification/efficientnet_b2/ixrt/README.md index d5e4c234..e627737e 100644 --- a/models/cv/classification/efficientnet_b2/ixrt/README.md +++ b/models/cv/classification/efficientnet_b2/ixrt/README.md @@ -1,4 +1,4 @@ -# EfficientNet B2 +# EfficientNet B2 (IxRT) ## Model Description @@ -6,6 +6,12 @@ EfficientNet B2 is a member of the EfficientNet family, a series of convolutiona ## Model Preparation +### Prepare Resources + +Pretrained model: + +Dataset: to download the validation dataset. + ### Install Dependencies ```bash @@ -18,12 +24,6 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Prepare Resources - -Pretrained model: - -Dataset: to download the validation dataset. - ### Model Conversion ```bash diff --git a/models/cv/classification/efficientnet_b3/igie/README.md b/models/cv/classification/efficientnet_b3/igie/README.md index c4d72df2..cd219d92 100644 --- a/models/cv/classification/efficientnet_b3/igie/README.md +++ b/models/cv/classification/efficientnet_b3/igie/README.md @@ -1,4 +1,4 @@ -# EfficientNet B3 +# EfficientNet B3 (IGIE) ## Model Description @@ -6,18 +6,18 @@ EfficientNet B3 is a member of the EfficientNet family, a series of convolutiona ## Model Preparation -### Install Dependencies - -```bash -pip3 install -r requirements.txt -``` - ### Prepare Resources Pretrained model: Dataset: to download the validation dataset. +### Install Dependencies + +```bash +pip3 install -r requirements.txt +``` + ### Model Conversion ```bash diff --git a/models/cv/classification/efficientnet_b3/ixrt/README.md b/models/cv/classification/efficientnet_b3/ixrt/README.md index b9861c6b..4851383f 100644 --- a/models/cv/classification/efficientnet_b3/ixrt/README.md +++ b/models/cv/classification/efficientnet_b3/ixrt/README.md @@ -1,4 +1,4 @@ -# EfficientNet B3 +# EfficientNet B3 (IxRT) ## Model Description @@ -6,6 +6,12 @@ EfficientNet B3 is a member of the EfficientNet family, a series of convolutiona ## Model Preparation +### Prepare Resources + +Pretrained model: + +Dataset: to download the validation dataset. + ### Install Dependencies ```bash @@ -15,18 +21,9 @@ yum install -y mesa-libGL ## Ubuntu apt install -y libgl1-mesa-glx -pip3 install tqdm -pip3 install onnx -pip3 install onnxsim -pip3 install tabulate +pip3 install -r requirements.txt ``` -### Prepare Resources - -Pretrained model: - -Dataset: to download the validation dataset. - ### Model Conversion ```bash diff --git a/models/cv/classification/efficientnet_b3/ixrt/requirements.txt b/models/cv/classification/efficientnet_b3/ixrt/requirements.txt new file mode 100644 index 00000000..e1eda59c --- /dev/null +++ b/models/cv/classification/efficientnet_b3/ixrt/requirements.txt @@ -0,0 +1,4 @@ +tqdm +onnx +onnxsim +tabulate \ No newline at end of file diff --git a/models/cv/classification/efficientnet_b4/igie/README.md b/models/cv/classification/efficientnet_b4/igie/README.md index 403194e3..8e97a99c 100644 --- a/models/cv/classification/efficientnet_b4/igie/README.md +++ b/models/cv/classification/efficientnet_b4/igie/README.md @@ -1,4 +1,4 @@ -# EfficientNet B4 +# EfficientNet B4 (IGIE) ## Model Description @@ -6,18 +6,18 @@ EfficientNet B4 is a high-performance convolutional neural network model introdu ## Model Preparation -### Install Dependencies - -```bash -pip3 install -r requirements.txt -``` - ### Prepare Resources Pretrained model: Dataset: to download the validation dataset. +### Install Dependencies + +```bash +pip3 install -r requirements.txt +``` + ### Model Conversion ```bash diff --git a/models/cv/classification/efficientnet_v2/igie/README.md b/models/cv/classification/efficientnet_v2/igie/README.md index 0ae45c84..3ee88837 100644 --- a/models/cv/classification/efficientnet_v2/igie/README.md +++ b/models/cv/classification/efficientnet_v2/igie/README.md @@ -1,4 +1,4 @@ -# EfficientNetV2-M +# EfficientNetV2-M (IGIE) ## Model Description @@ -6,18 +6,18 @@ EfficientNetV2 M is an optimized model in the EfficientNetV2 series, which was d ## Model Preparation -### Install Dependencies - -```bash -pip3 install -r requirements.txt -``` - ### Prepare Resources Pretrained model: Dataset: to download the validation dataset. +### Install Dependencies + +```bash +pip3 install -r requirements.txt +``` + ### Model Conversion ```bash diff --git a/models/cv/classification/efficientnet_v2/ixrt/README.md b/models/cv/classification/efficientnet_v2/ixrt/README.md index e4acdd8c..9355271c 100755 --- a/models/cv/classification/efficientnet_v2/ixrt/README.md +++ b/models/cv/classification/efficientnet_v2/ixrt/README.md @@ -1,11 +1,19 @@ -# EfficientNetV2 +# EfficientNetV2 (IxRT) ## Model Description -EfficientNetV2 is an improved version of the EfficientNet architecture proposed by Google, aiming to enhance model performance and efficiency. Unlike the original EfficientNet, EfficientNetV2 features a simplified design and incorporates a series of enhancement strategies to further boost performance. +EfficientNetV2 is an improved version of the EfficientNet architecture proposed by Google, aiming to enhance model +performance and efficiency. Unlike the original EfficientNet, EfficientNetV2 features a simplified design and +incorporates a series of enhancement strategies to further boost performance. ## Model Preparation +### Prepare Resources + +Pretrained model: + +Dataset: to download the validation dataset. + ### Install Dependencies ```bash @@ -18,12 +26,6 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Prepare Resources - -Pretrained model: - -Dataset: to download the validation dataset. - ### Model Conversion ```bash @@ -70,7 +72,7 @@ bash scripts/infer_efficientnet_v2_int8_performance.sh ## Model Results -Model | BatchSize | Precision | FPS | Top-1(%) | Top-5(%) ----------------|-----------|-----------|----------|----------|-------- -EfficientnetV2 | 32 | FP16 | 1882.87 | 82.14 | 96.16 -EfficientnetV2 | 32 | INT8 | 2595.96 | 81.50 | 95.96 +| Model | BatchSize | Precision | FPS | Top-1(%) | Top-5(%) | +|----------------|-----------|-----------|---------|----------|----------| +| EfficientnetV2 | 32 | FP16 | 1882.87 | 82.14 | 96.16 | +| EfficientnetV2 | 32 | INT8 | 2595.96 | 81.50 | 95.96 | diff --git a/models/cv/classification/efficientnet_v2_s/igie/README.md b/models/cv/classification/efficientnet_v2_s/igie/README.md index 69508ab6..00a733d5 100644 --- a/models/cv/classification/efficientnet_v2_s/igie/README.md +++ b/models/cv/classification/efficientnet_v2_s/igie/README.md @@ -1,4 +1,4 @@ -# EfficientNet_v2_s +# EfficientNet_v2_s (IGIE) ## Model Description @@ -6,18 +6,18 @@ EfficientNetV2 S is an optimized model in the EfficientNetV2 series, which was d ## Model Preparation -### Install Dependencies - -```bash -pip3 install -r requirements.txt -``` - ### Prepare Resources Pretrained model: Dataset: to download the validation dataset. +### Install Dependencies + +```bash +pip3 install -r requirements.txt +``` + ### Model Conversion ```bash diff --git a/models/cv/classification/efficientnet_v2_s/ixrt/README.md b/models/cv/classification/efficientnet_v2_s/ixrt/README.md index 06947aa9..92f3874b 100644 --- a/models/cv/classification/efficientnet_v2_s/ixrt/README.md +++ b/models/cv/classification/efficientnet_v2_s/ixrt/README.md @@ -1,4 +1,4 @@ -# EfficientNet_v2_s +# EfficientNet_v2_s (IxRT) ## Model Description @@ -6,18 +6,18 @@ EfficientNetV2 S is an optimized model in the EfficientNetV2 series, which was d ## Model Preparation -### Install Dependencies - -```bash -pip3 install -r requirements.txt -``` - ### Prepare Resources Pretrained model: Dataset: to download the validation dataset. +### Install Dependencies + +```bash +pip3 install -r requirements.txt +``` + ### Model Conversion ```bash diff --git a/models/cv/classification/efficientnetv2_rw_t/igie/README.md b/models/cv/classification/efficientnetv2_rw_t/igie/README.md index cec8e84e..1f16673b 100644 --- a/models/cv/classification/efficientnetv2_rw_t/igie/README.md +++ b/models/cv/classification/efficientnetv2_rw_t/igie/README.md @@ -1,4 +1,4 @@ -# EfficientNetv2_rw_t +# EfficientNetv2_rw_t (IGIE) ## Model Description @@ -6,18 +6,18 @@ EfficientNetV2_rw_t is an enhanced version of the EfficientNet family of convolu ## Model Preparation -### Install Dependencies - -```bash -pip3 install -r requirements.txt -``` - ### Prepare Resources Pretrained model: Dataset: to download the validation dataset. +### Install Dependencies + +```bash +pip3 install -r requirements.txt +``` + ### Model Conversion ```bash @@ -41,6 +41,6 @@ bash scripts/infer_efficientnetv2_rw_t_fp16_performance.sh ## Model Results -Model |BatchSize |Precision |FPS |Top-1(%) |Top-5(%) ---------------------|-----------|----------|---------|---------|-------- -Efficientnetv2_rw_t | 32 | FP16 | 831.678 | 82.306 | 96.163 +| Model | BatchSize | Precision | FPS | Top-1(%) | Top-5(%) | +|---------------------|-----------|-----------|---------|----------|----------| +| Efficientnetv2_rw_t | 32 | FP16 | 831.678 | 82.306 | 96.163 | diff --git a/models/cv/classification/efficientnetv2_rw_t/ixrt/README.md b/models/cv/classification/efficientnetv2_rw_t/ixrt/README.md index 07877330..3ca2ec65 100644 --- a/models/cv/classification/efficientnetv2_rw_t/ixrt/README.md +++ b/models/cv/classification/efficientnetv2_rw_t/ixrt/README.md @@ -1,4 +1,4 @@ -# EfficientNetv2_rw_t +# EfficientNetv2_rw_t (IGIE) ## Model Description @@ -6,6 +6,12 @@ EfficientNetV2_rw_t is an enhanced version of the EfficientNet family of convolu ## Model Preparation +### Prepare Resources + +Pretrained model: + +Dataset: to download the validation dataset. + ### Install Dependencies ```bash @@ -15,22 +21,9 @@ yum install -y mesa-libGL ## Ubuntu apt install -y libgl1-mesa-glx -pip3 install tqdm -pip3 install timm -pip3 install onnx -pip3 install onnxsim -pip3 install tabulate -pip3 install ppq -pip3 install tqdm -pip3 install cuda-python +pip3 install -r requirements.txt ``` -### Prepare Resources - -Pretrained model: - -Dataset: to download the validation dataset. - ### Model Conversion ```bash @@ -54,6 +47,6 @@ bash scripts/infer_efficientnetv2_rw_t_fp16_performance.sh ## Model Results -Model |BatchSize |Precision |FPS |Top-1(%) |Top-5(%) ---------------------|-----------|----------|---------|---------|-------- -Efficientnetv2_rw_t | 32 | FP16 | 1525.22 | 82.336 | 96.194 +| Model | BatchSize | Precision | FPS | Top-1(%) | Top-5(%) | +|---------------------|-----------|-----------|---------|----------|----------| +| Efficientnetv2_rw_t | 32 | FP16 | 1525.22 | 82.336 | 96.194 | diff --git a/models/cv/classification/efficientnetv2_rw_t/ixrt/requirements.txt b/models/cv/classification/efficientnetv2_rw_t/ixrt/requirements.txt new file mode 100644 index 00000000..72371658 --- /dev/null +++ b/models/cv/classification/efficientnetv2_rw_t/ixrt/requirements.txt @@ -0,0 +1,8 @@ +tqdm +timm +onnx +onnxsim +tabulate +ppq +tqdm +cuda-python \ No newline at end of file diff --git a/models/cv/classification/googlenet/igie/README.md b/models/cv/classification/googlenet/igie/README.md index 3279e311..4f1a030a 100644 --- a/models/cv/classification/googlenet/igie/README.md +++ b/models/cv/classification/googlenet/igie/README.md @@ -1,4 +1,4 @@ -# GoogleNet +# GoogleNet (IGIE) ## Model Description @@ -6,18 +6,18 @@ Introduced in 2014, GoogleNet revolutionized image classification models by intr ## Model Preparation -### Install Dependencies - -```bash -pip3 install -r requirements.txt -``` - ### Prepare Resources Pretrained model: Dataset: to download the validation dataset. +### Install Dependencies + +```bash +pip3 install -r requirements.txt +``` + ### Model Conversion ```bash @@ -50,7 +50,7 @@ bash scripts/infer_googlenet_int8_performance.sh ## Model Results -Model |BatchSize |Precision |FPS |Top-1(%) |Top-5(%) -----------|-----------|----------|----------|---------|-------- -GoogleNet | 32 | FP16 | 6564.20 | 62.44 | 84.31 -GoogleNet | 32 | INT8 | 7910.65 | 61.06 | 83.26 +| Model | BatchSize | Precision | FPS | Top-1(%) | Top-5(%) | +|-----------|-----------|-----------|---------|----------|----------| +| GoogleNet | 32 | FP16 | 6564.20 | 62.44 | 84.31 | +| GoogleNet | 32 | INT8 | 7910.65 | 61.06 | 83.26 | diff --git a/models/cv/classification/googlenet/ixrt/README.md b/models/cv/classification/googlenet/ixrt/README.md index bd71b32f..b0d14230 100644 --- a/models/cv/classification/googlenet/ixrt/README.md +++ b/models/cv/classification/googlenet/ixrt/README.md @@ -1,4 +1,4 @@ -# GoogLeNet +# GoogLeNet (IxRT) ## Model Description @@ -6,6 +6,12 @@ GoogLeNet is a type of convolutional neural network based on the Inception archi ## Model Preparation +### Prepare Resources + +Pretrained model: + +Dataset: to download the validation dataset. + ### Install Dependencies ```bash @@ -18,12 +24,6 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Prepare Resources - -Pretrained model: - -Dataset: to download the validation dataset. - ### Model Conversion ```bash @@ -61,7 +61,7 @@ bash scripts/infer_googlenet_int8_performance.sh ## Model Results -Model |BatchSize |Precision |FPS |Top-1(%) |Top-5(%) -----------|-----------|----------|----------|----------|-------- -GoogLeNet | 32 | FP16 | 6470.34 | 62.456 | 84.33 -GoogLeNet | 32 | INT8 | 9358.11 | 62.106 | 84.30 +| Model | BatchSize | Precision | FPS | Top-1(%) | Top-5(%) | +|-----------|-----------|-----------|---------|----------|----------| +| GoogLeNet | 32 | FP16 | 6470.34 | 62.456 | 84.33 | +| GoogLeNet | 32 | INT8 | 9358.11 | 62.106 | 84.30 | diff --git a/models/cv/classification/hrnet_w18/igie/README.md b/models/cv/classification/hrnet_w18/igie/README.md index 65625631..80eb7c9d 100644 --- a/models/cv/classification/hrnet_w18/igie/README.md +++ b/models/cv/classification/hrnet_w18/igie/README.md @@ -1,4 +1,4 @@ -# HRNet-W18 +# HRNet-W18 (IGIE) ## Model Description @@ -6,6 +6,12 @@ HRNet, short for High-Resolution Network, presents a paradigm shift in handling ## Model Preparation +### Prepare Resources + +Pretrained model: + +Dataset: to download the validation dataset. + ### Install Dependencies ```bash @@ -18,12 +24,6 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Prepare Resources - -Pretrained model: - -Dataset: to download the validation dataset. - ### Model Conversion ```bash @@ -35,7 +35,6 @@ python3 export.py --cfg mmpretrain/configs/hrnet/hrnet-w18_4xb32_in1k.py --weigh # Use onnxsim optimize onnx model onnxsim hrnet_w18.onnx hrnet_w18_opt.onnx - ``` ## Model Inference @@ -61,4 +60,4 @@ HRNet_w18 | 32 | FP16 | 954.18 | 76.74 | 93.42 ## References -HRNet: +- [mmpretrain](https://github.com/open-mmlab/mmpretrain) diff --git a/models/cv/classification/hrnet_w18/ixrt/README.md b/models/cv/classification/hrnet_w18/ixrt/README.md index fe8f9726..d09d4fe9 100644 --- a/models/cv/classification/hrnet_w18/ixrt/README.md +++ b/models/cv/classification/hrnet_w18/ixrt/README.md @@ -1,4 +1,4 @@ -# HRNet-W18 +# HRNet-W18 (IxRT) ## Model Description @@ -6,6 +6,10 @@ HRNet-W18 is a powerful image classification model developed by Jingdong AI Rese ## Model Preparation +### Prepare Resources + +Dataset: to download the validation dataset. + ### Install Dependencies ```bash @@ -18,10 +22,6 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Prepare Resources - -Dataset: to download the validation dataset. - ### Model Conversion ```bash @@ -59,6 +59,6 @@ bash scripts/infer_hrnet_w18_int8_performance.sh ## Model Results | Model | BatchSize | Precision | FPS | Top-1(%) | Top-5(%) | -| -------- | --------- | --------- | ------- | -------- | -------- | +|----------|-----------|-----------|---------|----------|----------| | ResNet50 | 32 | FP16 | 1474.26 | 0.76764 | 0.93446 | | ResNet50 | 32 | INT8 | 1649.40 | 0.76158 | 0.93152 | diff --git a/models/cv/classification/inception_resnet_v2/ixrt/README.md b/models/cv/classification/inception_resnet_v2/ixrt/README.md index 01c3965b..4ab239f6 100755 --- a/models/cv/classification/inception_resnet_v2/ixrt/README.md +++ b/models/cv/classification/inception_resnet_v2/ixrt/README.md @@ -1,4 +1,4 @@ -# Inception-ResNet-V2 +# Inception-ResNet-V2 (IxRT) ## Model Description @@ -6,6 +6,12 @@ Inception-ResNet-V2 is a deep learning model proposed by Google in 2016, which c ## Model Preparation +### Prepare Resources + +Pretrained model: + +Dataset: to download the validation dataset. + ### Install Dependencies ```bash @@ -18,12 +24,6 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Prepare Resources - -Pretrained model: - -Dataset: to download the validation dataset. - ### Model Conversion ```bash diff --git a/models/cv/classification/inception_v3/igie/README.md b/models/cv/classification/inception_v3/igie/README.md index 2aeb2e7b..69dbd46b 100644 --- a/models/cv/classification/inception_v3/igie/README.md +++ b/models/cv/classification/inception_v3/igie/README.md @@ -1,4 +1,4 @@ -# Inception V3 +# Inception V3 (IGIE) ## Model Description @@ -6,18 +6,18 @@ Inception v3 is a convolutional neural network architecture designed for image r ## Model Preparation -### Install Dependencies - -```bash -pip3 install -r requirements.txt -``` - ### Prepare Resources Pretrained model: Dataset: to download the validation dataset. +### Install Dependencies + +```bash +pip3 install -r requirements.txt +``` + ### Model Conversion ```bash @@ -50,7 +50,7 @@ bash scripts/infer_inception_v3_int8_performance.sh ## Model Results -Model |BatchSize |Precision |FPS |Top-1(%) |Top-5(%) --------------|-----------|----------|----------|----------|-------- -Inception_v3 | 32 | FP16 | 3557.25 | 69.848 | 88.858 -Inception_v3 | 32 | INT8 | 3631.80 | 69.022 | 88.412 +| Model | BatchSize | Precision | FPS | Top-1(%) | Top-5(%) | +|--------------|-----------|-----------|---------|----------|----------| +| Inception_v3 | 32 | FP16 | 3557.25 | 69.848 | 88.858 | +| Inception_v3 | 32 | INT8 | 3631.80 | 69.022 | 88.412 | diff --git a/models/cv/classification/inception_v3/ixrt/README.md b/models/cv/classification/inception_v3/ixrt/README.md index b795ac9c..ba183ef3 100755 --- a/models/cv/classification/inception_v3/ixrt/README.md +++ b/models/cv/classification/inception_v3/ixrt/README.md @@ -1,4 +1,4 @@ -# Inception V3 +# Inception V3 (IxRT) ## Model Description @@ -6,6 +6,12 @@ Inception v3 is a convolutional neural network architecture designed for image r ## Model Preparation +### Prepare Resources + +Pretrained model: + +Dataset: to download the validation dataset. + ### Install Dependencies ```bash @@ -18,12 +24,6 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Prepare Resources - -Pretrained model: - -Dataset: to download the validation dataset. - ### Model Conversion ```bash @@ -63,7 +63,7 @@ bash scripts/infer_inception_v3_int8_performance.sh ## Model Results -Model |BatchSize |Precision |FPS |Top-1(%) |Top-5(%) --------------|-----------|----------|----------|----------|-------- -Inception_v3 | 32 | FP16 | 3515.29 | 70.64 | 89.33 -Inception_v3 | 32 | INT8 | 4916.32 | 70.45 | 89.28 +| Model | BatchSize | Precision | FPS | Top-1(%) | Top-5(%) | +|--------------|-----------|-----------|---------|----------|----------| +| Inception_v3 | 32 | FP16 | 3515.29 | 70.64 | 89.33 | +| Inception_v3 | 32 | INT8 | 4916.32 | 70.45 | 89.28 | diff --git a/models/cv/classification/mlp_mixer_base/igie/README.md b/models/cv/classification/mlp_mixer_base/igie/README.md index b9f1008d..ecd32b94 100644 --- a/models/cv/classification/mlp_mixer_base/igie/README.md +++ b/models/cv/classification/mlp_mixer_base/igie/README.md @@ -1,4 +1,4 @@ -# MLP-Mixer Base +# MLP-Mixer Base (IGIE) ## Model Description @@ -6,6 +6,12 @@ MLP-Mixer Base is a foundational model in the MLP-Mixer family, designed to use ## Model Preparation +### Prepare Resources + +Pretrained model: + +Dataset: to download the validation dataset. + ### Install Dependencies ```bash @@ -18,12 +24,6 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Prepare Resources - -Pretrained model: - -Dataset: to download the validation dataset. - ### Model Conversion ```bash @@ -61,4 +61,4 @@ bash scripts/infer_mlp_mixer_base_fp16_performance.sh ## References -MLP-Mixer-Base: +- [mmpretrain](https://github.com/open-mmlab/mmpretrain) diff --git a/models/cv/classification/mnasnet0_5/igie/README.md b/models/cv/classification/mnasnet0_5/igie/README.md index 3c3ea3a0..cc8f2c38 100644 --- a/models/cv/classification/mnasnet0_5/igie/README.md +++ b/models/cv/classification/mnasnet0_5/igie/README.md @@ -1,4 +1,4 @@ -# MNASNet0_5 +# MNASNet0_5 (IGIE) ## Model Description @@ -6,18 +6,18 @@ MNASNet0_5 is a neural network architecture optimized for mobile devices, design ## Model Preparation -### Install Dependencies - -```bash -pip3 install -r requirements.txt -``` - ### Prepare Resources Pretrained model: Dataset: to download the validation dataset. +### Install Dependencies + +```bash +pip3 install -r requirements.txt +``` + ### Model Conversion ```bash diff --git a/models/cv/classification/mnasnet0_75/igie/README.md b/models/cv/classification/mnasnet0_75/igie/README.md index 1899cc39..9288814c 100644 --- a/models/cv/classification/mnasnet0_75/igie/README.md +++ b/models/cv/classification/mnasnet0_75/igie/README.md @@ -1,4 +1,4 @@ -# MNASNet0_75 +# MNASNet0_75 (IGIE) ## Model Description @@ -6,18 +6,18 @@ MNASNet0_75 is a lightweight convolutional neural network designed for mobile de ## Model Preparation -### Install Dependencies - -```bash -pip3 install -r requirements.txt -``` - ### Prepare Resources Pretrained model: Dataset: to download the validation dataset. +### Install Dependencies + +```bash +pip3 install -r requirements.txt +``` + ### Model Conversion ```bash diff --git a/models/cv/classification/mobilenet_v2/igie/README.md b/models/cv/classification/mobilenet_v2/igie/README.md index 07d75bed..193f744f 100644 --- a/models/cv/classification/mobilenet_v2/igie/README.md +++ b/models/cv/classification/mobilenet_v2/igie/README.md @@ -1,4 +1,4 @@ -# MobileNetV2 +# MobileNetV2 (IGIE) ## Model Description @@ -6,18 +6,18 @@ MobileNetV2 is an improvement on V1. Its new ideas include Linear Bottleneck and ## Model Preparation -### Install Dependencies - -```bash -pip3 install -r requirements.txt -``` - ### Prepare Resources Pretrained model: Dataset: to download the validation dataset. +### Install Dependencies + +```bash +pip3 install -r requirements.txt +``` + ### Model Conversion ```bash @@ -50,7 +50,7 @@ bash scripts/infer_mobilenet_v2_int8_performance.sh ## Model Results -Model |BatchSize |Precision |FPS |Top-1(%) |Top-5(%) --------------|-----------|----------|---------|----------|-------- -MobileNetV2 | 32 | FP16 | 6910.65 | 71.96 | 90.60 -MobileNetV2 | 32 | INT8 | 8155.362 | 71.48 | 90.47 +| Model | BatchSize | Precision | FPS | Top-1(%) | Top-5(%) | +|-------------|-----------|-----------|----------|----------|----------| +| MobileNetV2 | 32 | FP16 | 6910.65 | 71.96 | 90.60 | +| MobileNetV2 | 32 | INT8 | 8155.362 | 71.48 | 90.47 | diff --git a/models/cv/classification/mobilenet_v2/ixrt/README.md b/models/cv/classification/mobilenet_v2/ixrt/README.md index f893faa2..883b366e 100644 --- a/models/cv/classification/mobilenet_v2/ixrt/README.md +++ b/models/cv/classification/mobilenet_v2/ixrt/README.md @@ -1,4 +1,4 @@ -# MobileNetV2 +# MobileNetV2 (IxRT) ## Model Description @@ -6,18 +6,18 @@ The MobileNetV2 architecture is based on an inverted residual structure where th ## Model Preparation -### Install Dependencies - -```bash -pip3 install -r requirements.txt -``` - ### Prepare Resources Pretrained model: Download the [imagenet](https://www.image-net.org/download.php) to download the validation dataset. +### Install Dependencies + +```bash +pip3 install -r requirements.txt +``` + ### Model Conversion ```bash @@ -58,7 +58,6 @@ bash script/infer_mobilenet_v2_int8_performance.sh | ----------- | --------- | --------- | ------- | -------- | -------- | | MobileNetV2 | 32 | FP16 | 4835.19 | 0.7186 | 0.90316 | -## Referenece +## Refereneces -- [MobileNetV2](https://arxiv.org/abs/1801.04381) -- +- [Paper](https://arxiv.org/abs/1801.04381) diff --git a/models/cv/classification/mobilenet_v3/igie/README.md b/models/cv/classification/mobilenet_v3/igie/README.md index 77cd08ad..82ab6081 100644 --- a/models/cv/classification/mobilenet_v3/igie/README.md +++ b/models/cv/classification/mobilenet_v3/igie/README.md @@ -1,4 +1,4 @@ -# MobileNetV3_Small +# MobileNetV3_Small (IGIE) ## Model Description @@ -6,18 +6,18 @@ MobileNetV3_Small is a lightweight convolutional neural network architecture des ## Model Preparation -### Install Dependencies - -```bash -pip3 install -r requirements.txt -``` - ### Prepare Resources Pretrained model: Dataset: to download the validation dataset. +### Install Dependencies + +```bash +pip3 install -r requirements.txt +``` + ### Model Conversion ```bash @@ -41,6 +41,6 @@ bash scripts/infer_mobilenet_v3_fp16_performance.sh ## Model Results -Model |BatchSize |Precision |FPS |Top-1(%) |Top-5(%) -------------------|-----------|----------|---------|---------|-------- -MobileNetV3_Small | 32 | FP16 | 6837.86 | 67.612 | 87.404 +| Model | BatchSize | Precision | FPS | Top-1(%) | Top-5(%) | +|-------------------|-----------|-----------|---------|----------|----------| +| MobileNetV3_Small | 32 | FP16 | 6837.86 | 67.612 | 87.404 | diff --git a/models/cv/classification/mobilenet_v3/ixrt/README.md b/models/cv/classification/mobilenet_v3/ixrt/README.md index f044216d..cfbbf00c 100644 --- a/models/cv/classification/mobilenet_v3/ixrt/README.md +++ b/models/cv/classification/mobilenet_v3/ixrt/README.md @@ -1,4 +1,4 @@ -# MobileNetV3 +# MobileNetV3 (IxRT) ## Model Description @@ -6,6 +6,12 @@ MobileNetV3 is a convolutional neural network that is tuned to mobile phone CPUs ## Model Preparation +### Prepare Resources + +Pretrained model: + +Dataset: to download the validation dataset. + ### Install Dependencies ```bash @@ -18,12 +24,6 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Prepare Resources - -Pretrained model: - -Dataset: to download the validation dataset. - ### Model Conversion ```bash @@ -52,6 +52,6 @@ bash scripts/infer_mobilenet_v3_fp16_performance.sh ## Model Results -Model | BatchSize | Precision| FPS | Top-1(%) | Top-5(%) -------------|-----------|----------|----------|----------|-------- -MobileNetV3 | 32 | FP16 | 8464.36 | 67.62 | 87.42 +| Model | BatchSize | Precision | FPS | Top-1(%) | Top-5(%) | +|-------------|-----------|-----------|---------|----------|----------| +| MobileNetV3 | 32 | FP16 | 8464.36 | 67.62 | 87.42 | diff --git a/models/cv/classification/mobilenet_v3_large/igie/README.md b/models/cv/classification/mobilenet_v3_large/igie/README.md index 2a73312d..fc4193b0 100644 --- a/models/cv/classification/mobilenet_v3_large/igie/README.md +++ b/models/cv/classification/mobilenet_v3_large/igie/README.md @@ -1,4 +1,4 @@ -# MobileNetV3_Large +# MobileNetV3_Large (IGIE) ## Model Description @@ -6,18 +6,18 @@ MobileNetV3_Large builds upon the success of its predecessors by incorporating s ## Model Preparation -### Install Dependencies - -```bash -pip3 install -r requirements.txt -``` - ### Prepare Resources Pretrained model: Dataset: to download the validation dataset. +### Install Dependencies + +```bash +pip3 install -r requirements.txt +``` + ### Model Conversion ```bash @@ -41,6 +41,6 @@ bash scripts/infer_mobilenet_v3_large_fp16_performance.sh ## Model Results -Model |BatchSize |Precision |FPS |Top-1(%) |Top-5(%) -------------------|-----------|----------|---------|---------|-------- -MobileNetV3_Large | 32 | FP16 | 3644.08 | 74.042 | 91.303 +| Model | BatchSize | Precision | FPS | Top-1(%) | Top-5(%) | +|-------------------|-----------|-----------|---------|----------|----------| +| MobileNetV3_Large | 32 | FP16 | 3644.08 | 74.042 | 91.303 | diff --git a/models/cv/classification/mvitv2_base/igie/README.md b/models/cv/classification/mvitv2_base/igie/README.md index b2f018fb..3a3ed093 100644 --- a/models/cv/classification/mvitv2_base/igie/README.md +++ b/models/cv/classification/mvitv2_base/igie/README.md @@ -1,4 +1,4 @@ -# MViTv2-base +# MViTv2-base (IGIE) ## Model Description @@ -6,6 +6,12 @@ MViTv2_base is an efficient multi-scale vision Transformer model designed specif ## Model Preparation +### Prepare Resources + +Pretrained model: + +Dataset: to download the validation dataset. + ### Install Dependencies ```bash @@ -18,12 +24,6 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Prepare Resources - -Pretrained model: - -Dataset: to download the validation dataset. - ### Model Conversion ```bash @@ -61,4 +61,4 @@ bash scripts/infer_mvitv2_base_fp16_performance.sh ## References -MViTv2-base: +- [mmpretrain](https://github.com/open-mmlab/mmpretrain) diff --git a/models/cv/classification/regnet_x_16gf/igie/README.md b/models/cv/classification/regnet_x_16gf/igie/README.md index 84b2957c..a52c9da2 100644 --- a/models/cv/classification/regnet_x_16gf/igie/README.md +++ b/models/cv/classification/regnet_x_16gf/igie/README.md @@ -1,4 +1,4 @@ -# RegNet_x_16gf +# RegNet_x_16gf (IGIE) ## Model Description @@ -7,18 +7,18 @@ RegNet_x_16gf is a deep convolutional neural network from the RegNet family, int ## Model Preparation -### Install Dependencies - -```bash -pip3 install -r requirements.txt -``` - ### Prepare Resources Pretrained model: Dataset: to download the validation dataset. +### Install Dependencies + +```bash +pip3 install -r requirements.txt +``` + ### Model Conversion ```bash @@ -42,6 +42,6 @@ bash scripts/infer_regnet_x_16gf_fp16_performance.sh ## Model Results -Model |BatchSize |Precision |FPS |Top-1(%) |Top-5(%) -------------------|-----------|----------|---------|---------|-------- -RegNet_x_16gf | 32 | FP16 | 970.928 | 80.028 | 94.922 +| Model | BatchSize | Precision | FPS | Top-1(%) | Top-5(%) | +|---------------|-----------|-----------|---------|----------|----------| +| RegNet_x_16gf | 32 | FP16 | 970.928 | 80.028 | 94.922 | diff --git a/models/cv/classification/regnet_x_1_6gf/igie/README.md b/models/cv/classification/regnet_x_1_6gf/igie/README.md index 4d4e84bc..4e136c85 100644 --- a/models/cv/classification/regnet_x_1_6gf/igie/README.md +++ b/models/cv/classification/regnet_x_1_6gf/igie/README.md @@ -1,4 +1,4 @@ -# RegNet_x_1_6gf +# RegNet_x_1_6gf (IGIE) ## Model Description @@ -6,18 +6,18 @@ RegNet is a family of models designed for image classification tasks, as describ ## Model Preparation -### Install Dependencies - -```bash -pip3 install -r requirements.txt -``` - ### Prepare Resources Pretrained model: Dataset: to download the validation dataset. +### Install Dependencies + +```bash +pip3 install -r requirements.txt +``` + ### Model Conversion ```bash @@ -41,6 +41,6 @@ bash scripts/infer_regnet_x_1_6gf_fp16_performance.sh ## Model Results -Model |BatchSize |Precision |FPS |Top-1(%) |Top-5(%) -------------------|-----------|----------|---------|---------|-------- -RegNet_x_1_6gf | 32 | FP16 | 487.749 | 79.303 | 94.624 +| Model | BatchSize | Precision | FPS | Top-1(%) | Top-5(%) | +|----------------|-----------|-----------|---------|----------|----------| +| RegNet_x_1_6gf | 32 | FP16 | 487.749 | 79.303 | 94.624 | diff --git a/models/cv/classification/regnet_y_1_6gf/igie/README.md b/models/cv/classification/regnet_y_1_6gf/igie/README.md index 35244009..602a2afd 100644 --- a/models/cv/classification/regnet_y_1_6gf/igie/README.md +++ b/models/cv/classification/regnet_y_1_6gf/igie/README.md @@ -1,4 +1,4 @@ -# RegNet_y_1_6gf +# RegNet_y_1_6gf (IGIE) ## Model Description @@ -6,18 +6,18 @@ RegNet is a family of models designed for image classification tasks, as describ ## Model Preparation -### Install Dependencies - -```bash -pip3 install -r requirements.txt -``` - ### Prepare Resources Pretrained model: Dataset: to download the validation dataset. +### Install Dependencies + +```bash +pip3 install -r requirements.txt +``` + ### Model Conversion ```bash diff --git a/models/cv/classification/repvgg/igie/README.md b/models/cv/classification/repvgg/igie/README.md index 9ff0b997..80c5bf19 100644 --- a/models/cv/classification/repvgg/igie/README.md +++ b/models/cv/classification/repvgg/igie/README.md @@ -1,4 +1,4 @@ -# RepVGG +# RepVGG (IGIE) ## Model Description @@ -6,6 +6,12 @@ RepVGG is an innovative convolutional neural network architecture that combines ## Model Preparation +### Prepare Resources + +Pretrained model: + +Dataset: to download the validation dataset. + ### Install Dependencies ```bash @@ -18,12 +24,6 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Prepare Resources - -Pretrained model: - -Dataset: to download the validation dataset. - ### Model Conversion ```bash @@ -58,4 +58,4 @@ bash scripts/infer_repvgg_fp16_performance.sh ## References -RepVGG: +- [mmpretrain](https://github.com/open-mmlab/mmpretrain) diff --git a/models/cv/classification/repvgg/ixrt/README.md b/models/cv/classification/repvgg/ixrt/README.md index f920d3b8..bb046c5d 100644 --- a/models/cv/classification/repvgg/ixrt/README.md +++ b/models/cv/classification/repvgg/ixrt/README.md @@ -1,4 +1,4 @@ -# RepVGG +# RepVGG (IxRT) ## Model Description @@ -7,6 +7,10 @@ It was developed by researchers at the University of Oxford and introduced in th ## Model Preparation +### Prepare Resources + +Dataset: to download the validation dataset. + ### Install Dependencies ```bash @@ -19,10 +23,6 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Prepare Resources - -Dataset: to download the validation dataset. - ### Model Conversion ```bash diff --git a/models/cv/classification/res2net50/igie/README.md b/models/cv/classification/res2net50/igie/README.md index aad8a6ae..6f4cb1a3 100644 --- a/models/cv/classification/res2net50/igie/README.md +++ b/models/cv/classification/res2net50/igie/README.md @@ -1,4 +1,4 @@ -# Res2Net50 +# Res2Net50 (IGIE) ## Model Description @@ -6,6 +6,12 @@ Res2Net50 is a convolutional neural network architecture that introduces the con ## Model Preparation +### Prepare Resources + +Pretrained model: + +Dataset: to download the validation dataset. + ### Install Dependencies ```bash @@ -18,12 +24,6 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Prepare Resources - -Pretrained model: - -Dataset: to download the validation dataset. - ### Model Conversion ```bash @@ -55,10 +55,10 @@ bash scripts/infer_res2net50_fp16_performance.sh ## Model Results -Model |BatchSize |Precision |FPS |Top-1(%) |Top-5(%) -----------|-----------|----------|----------|----------|-------- -Res2Net50 | 32 | FP16 | 1641.961 | 78.139 | 93.826 +| Model | BatchSize | Precision | FPS | Top-1(%) | Top-5(%) | +|-----------|-----------|-----------|----------|----------|----------| +| Res2Net50 | 32 | FP16 | 1641.961 | 78.139 | 93.826 | ## References -Res2Net50: +- [mmpretrain](https://github.com/open-mmlab/mmpretrain) diff --git a/models/cv/classification/res2net50/ixrt/README.md b/models/cv/classification/res2net50/ixrt/README.md index 05f3fbc2..9d97a31a 100644 --- a/models/cv/classification/res2net50/ixrt/README.md +++ b/models/cv/classification/res2net50/ixrt/README.md @@ -1,4 +1,4 @@ -# Res2Net50 +# Res2Net50 (IxRT) ## Model Description @@ -6,6 +6,12 @@ A novel building block for CNNs, namely Res2Net, by constructing hierarchical re ## Model Preparation +### Prepare Resources + +Pretrained model: + +Dataset: to download the validation dataset. + ### Install Dependencies ```bash @@ -18,12 +24,6 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Prepare Resources - -Pretrained model: - -Dataset: to download the validation dataset. - ### Model Conversion ```bash @@ -61,7 +61,7 @@ bash scripts/infer_res2net50_int8_performance.sh ## Model Results -Model |BatchSize |Precision |FPS |Top-1(%) |Top-5(%) -----------|-----------|----------|----------|---------|-------- -Res2Net50 | 32 | FP16 | 921.37 | 77.92 | 93.71 -Res2Net50 | 32 | INT8 | 1933.74 | 77.80 | 93.62 +| Model | BatchSize | Precision | FPS | Top-1(%) | Top-5(%) | +|-----------|-----------|-----------|---------|----------|----------| +| Res2Net50 | 32 | FP16 | 921.37 | 77.92 | 93.71 | +| Res2Net50 | 32 | INT8 | 1933.74 | 77.80 | 93.62 | diff --git a/models/cv/classification/resnest50/igie/README.md b/models/cv/classification/resnest50/igie/README.md index c18f7bcb..7b9ddc20 100644 --- a/models/cv/classification/resnest50/igie/README.md +++ b/models/cv/classification/resnest50/igie/README.md @@ -1,4 +1,4 @@ -# ResNeSt50 +# ResNeSt50 (IGIE) ## Model Description @@ -6,6 +6,12 @@ ResNeSt50 is a deep convolutional neural network model based on the ResNeSt arch ## Model Preparation +### Prepare Resources + +Pretrained model: + +Dataset: to download the validation dataset. + ### Install Dependencies ```bash @@ -18,12 +24,6 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Prepare Resources - -Pretrained model: - -Dataset: to download the validation dataset. - ### Model Conversion ```bash @@ -52,10 +52,10 @@ bash scripts/infer_resnest50_fp16_performance.sh ## Model Results -Model |BatchSize |Precision |FPS |Top-1(%) |Top-5(%) -----------|-----------|----------|----------|----------|-------- -ResNeSt50 | 32 | FP16 | 344.453 | 80.93 | 95.347 +| Model | BatchSize | Precision | FPS | Top-1(%) | Top-5(%) | +|-----------|-----------|-----------|---------|----------|----------| +| ResNeSt50 | 32 | FP16 | 344.453 | 80.93 | 95.347 | ## References -ResNeSt50: +- [ResNeSt](https://github.com/zhanghang1989/ResNeSt) diff --git a/models/cv/classification/resnet101/igie/README.md b/models/cv/classification/resnet101/igie/README.md index 7c63ec94..43f1c559 100644 --- a/models/cv/classification/resnet101/igie/README.md +++ b/models/cv/classification/resnet101/igie/README.md @@ -1,4 +1,4 @@ -# ResNet101 +# ResNet101 (IGIE) ## Model Description @@ -6,18 +6,18 @@ ResNet101 is a convolutional neural network architecture that belongs to the Res ## Model Preparation -### Install Dependencies - -```bash -pip3 install -r requirements.txt -``` - ### Prepare Resources Pretrained model: Dataset: to download the validation dataset. +### Install Dependencies + +```bash +pip3 install -r requirements.txt +``` + ### Model Conversion ```bash @@ -50,7 +50,7 @@ bash scripts/infer_resnet101_int8_performance.sh ## Model Results -Model |BatchSize |Precision |FPS |Top-1(%) |Top-5(%) -----------|-----------|----------|----------|----------|-------- -ResNet101 | 32 | FP16 | 2507.074 | 77.331 | 93.520 -ResNet101 | 32 | INT8 | 5458.890 | 76.719 | 93.348 +| Model | BatchSize | Precision | FPS | Top-1(%) | Top-5(%) | +|-----------|-----------|-----------|----------|----------|----------| +| ResNet101 | 32 | FP16 | 2507.074 | 77.331 | 93.520 | +| ResNet101 | 32 | INT8 | 5458.890 | 76.719 | 93.348 | diff --git a/models/cv/classification/resnet101/ixrt/README.md b/models/cv/classification/resnet101/ixrt/README.md index a11341db..5c278747 100644 --- a/models/cv/classification/resnet101/ixrt/README.md +++ b/models/cv/classification/resnet101/ixrt/README.md @@ -1,4 +1,4 @@ -# Resnet101 +# Resnet101 (IxRT) ## Model Description @@ -6,6 +6,10 @@ ResNet-101 is a variant of the ResNet (Residual Network) architecture, and it be ## Model Preparation +### Prepare Resources + +Dataset: to download the validation dataset. + ### Install Dependencies ```bash @@ -18,10 +22,6 @@ apt install -y libgl1-mesa-glx pip3 install -r reuirements.txt ``` -### Prepare Resources - -Dataset: to download the validation dataset. - ### Model Conversion ```bash @@ -59,7 +59,7 @@ bash scripts/infer_resnet101_int8_performance.sh ## Model Results -Model |BatchSize |Precision |FPS |Top-1(%) |Top-5(%) -----------|-----------|----------|---------|----------|-------- -Resnet101 | 32 | FP16 | 2592.04 | 77.36 | 93.56 -Resnet101 | 32 | INT8 | 5760.69 | 76.88 | 93.43 +| Model | BatchSize | Precision | FPS | Top-1(%) | Top-5(%) | +|-----------|-----------|-----------|---------|----------|----------| +| Resnet101 | 32 | FP16 | 2592.04 | 77.36 | 93.56 | +| Resnet101 | 32 | INT8 | 5760.69 | 76.88 | 93.43 | diff --git a/models/cv/classification/resnet152/igie/README.md b/models/cv/classification/resnet152/igie/README.md index 774ee6aa..173e1f38 100644 --- a/models/cv/classification/resnet152/igie/README.md +++ b/models/cv/classification/resnet152/igie/README.md @@ -1,4 +1,4 @@ -# ResNet152 +# ResNet152 (IGIE) ## Model Description @@ -6,18 +6,18 @@ ResNet152 is a convolutional neural network architecture that is part of the Res ## Model Preparation -### Install Dependencies - -```bash -pip3 install -r requirements.txt -``` - ### Prepare Resources Pretrained model: Dataset: to download the validation dataset. +### Install Dependencies + +```bash +pip3 install -r requirements.txt +``` + ### Model Conversion ```bash @@ -50,7 +50,7 @@ bash scripts/infer_resnet152_int8_performance.sh ## Model Results -Model |BatchSize |Precision |FPS |Top-1(%) |Top-5(%) -----------|-----------|----------|----------|----------|-------- -ResNet152 | 32 | FP16 | 1768.348 | 78.285 | 94.022 -ResNet152 | 32 | INT8 | 3864.913 | 77.637 | 93.728 +| Model | BatchSize | Precision | FPS | Top-1(%) | Top-5(%) | +|-----------|-----------|-----------|----------|----------|----------| +| ResNet152 | 32 | FP16 | 1768.348 | 78.285 | 94.022 | +| ResNet152 | 32 | INT8 | 3864.913 | 77.637 | 93.728 | diff --git a/models/cv/classification/resnet18/igie/README.md b/models/cv/classification/resnet18/igie/README.md index 6187c315..e6373ba2 100644 --- a/models/cv/classification/resnet18/igie/README.md +++ b/models/cv/classification/resnet18/igie/README.md @@ -1,4 +1,4 @@ -# ResNet18 +# ResNet18 (IGIE) ## Model Description @@ -6,18 +6,18 @@ ResNet-18 is a relatively compact deep neural network.The ResNet-18 architecture ## Model Preparation -### Install Dependencies - -```bash -pip3 install -r requirements.txt -``` - ### Prepare Resources Pretrained model: Dataset: to download the validation dataset. +### Install Dependencies + +```bash +pip3 install -r requirements.txt +``` + ### Model Conversion ```bash @@ -50,7 +50,7 @@ bash scripts/infer_resnet18_int8_performance.sh ## Model Results -Model |BatchSize |Precision |FPS |Top-1(%) |Top-5(%) ----------|-----------|----------|----------|----------|-------- -ResNet18 | 32 | FP16 | 9592.98 | 69.77 | 89.09 -ResNet18 | 32 | INT8 | 21314.55 | 69.53 | 88.97 +| Model | BatchSize | Precision | FPS | Top-1(%) | Top-5(%) | +|----------|-----------|-----------|----------|----------|----------| +| ResNet18 | 32 | FP16 | 9592.98 | 69.77 | 89.09 | +| ResNet18 | 32 | INT8 | 21314.55 | 69.53 | 88.97 | diff --git a/models/cv/classification/resnet18/ixrt/README.md b/models/cv/classification/resnet18/ixrt/README.md index c385ac35..1a69e474 100644 --- a/models/cv/classification/resnet18/ixrt/README.md +++ b/models/cv/classification/resnet18/ixrt/README.md @@ -1,4 +1,4 @@ -# Resnet18 +# ResNet18 (IxRT) ## Model Description @@ -6,6 +6,12 @@ ResNet-18 is a variant of the ResNet (Residual Network) architecture, which was ## Model Preparation +### Prepare Resources + +Pretrained model: + +Dataset: to download the validation dataset. + ### Install Dependencies ```bash @@ -18,12 +24,6 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Prepare Resources - -Pretrained model: - -Dataset: to download the validation dataset. - ### Model Conversion ```bash @@ -61,7 +61,7 @@ bash scripts/infer_resnet18_int8_performance.sh ## Model Results -Model |BatchSize |Precision |FPS |Top-1(%) |Top-5(%) ----------|-----------|----------|----------|----------|-------- -Resnet18 | 32 | FP16 | 9592.98 | 69.77 | 89.09 -Resnet18 | 32 | INT8 | 21314.55 | 69.53 | 88.97 +| Model | BatchSize | Precision | FPS | Top-1(%) | Top-5(%) | +|----------|-----------|-----------|----------|----------|----------| +| Resnet18 | 32 | FP16 | 9592.98 | 69.77 | 89.09 | +| Resnet18 | 32 | INT8 | 21314.55 | 69.53 | 88.97 | diff --git a/models/cv/classification/resnet34/ixrt/README.md b/models/cv/classification/resnet34/ixrt/README.md index 8ab2b34a..b421869a 100644 --- a/models/cv/classification/resnet34/ixrt/README.md +++ b/models/cv/classification/resnet34/ixrt/README.md @@ -1,4 +1,4 @@ -# ResNet34 +# ResNet34 (IxRT) ## Model Description @@ -6,6 +6,10 @@ Residual Networks, or ResNets, learn residual functions with reference to the la ## Model Preparation +### Prepare Resources + +Dataset: to download the validation dataset. + ### Install Dependencies ```bash @@ -18,10 +22,6 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Prepare Resources - -Dataset: to download the validation dataset. - ### Model Conversion ```bash @@ -59,7 +59,7 @@ bash scripts/infer_resnet34_int8_performance.sh ## Model Results -Model |BatchSize |Precision |FPS |Top-1(%) |Top-5(%) ----------|-----------|----------|----------|----------|-------- -ResNet34 | 32 | FP16 | 6179.47 | 73.30 | 91.42 -ResNet34 | 32 | INT8 | 11256.36 | 73.13 | 91.34 +| Model | BatchSize | Precision | FPS | Top-1(%) | Top-5(%) | +|----------|-----------|-----------|----------|----------|----------| +| ResNet34 | 32 | FP16 | 6179.47 | 73.30 | 91.42 | +| ResNet34 | 32 | INT8 | 11256.36 | 73.13 | 91.34 | diff --git a/models/cv/classification/resnet50/igie/README.md b/models/cv/classification/resnet50/igie/README.md index 6820f2cb..57347150 100644 --- a/models/cv/classification/resnet50/igie/README.md +++ b/models/cv/classification/resnet50/igie/README.md @@ -1,4 +1,4 @@ -# ResNet50 +# ResNet50 (IGIE) ## Model Description @@ -6,18 +6,18 @@ ResNet-50 is a convolutional neural network architecture that belongs to the Res ## Model Preparation -### Install Dependencies - -```bash -pip3 install -r requirements.txt -``` - ### Prepare Resources Pretrained model: Dataset: to download the validation dataset. +### Install Dependencies + +```bash +pip3 install -r requirements.txt +``` + ### Model Conversion ```bash @@ -50,7 +50,7 @@ bash scripts/infer_resnet50_int8_performance.sh ## Model Results -Model |BatchSize |Precision |FPS |Top-1(%) |Top-5(%) ----------|-----------|----------|----------|----------|-------- -ResNet50 | 32 | FP16 | 4417.29 | 76.11 | 92.85 -ResNet50 | 32 | INT8 | 8628.61 | 75.72 | 92.71 +| Model | BatchSize | Precision | FPS | Top-1(%) | Top-5(%) | +|----------|-----------|-----------|---------|----------|----------| +| ResNet50 | 32 | FP16 | 4417.29 | 76.11 | 92.85 | +| ResNet50 | 32 | INT8 | 8628.61 | 75.72 | 92.71 | diff --git a/models/cv/classification/resnet50/ixrt/README.md b/models/cv/classification/resnet50/ixrt/README.md index c9e1ae9c..df3a0893 100644 --- a/models/cv/classification/resnet50/ixrt/README.md +++ b/models/cv/classification/resnet50/ixrt/README.md @@ -1,4 +1,4 @@ -# ResNet50 +# ResNet50 (IxRT) ## Model Description @@ -6,6 +6,12 @@ Residual Networks, or ResNets, learn residual functions with reference to the la ## Model Preparation +### Prepare Resources + +Pretrained model: + +Dataset: to download the validation dataset. + ### Install Dependencies ```bash @@ -18,12 +24,6 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Prepare Resources - -Pretrained model: - -Dataset: to download the validation dataset. - ### Model Conversion ```bash @@ -61,6 +61,6 @@ bash scripts/infer_resnet50_int8_performance.sh ## Model Results | Model | BatchSize | Precision | FPS | Top-1(%) | Top-5(%) | -| -------- | --------- | --------- | ------- | -------- | -------- | +|----------|-----------|-----------|---------|----------|----------| | ResNet50 | 32 | FP16 | 4077.58 | 0.76158 | 0.92872 | | ResNet50 | 32 | INT8 | 9113.07 | 0.74516 | 0.9287 | diff --git a/models/cv/classification/resnetv1d50/igie/README.md b/models/cv/classification/resnetv1d50/igie/README.md index a5d42f87..e8b669da 100644 --- a/models/cv/classification/resnetv1d50/igie/README.md +++ b/models/cv/classification/resnetv1d50/igie/README.md @@ -1,4 +1,4 @@ -# ResNetV1D50 +# ResNetV1D50 (IGIE) ## Model Description @@ -6,6 +6,12 @@ ResNetV1D50 is an enhanced version of ResNetV1-50 that incorporates changes like ## Model Preparation +### Prepare Resources + +Pretrained model: + +Dataset: to download the validation dataset. + ### Install Dependencies ```bash @@ -18,12 +24,6 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Prepare Resources - -Pretrained model: - -Dataset: to download the validation dataset. - ### Model Conversion ```bash @@ -58,4 +58,4 @@ bash scripts/infer_resnetv1d50_fp16_performance.sh ## References -ResNetV1D50: +- [mmpretrain](https://github.com/open-mmlab/mmpretrain) diff --git a/models/cv/classification/resnetv1d50/ixrt/README.md b/models/cv/classification/resnetv1d50/ixrt/README.md index d333342f..954ff13a 100644 --- a/models/cv/classification/resnetv1d50/ixrt/README.md +++ b/models/cv/classification/resnetv1d50/ixrt/README.md @@ -1,4 +1,4 @@ -# ResNetV1D50 +# ResNetV1D50 (IxRT) ## Model Description @@ -6,6 +6,10 @@ Residual Networks, or ResNets, learn residual functions with reference to the la ## Model Preparation +### Prepare Resources + +Dataset: to download the validation dataset. + ### Install Dependencies ```bash @@ -18,10 +22,6 @@ apt install -y libgl1-mesa-glx pip3 install -r requirments.txt ``` -### Prepare Resources - -Dataset: to download the validation dataset. - ### Model Conversion ```bash diff --git a/models/cv/classification/resnext101_32x8d/igie/README.md b/models/cv/classification/resnext101_32x8d/igie/README.md index fad1347d..de622298 100644 --- a/models/cv/classification/resnext101_32x8d/igie/README.md +++ b/models/cv/classification/resnext101_32x8d/igie/README.md @@ -1,4 +1,4 @@ -# ResNext101_32x8d +# ResNext101_32x8d (IGIE) ## Model Description @@ -6,18 +6,18 @@ ResNeXt101_32x8d is a deep convolutional neural network introduced in the paper ## Model Preparation -### Install Dependencies - -```bash -pip3 install -r requirements.txt -``` - ### Prepare Resources Pretrained model: Dataset: to download the validation dataset. +### Install Dependencies + +```bash +pip3 install -r requirements.txt +``` + ### Model Conversion ```bash diff --git a/models/cv/classification/resnext101_64x4d/igie/README.md b/models/cv/classification/resnext101_64x4d/igie/README.md index 4504632c..5f9d62f0 100644 --- a/models/cv/classification/resnext101_64x4d/igie/README.md +++ b/models/cv/classification/resnext101_64x4d/igie/README.md @@ -1,4 +1,4 @@ -# ResNext101_64x4d +# ResNext101_64x4d (IGIE) ## Model Description @@ -6,18 +6,18 @@ The ResNeXt101_64x4d is a deep learning model based on the deep residual network ## Model Preparation -### Install Dependencies - -```bash -pip3 install -r requirements.txt -``` - ### Prepare Resources Pretrained model: Dataset: to download the validation dataset. +### Install Dependencies + +```bash +pip3 install -r requirements.txt +``` + ### Model Conversion ```bash diff --git a/models/cv/classification/resnext50_32x4d/igie/README.md b/models/cv/classification/resnext50_32x4d/igie/README.md index 0ec8da3c..bb6532b9 100644 --- a/models/cv/classification/resnext50_32x4d/igie/README.md +++ b/models/cv/classification/resnext50_32x4d/igie/README.md @@ -1,4 +1,4 @@ -# ResNext50_32x4d +# ResNext50_32x4d (IGIE) ## Model Description @@ -6,18 +6,18 @@ The ResNeXt50_32x4d model is a convolutional neural network architecture designe ## Model Preparation -### Install Dependencies - -```bash -pip3 install -r requirements.txt -``` - ### Prepare Resources Pretrained model: Dataset: to download the validation dataset. +### Install Dependencies + +```bash +pip3 install -r requirements.txt +``` + ### Model Conversion ```bash @@ -41,6 +41,6 @@ bash scripts/infer_resnext50_32x4d_fp16_performance.sh ## Model Results -Model |BatchSize |Precision |FPS |Top-1(%) |Top-5(%) -----------------|-----------|----------|---------|----------|-------- -resnext50_32x4d | 32 | FP16 | 273.20 | 77.601 | 93.656 +| Model | BatchSize | Precision | FPS | Top-1(%) | Top-5(%) | +|-----------------|-----------|-----------|--------|----------|----------| +| ResNext50_32x4d | 32 | FP16 | 273.20 | 77.601 | 93.656 | diff --git a/models/cv/classification/resnext50_32x4d/ixrt/README.md b/models/cv/classification/resnext50_32x4d/ixrt/README.md index 9a2fc061..a9782585 100644 --- a/models/cv/classification/resnext50_32x4d/ixrt/README.md +++ b/models/cv/classification/resnext50_32x4d/ixrt/README.md @@ -1,4 +1,4 @@ -# ResNext50_32x4d +# ResNext50_32x4d (IxRT) ## Model Description @@ -6,18 +6,18 @@ The ResNeXt50_32x4d model is a convolutional neural network architecture designe ## Model Preparation -### Install Dependencies - -```bash -pip3 install -r requirements.txt -``` - ### Prepare Resources Pretrained model: Dataset: to download the validation dataset. +### Install Dependencies + +```bash +pip3 install -r requirements.txt +``` + ### Model Conversion ```bash diff --git a/models/cv/classification/seresnet50/igie/README.md b/models/cv/classification/seresnet50/igie/README.md index a89fdefe..b2b736fa 100644 --- a/models/cv/classification/seresnet50/igie/README.md +++ b/models/cv/classification/seresnet50/igie/README.md @@ -1,4 +1,4 @@ -# SEResNet50 +# SEResNet50 (IGIE) ## Model Description @@ -6,6 +6,12 @@ SEResNet50 is an enhanced version of the ResNet50 network integrated with Squeez ## Model Preparation +### Prepare Resources + +Pretrained model: + +Dataset: to download the validation dataset. + ### Install Dependencies ```bash @@ -18,12 +24,6 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Prepare Resources - -Pretrained model: - -Dataset: to download the validation dataset. - ### Model Conversion ```bash @@ -32,7 +32,6 @@ git clone -b v0.24.0 https://github.com/open-mmlab/mmpretrain.git # export onnx model python3 export.py --cfg mmpretrain/configs/seresnet/seresnet50_8xb32_in1k.py --weight se-resnet50_batch256_imagenet_20200804-ae206104.pth --output seresnet50.onnx - ``` ## Model Inference @@ -58,4 +57,4 @@ bash scripts/infer_seresnet_fp16_performance.sh ## References -SE_ResNet50: +- [mmpretrain](https://github.com/open-mmlab/mmpretrain) diff --git a/models/cv/classification/shufflenet_v1/ixrt/README.md b/models/cv/classification/shufflenet_v1/ixrt/README.md index b863e00a..2e4b6686 100644 --- a/models/cv/classification/shufflenet_v1/ixrt/README.md +++ b/models/cv/classification/shufflenet_v1/ixrt/README.md @@ -1,4 +1,4 @@ -# ShuffleNetV1 +# ShuffleNetV1 (IxRT) ## Model Description @@ -7,6 +7,12 @@ It uses techniques such as deep separable convolution and channel shuffle to red ## Model Preparation +### Prepare Resources + +Pretrained model: + +Dataset: to download the validation dataset. + ### Install Dependencies ```bash @@ -19,12 +25,6 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Prepare Resources - -Pretrained model: - -Dataset: to download the validation dataset. - ### Model Conversion ```bash @@ -59,6 +59,6 @@ bash scripts/infer_shufflenet_v1_fp16_performance.sh ## Model Results -Model |BatchSize |Precision |FPS |Top-1(%) |Top-5(%) --------------|-----------|----------|---------|----------|-------- -ShuffleNetV1 | 32 | FP16 | 3619.89 | 66.17 | 86.54 +| Model | BatchSize | Precision | FPS | Top-1(%) | Top-5(%) | +|--------------|-----------|-----------|---------|----------|----------| +| ShuffleNetV1 | 32 | FP16 | 3619.89 | 66.17 | 86.54 | diff --git a/models/cv/classification/shufflenetv2_x0_5/igie/README.md b/models/cv/classification/shufflenetv2_x0_5/igie/README.md index 068b944c..def9e304 100644 --- a/models/cv/classification/shufflenetv2_x0_5/igie/README.md +++ b/models/cv/classification/shufflenetv2_x0_5/igie/README.md @@ -1,4 +1,4 @@ -# ShuffleNetV2_x0_5 +# ShuffleNetV2_x0_5 (IGIE) ## Model Description @@ -6,18 +6,18 @@ ShuffleNetV2_x0_5 is a lightweight convolutional neural network architecture des ## Model Preparation -### Install Dependencies - -```bash -pip3 install -r requirements.txt -``` - ### Prepare Resources Pretrained model: Dataset: to download the validation dataset. +### Install Dependencies + +```bash +pip3 install -r requirements.txt +``` + ### Model Conversion ```bash @@ -41,6 +41,6 @@ bash scripts/infer_shufflenetv2_x0_5_fp16_performance.sh ## Model Results -Model |BatchSize |Precision |FPS |Top-1(%) |Top-5(%) -------------------|-----------|----------|----------|----------|-------- -ShuffleNetV2_x0_5 | 32 | FP16 | 11677.55 | 60.501 | 81.702 +| Model | BatchSize | Precision | FPS | Top-1(%) | Top-5(%) | +|-------------------|-----------|-----------|----------|----------|----------| +| ShuffleNetV2_x0_5 | 32 | FP16 | 11677.55 | 60.501 | 81.702 | diff --git a/models/cv/classification/shufflenetv2_x1_0/igie/README.md b/models/cv/classification/shufflenetv2_x1_0/igie/README.md index 20586720..15243248 100644 --- a/models/cv/classification/shufflenetv2_x1_0/igie/README.md +++ b/models/cv/classification/shufflenetv2_x1_0/igie/README.md @@ -1,4 +1,4 @@ -# ShuffleNetV2_x1_0 +# ShuffleNetV2_x1_0 (IGIE) ## Model Description @@ -6,18 +6,18 @@ ShuffleNet V2_x1_0 is an efficient convolutional neural network (CNN) architectu ## Model Preparation -### Install Dependencies - -```bash -pip3 install -r requirements.txt -``` - ### Prepare Resources Pretrained model: Dataset: to download the validation dataset. +### Install Dependencies + +```bash +pip3 install -r requirements.txt +``` + ### Model Conversion ```bash diff --git a/models/cv/classification/shufflenetv2_x1_5/igie/README.md b/models/cv/classification/shufflenetv2_x1_5/igie/README.md index 7e6dfb38..a1ec634d 100644 --- a/models/cv/classification/shufflenetv2_x1_5/igie/README.md +++ b/models/cv/classification/shufflenetv2_x1_5/igie/README.md @@ -1,4 +1,4 @@ -# ShuffleNetV2_x1_5 +# ShuffleNetV2_x1_5 (IGIE) ## Model Description @@ -6,18 +6,18 @@ ShuffleNetV2_x1_5 is a lightweight convolutional neural network specifically des ## Model Preparation -### Install Dependencies - -```bash -pip3 install -r requirements.txt -``` - ### Prepare Resources Pretrained model: Dataset: to download the validation dataset. +### Install Dependencies + +```bash +pip3 install -r requirements.txt +``` + ### Model Conversion ```bash diff --git a/models/cv/classification/shufflenetv2_x2_0/igie/README.md b/models/cv/classification/shufflenetv2_x2_0/igie/README.md index 51e4222e..009b4aba 100644 --- a/models/cv/classification/shufflenetv2_x2_0/igie/README.md +++ b/models/cv/classification/shufflenetv2_x2_0/igie/README.md @@ -1,4 +1,4 @@ -# ShuffleNetV2_x2_0 +# ShuffleNetV2_x2_0 (IGIE) ## Model Description @@ -6,18 +6,18 @@ ShuffleNetV2_x2_0 is a lightweight convolutional neural network introduced in th ## Model Preparation -### Install Dependencies - -```bash -pip3 install -r requirements.txt -``` - ### Prepare Resources Pretrained model: Dataset: to download the validation dataset. +### Install Dependencies + +```bash +pip3 install -r requirements.txt +``` + ### Model Conversion ```bash diff --git a/models/cv/classification/squeezenet_v1_0/igie/README.md b/models/cv/classification/squeezenet_v1_0/igie/README.md index 8cb0dd5b..411abc62 100644 --- a/models/cv/classification/squeezenet_v1_0/igie/README.md +++ b/models/cv/classification/squeezenet_v1_0/igie/README.md @@ -1,4 +1,4 @@ -# SqueezeNet1_0 +# SqueezeNet1_0 (IGIE) ## Model Description @@ -6,18 +6,18 @@ SqueezeNet1_0 is a lightweight convolutional neural network introduced in the pa ## Model Preparation -### Install Dependencies - -```bash -pip3 install -r requirements.txt -``` - ### Prepare Resources Pretrained model: Dataset: to download the validation dataset. +### Install Dependencies + +```bash +pip3 install -r requirements.txt +``` + ### Model Conversion ```bash @@ -41,6 +41,6 @@ bash scripts/infer_squeezenet_v1_0_fp16_performance.sh ## Model Results -Model |BatchSize |Precision |FPS |Top-1(%) |Top-5(%) -----------------|-----------|----------|----------|----------|-------- -Squeezenet_v1_0 | 32 | FP16 | 7777.50 | 58.08 | 80.39 +| Model | BatchSize | Precision | FPS | Top-1(%) | Top-5(%) | +|-----------------|-----------|-----------|---------|----------|----------| +| Squeezenet_v1_0 | 32 | FP16 | 7777.50 | 58.08 | 80.39 | diff --git a/models/cv/classification/squeezenet_v1_0/ixrt/README.md b/models/cv/classification/squeezenet_v1_0/ixrt/README.md index c2180f7b..bab185ee 100644 --- a/models/cv/classification/squeezenet_v1_0/ixrt/README.md +++ b/models/cv/classification/squeezenet_v1_0/ixrt/README.md @@ -1,4 +1,4 @@ -# SqueezeNet 1.0 +# SqueezeNet 1.0 (IxRT) ## Model Description @@ -8,6 +8,12 @@ It was developed by researchers at DeepScale and released in 2016. ## Model Preparation +### Prepare Resources + +Pretrained model: + +Dataset: to download the validation dataset. + ### Install Dependencies ```bash @@ -20,12 +26,6 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Prepare Resources - -Pretrained model: - -Dataset: to download the validation dataset. - ### Model Conversion ```bash @@ -63,7 +63,7 @@ bash scripts/infer_squeezenet_v1_0_int8_performance.sh ## Model Results -Model |BatchSize |Precision |FPS |Top-1(%) |Top-5(%) ----------------|-----------|----------|---------|----------|-------- -SqueezeNet 1.0 | 32 | FP16 | 7740.26 | 58.07 | 80.43 -SqueezeNet 1.0 | 32 | INT8 | 8871.93 | 55.10 | 79.21 +| Model | BatchSize | Precision | FPS | Top-1(%) | Top-5(%) | +|----------------|-----------|-----------|---------|----------|----------| +| SqueezeNet 1.0 | 32 | FP16 | 7740.26 | 58.07 | 80.43 | +| SqueezeNet 1.0 | 32 | INT8 | 8871.93 | 55.10 | 79.21 | diff --git a/models/cv/classification/squeezenet_v1_1/ixrt/README.md b/models/cv/classification/squeezenet_v1_1/ixrt/README.md index c3678a40..477c5f8b 100644 --- a/models/cv/classification/squeezenet_v1_1/ixrt/README.md +++ b/models/cv/classification/squeezenet_v1_1/ixrt/README.md @@ -1,4 +1,4 @@ -# SqueezeNet 1.1 +# SqueezeNet 1.1 (IxRT) ## Model Description @@ -8,6 +8,12 @@ It was developed by researchers at DeepScale and released in 2016. ## Model Preparation +### Prepare Resources + +Pretrained model: + +Dataset: to download the validation dataset. + ### Install Dependencies ```bash @@ -20,12 +26,6 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Prepare Resources - -Pretrained model: - -Dataset: to download the validation dataset. - ### Model Conversion ```bash diff --git a/models/cv/classification/svt_base/igie/README.md b/models/cv/classification/svt_base/igie/README.md index 30739d9a..83da0b7c 100644 --- a/models/cv/classification/svt_base/igie/README.md +++ b/models/cv/classification/svt_base/igie/README.md @@ -1,4 +1,4 @@ -# SVT Base +# SVT Base (IGIE) ## Model Description @@ -6,6 +6,12 @@ SVT Base is a mid-sized variant of the Sparse Vision Transformer (SVT) series, d ## Model Preparation +### Prepare Resources + +Pretrained model: + +Dataset: to download the validation dataset. + ### Install Dependencies ```bash @@ -18,12 +24,6 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Prepare Resources - -Pretrained model: - -Dataset: to download the validation dataset. - ### Model Conversion ```bash @@ -60,4 +60,4 @@ bash scripts/infer_svt_base_fp16_performance.sh ## References -SVT Base: +- [mmpretrain](https://github.com/open-mmlab/mmpretrain) diff --git a/models/cv/classification/swin_transformer/igie/README.md b/models/cv/classification/swin_transformer/igie/README.md index 17a5b3e9..6eaac7d9 100644 --- a/models/cv/classification/swin_transformer/igie/README.md +++ b/models/cv/classification/swin_transformer/igie/README.md @@ -1,4 +1,4 @@ -# Swin Transformer +# Swin Transformer (IGIE) ## Model Description @@ -6,12 +6,6 @@ Swin Transformer is a pioneering neural network architecture that introduces a n ## Model Preparation -### Install Dependencies - -```bash -pip3 install -r requirements.txt -``` - ### Prepare Resources Pretrained model: @@ -23,6 +17,12 @@ git clone https://huggingface.co/microsoft/swin-tiny-patch4-window7-224 swin-tin Dataset: to download the validation dataset. +### Install Dependencies + +```bash +pip3 install -r requirements.txt +``` + ### Model Conversion ```bash @@ -49,6 +49,6 @@ bash scripts/infer_swin_transformer_fp16_performance.sh ## Model Results -Model |BatchSize |Precision |FPS |Top-1(%) |Top-5(%) ------------------|-----------|----------|----------|----------|-------- -Swin Transformer | 32 | FP16 |1104.52 | 80.578 | 95.2 +| Model | BatchSize | Precision | FPS | Top-1(%) | Top-5(%) | +|------------------|-----------|-----------|---------|----------|----------| +| Swin Transformer | 32 | FP16 | 1104.52 | 80.578 | 95.2 | diff --git a/models/cv/classification/swin_transformer_large/ixrt/README.md b/models/cv/classification/swin_transformer_large/ixrt/README.md index 6702a234..0abed040 100644 --- a/models/cv/classification/swin_transformer_large/ixrt/README.md +++ b/models/cv/classification/swin_transformer_large/ixrt/README.md @@ -1,4 +1,4 @@ -# Swin Transformer Large +# Swin Transformer Large (IxRT) ## Model Description @@ -6,18 +6,6 @@ Swin Transformer-Large is a variant of the Swin Transformer, an architecture des ## Model Preparation -### Install Dependencies - -```bash -export PROJ_ROOT=/PATH/TO/DEEPSPARKINFERENCE -export MODEL_PATH=${PROJ_ROOT}/models/cv/classification/swin_transformer_large/ixrt -cd ${MODEL_PATH} - -apt install -y libnuma-dev libgl1-mesa-glx - -pip3 install -r requirements.txt -``` - ### Prepare Resources Pretrained model: @@ -28,7 +16,18 @@ or you can : ```bash bash ./scripts/prepare_model_and_dataset.sh +``` + +### Install Dependencies +```bash +export PROJ_ROOT=/PATH/TO/DEEPSPARKINFERENCE +export MODEL_PATH=${PROJ_ROOT}/models/cv/classification/swin_transformer_large/ixrt +cd ${MODEL_PATH} + +apt install -y libnuma-dev libgl1-mesa-glx + +pip3 install -r requirements.txt ``` ### Model Conversion diff --git a/models/cv/classification/vgg11/igie/README.md b/models/cv/classification/vgg11/igie/README.md index cf2d5806..08ad4500 100644 --- a/models/cv/classification/vgg11/igie/README.md +++ b/models/cv/classification/vgg11/igie/README.md @@ -1,4 +1,4 @@ -# VGG11 +# VGG11 (IGIE) ## Model Description @@ -6,18 +6,18 @@ VGG11 is a deep convolutional neural network introduced by the Visual Geometry G ## Model Preparation -### Install Dependencies - -```bash -pip3 install -r requirements.txt -``` - ### Prepare Resources Pretrained model: Dataset: to download the validation dataset. +### Install Dependencies + +```bash +pip3 install -r requirements.txt +``` + ### Model Conversion ```bash @@ -41,6 +41,6 @@ bash scripts/infer_vgg11_fp16_performance.sh ## Model Results -Model |BatchSize |Precision |FPS |Top-1(%) |Top-5(%) ---------|-----------|----------|----------|----------|-------- -VGG11 | 32 | FP16 | 3872.86 | 69.03 | 88.6 +| Model | BatchSize | Precision | FPS | Top-1(%) | Top-5(%) | +|-------|-----------|-----------|---------|----------|----------| +| VGG11 | 32 | FP16 | 3872.86 | 69.03 | 88.6 | diff --git a/models/cv/classification/vgg16/igie/README.md b/models/cv/classification/vgg16/igie/README.md index 4c074f2f..ff1c9e52 100644 --- a/models/cv/classification/vgg16/igie/README.md +++ b/models/cv/classification/vgg16/igie/README.md @@ -1,4 +1,4 @@ -# VGG16 +# VGG16 (IGIE) ## Model Description @@ -6,18 +6,18 @@ VGG16 is a convolutional neural network (CNN) architecture designed for image cl ## Model Preparation -### Install Dependencies - -```bash -pip3 install -r requirements.txt -``` - ### Prepare Resources Pretrained model: Dataset: to download the validation dataset. +### Install Dependencies + +```bash +pip3 install -r requirements.txt +``` + ### Model Conversion ```bash @@ -50,7 +50,7 @@ bash scripts/infer_vgg16_int8_performance.sh ## Model Results -Model |BatchSize |Precision |FPS |Top-1(%) |Top-5(%) ---------|-----------|----------|----------|----------|-------- -VGG16 | 32 | FP16 | 1830.53 | 71.55 | 90.37 -VGG16 | 32 | INT8 | 3528.01 | 71.53 | 90.32 +| Model | BatchSize | Precision | FPS | Top-1(%) | Top-5(%) | +|-------|-----------|-----------|---------|----------|----------| +| VGG16 | 32 | FP16 | 1830.53 | 71.55 | 90.37 | +| VGG16 | 32 | INT8 | 3528.01 | 71.53 | 90.32 | diff --git a/models/cv/classification/vgg16/ixrt/README.md b/models/cv/classification/vgg16/ixrt/README.md index 11e32d7f..ae03982d 100644 --- a/models/cv/classification/vgg16/ixrt/README.md +++ b/models/cv/classification/vgg16/ixrt/README.md @@ -1,4 +1,4 @@ -# VGG16 +# VGG16 (IxRT) ## Model Description @@ -7,6 +7,12 @@ It finished second in the 2014 ImageNet Massive Visual Identity Challenge (ILSVR ## Model Preparation +### Prepare Resources + +Pretrained model: + +Dataset: to download the validation dataset. + ### Install Dependencies ```bash @@ -19,12 +25,6 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Prepare Resources - -Pretrained model: - -Dataset: to download the validation dataset. - ### Model Conversion ```bash @@ -62,7 +62,7 @@ bash scripts/infer_vgg16_int8_performance.sh ## Model Results -Model |BatchSize |Precision |FPS |Top-1(%) |Top-5(%) -------|-----------|----------|---------|---------|-------- -VGG16 | 32 | FP16 | 1777.85 | 71.57 | 90.40 -VGG16 | 32 | INT8 | 4451.80 | 71.47 | 90.35 +| Model | BatchSize | Precision | FPS | Top-1(%) | Top-5(%) | +|-------|-----------|-----------|---------|----------|----------| +| VGG16 | 32 | FP16 | 1777.85 | 71.57 | 90.40 | +| VGG16 | 32 | INT8 | 4451.80 | 71.47 | 90.35 | diff --git a/models/cv/classification/wide_resnet101/igie/README.md b/models/cv/classification/wide_resnet101/igie/README.md index 96dfc6cd..fb55e46a 100644 --- a/models/cv/classification/wide_resnet101/igie/README.md +++ b/models/cv/classification/wide_resnet101/igie/README.md @@ -1,4 +1,4 @@ -# Wide ResNet101 +# Wide ResNet101 (IGIE) ## Model Description @@ -6,18 +6,18 @@ Wide ResNet101 is a variant of the ResNet architecture that focuses on increasin ## Model Preparation -### Install Dependencies - -```bash -pip3 install -r requirements.txt -``` - ### Prepare Resources Pretrained model: Dataset: to download the validation dataset. +### Install Dependencies + +```bash +pip3 install -r requirements.txt +``` + ### Model Conversion ```bash diff --git a/models/cv/classification/wide_resnet50/igie/README.md b/models/cv/classification/wide_resnet50/igie/README.md index 7bcc1ffb..14e4afe3 100644 --- a/models/cv/classification/wide_resnet50/igie/README.md +++ b/models/cv/classification/wide_resnet50/igie/README.md @@ -1,4 +1,4 @@ -# Wide ResNet50 +# Wide ResNet50 (IGIE) ## Model Description @@ -6,18 +6,18 @@ The distinguishing feature of Wide ResNet50 lies in its widened architecture com ## Model Preparation -### Install Dependencies - -```bash -pip3 install -r requirements.txt -``` - ### Prepare Resources Pretrained model: Dataset: to download the validation dataset. +### Install Dependencies + +```bash +pip3 install -r requirements.txt +``` + ### Model Conversion ```bash @@ -51,6 +51,6 @@ bash scripts/infer_wide_resnet50_int8_performance.sh ## Model Results | Model | BatchSize | Precision | FPS | Top-1(%) | Top-5(%) | -| ------------- | --------- | --------- | -------- | -------- | -------- | +|---------------|-----------|-----------|----------|----------|----------| | Wide ResNet50 | 32 | FP16 | 2312.383 | 78.459 | 94.052 | | Wide ResNet50 | 32 | INT8 | 5195.654 | 77.957 | 93.798 | diff --git a/models/cv/classification/wide_resnet50/ixrt/README.md b/models/cv/classification/wide_resnet50/ixrt/README.md index b49b753a..616ef171 100644 --- a/models/cv/classification/wide_resnet50/ixrt/README.md +++ b/models/cv/classification/wide_resnet50/ixrt/README.md @@ -1,4 +1,4 @@ -# Wide ResNet50 +# Wide ResNet50 (IxRT) ## Model Description @@ -6,18 +6,18 @@ The distinguishing feature of Wide ResNet50 lies in its widened architecture com ## Model Preparation -### Install Dependencies - -```bash -pip3 install -r requirements.txt -``` - ### Prepare Resources Pretrained model: Dataset: to download the validation dataset. +### Install Dependencies + +```bash +pip3 install -r requirements.txt +``` + ### Model Conversion ```bash diff --git a/models/cv/face_recognition/facenet/ixrt/README.md b/models/cv/face_recognition/facenet/ixrt/README.md index 9558c3d6..1e4079f1 100644 --- a/models/cv/face_recognition/facenet/ixrt/README.md +++ b/models/cv/face_recognition/facenet/ixrt/README.md @@ -1,4 +1,4 @@ -# FaceNet +# FaceNet (IxRT) ## Model Description @@ -6,18 +6,6 @@ Facenet is a facial recognition system originally proposed and developed by Goog ## Model Preparation -### Install Dependencies - -```bash -# Install libGL -## CentOS -yum install -y mesa-libGL -## Ubuntu -apt install -y libgl1-mesa-glx - -pip3 install -r requirements.txt -``` - ### Prepare Resources Pretrained model: @@ -30,10 +18,21 @@ cd ${DeepSparkInference_PATH}/models/cv/face/facenet/ixrt unzip 20180408-102900.zip ``` -### Model Conversion +### Install Dependencies ```bash +# Install libGL +## CentOS +yum install -y mesa-libGL +## Ubuntu +apt install -y libgl1-mesa-glx +pip3 install -r requirements.txt +``` + +### Model Conversion + +```bash mkdir -p checkpoints mkdir -p facenet_weights git clone https://github.com/timesler/facenet-pytorch diff --git a/models/cv/instance_segmentation/mask_rcnn/ixrt/README.md b/models/cv/instance_segmentation/mask_rcnn/ixrt/README.md index 4ccad0cc..063840f1 100644 --- a/models/cv/instance_segmentation/mask_rcnn/ixrt/README.md +++ b/models/cv/instance_segmentation/mask_rcnn/ixrt/README.md @@ -1,15 +1,12 @@ -# Mask R-CNN +# Mask R-CNN (IxRT) ## Model Description Mask R-CNN (Mask Region-Based Convolutional Neural Network) is an extension of the Faster R-CNN model, which is itself an improvement over R-CNN and Fast R-CNN. Developed by Kaiming He et al., Mask R-CNN is designed for object instance segmentation tasks, meaning it not only detects objects within an image but also generates high-quality segmentation masks for each instance. -## Prepare +## Model Preparation -```bash -# go to current model home path -cd ${PROJ_ROOT}/models/cv/segmentation/mask_rcnn/ixrt -``` +### Prepare Resources Prepare weights and datasets referring to below steps: @@ -29,27 +26,25 @@ Visit [COCO site](https://cocodataset.org/) and get COCO2017 datasets - images directory: coco/images/val2017/*.jpg - annotations directory: coco/annotations/instances_val2017.json -## Model Preparation - -```bash -cd scripts/ -``` +### Install Dependencies -### Prepare on MR GPU +Prepare on MR GPU ```bash +cd scripts/ bash init.sh ``` -### Prepare on NV GPU +Prepare on NV GPU ```bash +cd scripts/ bash init_nv.sh ``` ## Model Inference -### FP16 Performance +### FP16 ```bash cd ../ @@ -61,11 +56,11 @@ bash scripts/infer_mask_rcnn_fp16_accuracy.sh ## Model Results -Model | BatchSize | Precision | FPS | ACC -------|-----------|-----------|-----|---- -Mask R-CNN | 1 | FP16 | 12.15 | bbox mAP@0.5 : 0.5512, segm mAP@0.5 : 0.5189 +| Model | BatchSize | Precision | FPS | ACC | +|------------|-----------|-----------|-------|------------------------------------------------| +| Mask R-CNN | 1 | FP16 | 12.15 | bbox mAP@0.5 : 0.5512, segm mAP@0.5 : 0.5189 | -## Referenece +## Refereneces - [tensorrtx](https://github.com/wang-xinyu/tensorrtx/tree/master/rcnn) - [detectron2](https://github.com/facebookresearch/detectron2) diff --git a/models/cv/instance_segmentation/solov1/ixrt/README.md b/models/cv/instance_segmentation/solov1/ixrt/README.md index b04a63d1..1c031d0c 100644 --- a/models/cv/instance_segmentation/solov1/ixrt/README.md +++ b/models/cv/instance_segmentation/solov1/ixrt/README.md @@ -1,4 +1,4 @@ -# SOLOv1 +# SOLOv1 (IxRT) ## Model Description @@ -6,19 +6,27 @@ SOLO (Segmenting Objects by Locations) is a new instance segmentation method tha ## Model Preparation +### Prepare Resources + +Pretrained model: + +Dataset: to download the validation dataset. + ### Install Dependencies ```bash -yum install mesa-libGL +# Install libGL +## CentOS +yum install -y mesa-libGL +## Ubuntu +apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Dependency - The inference of the Solov1 model requires a dependency on a well-adapted mmcv-v1.7.0 library. Please inquire with the staff to obtain the relevant libraries. -You can follow here to build: https://gitee.com/deep-spark/deepsparkhub/blob/master/toolbox/MMDetection/prepare_mmcv.sh +You can follow the script [prepare_mmcv.sh](https://gitee.com/deep-spark/deepsparkhub/blob/master/toolbox/MMDetection/prepare_mmcv.sh) to build: ```bash cd mmcv @@ -26,12 +34,6 @@ sh build_mmcv.sh sh install_mmcv.sh ``` -### Prepare Resources - -Pretrained model: - -Dataset: to download the validation dataset. - ### Model Conversion ```bash @@ -62,6 +64,6 @@ bash scripts/infer_solov1_fp16_performance.sh ## Model Results -Model |BatchSize |Precision |FPS |MAP@0.5 |MAP@0.5:0.95 ---------|-----------|----------|----------|----------|------------ -SOLOv1 | 1 | FP16 | 24.67 | 0.541 | 0.338 +| Model | BatchSize | Precision | FPS | MAP@0.5 | MAP@0.5:0.95 | +|--------|-----------|-----------|-------|---------|--------------| +| SOLOv1 | 1 | FP16 | 24.67 | 0.541 | 0.338 | diff --git a/models/cv/multi_object_tracking/deepsort/igie/README.md b/models/cv/multi_object_tracking/deepsort/igie/README.md index dda65e4a..adfc9d0b 100644 --- a/models/cv/multi_object_tracking/deepsort/igie/README.md +++ b/models/cv/multi_object_tracking/deepsort/igie/README.md @@ -1,4 +1,4 @@ -# DeepSort +# DeepSort (IGIE) ## Model Description @@ -6,18 +6,18 @@ DeepSort integrates deep neural networks with traditional tracking methods to ac ## Model Preparation -### Install Dependencies - -```bash -pip3 install -r requirements.txt -``` - ### Prepare Resources Pretrained model(ckpt.t7): Dataset: to download the market1501 dataset. +### Install Dependencies + +```bash +pip3 install -r requirements.txt +``` + ### Model Conversion ```bash @@ -53,7 +53,7 @@ bash scripts/infer_deepsort_int8_performance.sh ## Model Results -Model |BatchSize |Precision |FPS |Acc(%) | ----------|-----------|----------|----------|----------| -DeepSort | 32 | FP16 |17164.67 | 99.32 | -DeepSort | 32 | INT8 |20399.12 | 99.29 | +| Model | BatchSize | Precision | FPS | Acc(%) | +|----------|-----------|-----------|----------|--------| +| DeepSort | 32 | FP16 | 17164.67 | 99.32 | +| DeepSort | 32 | INT8 | 20399.12 | 99.29 | diff --git a/models/cv/multi_object_tracking/fastreid/igie/README.md b/models/cv/multi_object_tracking/fastreid/igie/README.md index 0353c81a..0f544602 100644 --- a/models/cv/multi_object_tracking/fastreid/igie/README.md +++ b/models/cv/multi_object_tracking/fastreid/igie/README.md @@ -1,4 +1,4 @@ -# FastReID +# FastReID (IGIE) ## Model Description @@ -6,18 +6,18 @@ FastReID is a research platform that implements state-of-the-art re-identificati ## Model Preparation -### Install Dependencies - -```bash -pip3 install -r requirements.txt -``` - ### Prepare Resources Pretrained model: Dataset: to download the vehicleid dataset. +### Install Dependencies + +```bash +pip3 install -r requirements.txt +``` + ### Model Conversion ```bash @@ -48,6 +48,6 @@ bash scripts/infer_fastreid_fp16_performance.sh ## Model Results -Model |BatchSize |Precision |FPS |Rank-1(%) |Rank-5(%) |mAP | ----------|-----------|----------|----------|----------|----------|--------| -FastReid | 32 | FP16 | 1850.78 | 88.39 | 98.45 | 92.79 | +| Model | BatchSize | Precision | FPS | Rank-1(%) | Rank-5(%) | mAP | +|----------|-----------|-----------|---------|-----------|-----------|-------| +| FastReid | 32 | FP16 | 1850.78 | 88.39 | 98.45 | 92.79 | diff --git a/models/cv/multi_object_tracking/repnet/igie/README.md b/models/cv/multi_object_tracking/repnet/igie/README.md index 28d221a4..3a161ecc 100644 --- a/models/cv/multi_object_tracking/repnet/igie/README.md +++ b/models/cv/multi_object_tracking/repnet/igie/README.md @@ -1,4 +1,4 @@ -# RepNet-Vehicle-ReID +# RepNet-Vehicle-ReID (IGIE) ## Model Description @@ -6,18 +6,18 @@ The paper "Deep Relative Distance Learning: Tell the Difference Between Similar ## Model Preparation -### Install Dependencies - -```bash -pip3 install -r requirements.txt -``` - ### Prepare Resources Pretrained model: Dataset: to download the VehicleID dataset. +### Install Dependencies + +```bash +pip3 install -r requirements.txt +``` + ### Model Conversion ```bash @@ -44,10 +44,10 @@ bash scripts/infer_repnet_fp16_performance.sh ## Model Results -Model |BatchSize |Precision |FPS |Acc(%) | ---------|-----------|----------|----------|----------| -RepNet | 32 | FP16 |1373.579 | 99.88 | +| Model | BatchSize | Precision | FPS | Acc(%) | +|--------|-----------|-----------|----------|--------| +| RepNet | 32 | FP16 | 1373.579 | 99.88 | ## References -RepNet-MDNet-VehicleReID: +- [RepNet-MDNet-VehicleReID](https://github.com/CaptainEven/RepNet-MDNet-VehicleReID) diff --git a/models/cv/object_detection/atss/igie/README.md b/models/cv/object_detection/atss/igie/README.md index 2fceb8f7..357d7c95 100644 --- a/models/cv/object_detection/atss/igie/README.md +++ b/models/cv/object_detection/atss/igie/README.md @@ -1,4 +1,4 @@ -# ATSS +# ATSS (IGIE) ## Model Description @@ -6,6 +6,16 @@ ATSS is an advanced adaptive training sample selection method that effectively e ## Model Preparation +### Prepare Resources + +Pretrained model: + +Dataset: to download the validation dataset. + +```bash +wget https://download.openmmlab.com/mmdetection/v2.0/atss/atss_r50_fpn_1x_coco/atss_r50_fpn_1x_coco_20200209-985f7bd0.pth +``` + ### Install Dependencies ```bash @@ -18,16 +28,6 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Prepare Resources - -Pretrained model: - -Dataset: to download the validation dataset. - -```bash -wget https://download.openmmlab.com/mmdetection/v2.0/atss/atss_r50_fpn_1x_coco/atss_r50_fpn_1x_coco_20200209-985f7bd0.pth -``` - ### Model Conversion ```bash @@ -55,11 +55,10 @@ bash scripts/infer_atss_fp16_performance.sh ## Model Results -Model |BatchSize |Precision |FPS |IOU@0.5 |IOU@0.5:0.95 | --------|-----------|----------|----------|----------|---------------| -ATSS | 32 | FP16 | 81.671 | 0.541 | 0.367 | - +| Model | BatchSize | Precision | FPS | IOU@0.5 | IOU@0.5:0.95 | +|-------|-----------|-----------|--------|---------|--------------| +| ATSS | 32 | FP16 | 81.671 | 0.541 | 0.367 | ## References -mmdetection: +- [mmdetection](https://github.com/open-mmlab/mmdetection.git) diff --git a/models/cv/object_detection/centernet/igie/README.md b/models/cv/object_detection/centernet/igie/README.md index 17429ef7..a9e1516a 100644 --- a/models/cv/object_detection/centernet/igie/README.md +++ b/models/cv/object_detection/centernet/igie/README.md @@ -1,4 +1,4 @@ -# CenterNet +# CenterNet (IGIE) ## Model Description @@ -6,6 +6,12 @@ CenterNet is an efficient object detection model that simplifies the traditional ## Model Preparation +### Prepare Resources + +Pretrained model: + +Dataset: to download the validation dataset. + ### Install Dependencies ```bash @@ -18,12 +24,6 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Prepare Resources - -Pretrained model: - -Dataset: to download the validation dataset. - ### Model Conversion ```bash @@ -48,10 +48,10 @@ bash scripts/infer_centernet_fp16_performance.sh ## Model Results -Model |BatchSize |Precision |FPS |IOU@0.5 |IOU@0.5:0.95 | -----------|-----------|----------|----------|----------|---------------| -CenterNet | 32 | FP16 | 799.70 | 0.423 | 0.258 | +| Model | BatchSize | Precision | FPS | IOU@0.5 | IOU@0.5:0.95 | +|-----------|-----------|-----------|--------|---------|--------------| +| CenterNet | 32 | FP16 | 799.70 | 0.423 | 0.258 | ## References -mmdetection: +- [mmdetection](https://github.com/open-mmlab/mmdetection.git) diff --git a/models/cv/object_detection/centernet/ixrt/README.md b/models/cv/object_detection/centernet/ixrt/README.md index bcb7e55f..031525be 100644 --- a/models/cv/object_detection/centernet/ixrt/README.md +++ b/models/cv/object_detection/centernet/ixrt/README.md @@ -1,4 +1,4 @@ -# CenterNet +# CenterNet (IxRT) ## Model Description @@ -6,6 +6,12 @@ CenterNet is an efficient object detection model that simplifies the traditional ## Model Preparation +### Prepare Resources + +Pretrained model: + +Dataset: to download the validation dataset. + ### Install Dependencies ```bash @@ -19,12 +25,6 @@ pip3 install -r requirements.txt # Contact the Iluvatar administrator to get the mmcv install package. ``` -### Prepare Resources - -Pretrained model: - -Dataset: to download the validation dataset. - ### Model Conversion ```bash @@ -56,4 +56,4 @@ bash scripts/infer_centernet_fp16_performance.sh ## References -mmdetection: +- [mmdetection](https://github.com/open-mmlab/mmdetection.git) diff --git a/models/cv/object_detection/detr/ixrt/README.md b/models/cv/object_detection/detr/ixrt/README.md index 2f59fe34..2b318fb5 100755 --- a/models/cv/object_detection/detr/ixrt/README.md +++ b/models/cv/object_detection/detr/ixrt/README.md @@ -1,4 +1,4 @@ -# DETR +# DETR (IxRT) ## Model Description @@ -6,6 +6,12 @@ DETR (DEtection TRansformer) is a novel approach that views object detection as ## Model Preparation +### Prepare Resources + +Pretrained model: + +Dataset: to download the validation dataset. + ### Install Dependencies ```bash @@ -18,12 +24,6 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Prepare Resources - -Pretrained model: - -Dataset: to download the validation dataset. - ### Model Conversion ```bash @@ -54,6 +54,6 @@ bash scripts/infer_detr_fp16_performance.sh ## Model Results -Model |BatchSize |Precision |FPS |MAP@0.5 |MAP@0.5:0.95 ---------|-----------|----------|----------|----------|------------ -DETR | 1 | FP16 | 65.84 | 0.370 | 0.198 +| Model | BatchSize | Precision | FPS | MAP@0.5 | MAP@0.5:0.95 | +|-------|-----------|-----------|-------|---------|--------------| +| DETR | 1 | FP16 | 65.84 | 0.370 | 0.198 | diff --git a/models/cv/object_detection/fcos/igie/README.md b/models/cv/object_detection/fcos/igie/README.md index 0e123d4d..c4f9ece1 100644 --- a/models/cv/object_detection/fcos/igie/README.md +++ b/models/cv/object_detection/fcos/igie/README.md @@ -1,4 +1,4 @@ -# FCOS +# FCOS (IGIE) ## Model Description @@ -6,6 +6,16 @@ FCOS is an innovative one-stage object detection framework that abandons traditi ## Model Preparation +### Prepare Resources + +Pretrained model: + +Dataset: to download the validation dataset. + +```bash +wget https://download.openmmlab.com/mmdetection/v2.0/fcos/fcos_r50_caffe_fpn_gn-head_1x_coco/fcos_r50_caffe_fpn_gn-head_1x_coco-821213aa.pth +``` + ### Install Dependencies ```bash @@ -18,16 +28,6 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Prepare Resources - -Pretrained model: - -Dataset: to download the validation dataset. - -```bash -wget https://download.openmmlab.com/mmdetection/v2.0/fcos/fcos_r50_caffe_fpn_gn-head_1x_coco/fcos_r50_caffe_fpn_gn-head_1x_coco-821213aa.pth -``` - ### Model Conversion ```bash @@ -55,10 +55,10 @@ bash scripts/infer_fcos_fp16_performance.sh ## Model Results -Model |BatchSize |Precision |FPS |IOU@0.5 |IOU@0.5:0.95 | --------|-----------|----------|----------|----------|---------------| -FCOS | 32 | FP16 | 83.09 | 0.522 | 0.339 | +| Model | BatchSize | Precision | FPS | IOU@0.5 | IOU@0.5:0.95 | +|-------|-----------|-----------|-------|---------|--------------| +| FCOS | 32 | FP16 | 83.09 | 0.522 | 0.339 | ## References -mmdetection: +- [mmdetection](https://github.com/open-mmlab/mmdetection.git) diff --git a/models/cv/object_detection/fcos/ixrt/README.md b/models/cv/object_detection/fcos/ixrt/README.md index 80b32ad8..4f17fe4d 100755 --- a/models/cv/object_detection/fcos/ixrt/README.md +++ b/models/cv/object_detection/fcos/ixrt/README.md @@ -1,4 +1,4 @@ -# FCOS +# FCOS (IxRT) ## Model Description @@ -7,6 +7,15 @@ For more details, please refer to our [report on Arxiv](https://arxiv.org/abs/19 ## Model Preparation +### Prepare Resources + +Pretrained model: + +COCO2017: + +- val2017: Path/To/val2017/*.jpg +- annotations: Path/To/annotations/instances_val2017.json + ### Install Dependencies ```bash @@ -19,27 +28,16 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Dependency - The inference of the FCOS model requires a dependency on a well-adapted mmcv-v1.7.0 library. Please inquire with the staff to obtain the relevant libraries. -You can follow here to build: https://gitee.com/deep-spark/deepsparkhub/blob/master/toolbox/MMDetection/prepare_mmcv.sh +You can follow the script [prepare_mmcv.sh](https://gitee.com/deep-spark/deepsparkhub/blob/master/toolbox/MMDetection/prepare_mmcv.sh) to build: ```bash - cd mmcv sh build_mmcv.sh sh install_mmcv.sh ``` -### Prepare Resources - -Pretrained model: - -- COCO2017数据集准备参考: - - 图片目录: Path/To/val2017/*.jpg - - 标注文件目录: Path/To/annotations/instances_val2017.json - ### Model Conversion MMDetection is an open source object detection toolbox based on PyTorch. It is a part of the OpenMMLab project.It is utilized for model conversion. In MMDetection, Execute model conversion command, and the checkpoints folder needs to be created, (mkdir checkpoints) in project diff --git a/models/cv/object_detection/foveabox/igie/README.md b/models/cv/object_detection/foveabox/igie/README.md index f90f39fb..bc5a8a87 100644 --- a/models/cv/object_detection/foveabox/igie/README.md +++ b/models/cv/object_detection/foveabox/igie/README.md @@ -1,4 +1,4 @@ -# FoveaBox +# FoveaBox (IGIE) ## Model Description @@ -6,6 +6,12 @@ FoveaBox is an advanced anchor-free object detection framework that enhances acc ## Model Preparation +### Prepare Resources + +Pretrained model: + +Dataset: to download the validation dataset. + ### Install Dependencies ```bash @@ -18,12 +24,6 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Prepare Resources - -Pretrained model: - -Dataset: to download the validation dataset. - ### Model Conversion ```bash @@ -51,10 +51,10 @@ bash scripts/infer_foveabox_fp16_performance.sh ## Model Results -Model |BatchSize |Precision |FPS |IOU@0.5 |IOU@0.5:0.95 | ----------|-----------|----------|----------|----------|---------------| -FoveaBox | 32 | FP16 | 192.496 | 0.531 | 0.346 | +| Model | BatchSize | Precision | FPS | IOU@0.5 | IOU@0.5:0.95 | +|----------|-----------|-----------|---------|---------|--------------| +| FoveaBox | 32 | FP16 | 192.496 | 0.531 | 0.346 | ## References -mmdetection: +- [mmdetection](https://github.com/open-mmlab/mmdetection.git) diff --git a/models/cv/object_detection/foveabox/ixrt/README.md b/models/cv/object_detection/foveabox/ixrt/README.md index b085bc6c..1949fca3 100644 --- a/models/cv/object_detection/foveabox/ixrt/README.md +++ b/models/cv/object_detection/foveabox/ixrt/README.md @@ -1,4 +1,4 @@ -# FoveaBox +# FoveaBox (IxRT) ## Model Description @@ -6,6 +6,12 @@ FoveaBox is an advanced anchor-free object detection framework that enhances acc ## Model Preparation +### Prepare Resources + +Pretrained model: + +Dataset: to download the validation dataset. + ### Install Dependencies ```bash @@ -15,22 +21,9 @@ yum install -y mesa-libGL ## Ubuntu apt install -y libgl1-mesa-glx -pip3 install tqdm -pip3 install onnx -pip3 install onnxsim -pip3 install ultralytics -pip3 install pycocotools -pip3 install mmdeploy -pip3 install mmdet -pip3 install opencv-python==4.6.0.66 +pip3 install -r requirements.txt ``` -### Prepare Resources - -Pretrained model: - -Dataset: to download the validation dataset. - ### Model Conversion ```bash @@ -58,10 +51,10 @@ bash scripts/infer_foveabox_fp16_performance.sh ## Model Results -Model |BatchSize |Precision |FPS |IOU@0.5 |IOU@0.5:0.95 | ----------|-----------|----------|----------|----------|---------------| -FoveaBox | 32 | FP16 | 181.304 | 0.531 | 0.346 | +| Model | BatchSize | Precision | FPS | IOU@0.5 | IOU@0.5:0.95 | +|----------|-----------|-----------|---------|---------|--------------| +| FoveaBox | 32 | FP16 | 181.304 | 0.531 | 0.346 | ## References -mmdetection: +- [mmdetection](https://github.com/open-mmlab/mmdetection.git) diff --git a/models/cv/object_detection/foveabox/ixrt/requirements.txt b/models/cv/object_detection/foveabox/ixrt/requirements.txt new file mode 100644 index 00000000..6b25e9d9 --- /dev/null +++ b/models/cv/object_detection/foveabox/ixrt/requirements.txt @@ -0,0 +1,8 @@ +tqdm +onnx +onnxsim +ultralytics +pycocotools +mmdeploy +mmdet +opencv-python==4.6.0.66 \ No newline at end of file diff --git a/models/cv/object_detection/fsaf/igie/README.md b/models/cv/object_detection/fsaf/igie/README.md index 047d6fad..ce71c0c5 100644 --- a/models/cv/object_detection/fsaf/igie/README.md +++ b/models/cv/object_detection/fsaf/igie/README.md @@ -1,4 +1,4 @@ -# FSAF +# FSAF (IGIE) ## Model Description @@ -6,6 +6,16 @@ The FSAF (Feature Selective Anchor-Free) module is an innovative component for s ## Model Preparation +### Prepare Resources + +Pretrained model: + +Dataset: to download the validation dataset. + +```bash +wget https://download.openmmlab.com/mmdetection/v2.0/fsaf/fsaf_r50_fpn_1x_coco/fsaf_r50_fpn_1x_coco-94ccc51f.pth +``` + ### Install Dependencies ```bash @@ -18,16 +28,6 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Prepare Resources - -Pretrained model: - -Dataset: to download the validation dataset. - -```bash -wget https://download.openmmlab.com/mmdetection/v2.0/fsaf/fsaf_r50_fpn_1x_coco/fsaf_r50_fpn_1x_coco-94ccc51f.pth -``` - ### Model Conversion ```bash @@ -55,10 +55,10 @@ bash scripts/infer_fsaf_fp16_performance.sh ## Model Results -Model |BatchSize |Precision |FPS |IOU@0.5 |IOU@0.5:0.95 | --------|-----------|----------|----------|----------|---------------| -FSAF | 32 | FP16 | 122.35 | 0.530 | 0.345 | +| Model | BatchSize | Precision | FPS | IOU@0.5 | IOU@0.5:0.95 | +|-------|-----------|-----------|--------|---------|--------------| +| FSAF | 32 | FP16 | 122.35 | 0.530 | 0.345 | ## References -mmdetection: +- [mmdetection](https://github.com/open-mmlab/mmdetection.git) diff --git a/models/cv/object_detection/fsaf/ixrt/README.md b/models/cv/object_detection/fsaf/ixrt/README.md index e1ecf0b9..8fdb52cc 100644 --- a/models/cv/object_detection/fsaf/ixrt/README.md +++ b/models/cv/object_detection/fsaf/ixrt/README.md @@ -1,4 +1,4 @@ -# FSAF +# FSAF (IxRT) ## Model Description @@ -6,6 +6,16 @@ The FSAF (Feature Selective Anchor-Free) module is an innovative component for s ## Model Preparation +### Prepare Resources + +Pretrained model: + +Dataset: to download the validation dataset. + +```bash +wget https://download.openmmlab.com/mmdetection/v2.0/fsaf/fsaf_r50_fpn_1x_coco/fsaf_r50_fpn_1x_coco-94ccc51f.pth +``` + ### Install Dependencies ```bash @@ -18,16 +28,6 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Prepare Resources - -Pretrained model: - -Dataset: to download the validation dataset. - -```bash -wget https://download.openmmlab.com/mmdetection/v2.0/fsaf/fsaf_r50_fpn_1x_coco/fsaf_r50_fpn_1x_coco-94ccc51f.pth -``` - ### Model Conversion ```bash @@ -55,10 +55,10 @@ bash scripts/infer_fsaf_fp16_performance.sh ## Model Results -Model |BatchSize |Precision |FPS |IOU@0.5 |IOU@0.5:0.95 | --------|-----------|----------|----------|----------|---------------| -FSAF | 32 | FP16 | 133.85 | 0.530 | 0.345 | +| Model | BatchSize | Precision | FPS | IOU@0.5 | IOU@0.5:0.95 | +|-------|-----------|-----------|--------|---------|--------------| +| FSAF | 32 | FP16 | 133.85 | 0.530 | 0.345 | ## References -mmdetection: +- [mmdetection](https://github.com/open-mmlab/mmdetection.git) diff --git a/models/cv/object_detection/hrnet/igie/README.md b/models/cv/object_detection/hrnet/igie/README.md index 8063bb6e..7889fb6f 100644 --- a/models/cv/object_detection/hrnet/igie/README.md +++ b/models/cv/object_detection/hrnet/igie/README.md @@ -1,4 +1,4 @@ -# HRNet +# HRNet (IGIE) ## Model Description @@ -6,6 +6,12 @@ HRNet is an advanced deep learning architecture for human pose estimation, chara ## Model Preparation +### Prepare Resources + +Pretrained model: + +Dataset: to download the validation dataset. + ### Install Dependencies ```bash @@ -18,12 +24,6 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Prepare Resources - -Pretrained model: - -Dataset: to download the validation dataset. - ### Model Conversion ```bash @@ -51,10 +51,10 @@ bash scripts/infer_hrnet_fp16_performance.sh ## Model Results -Model |BatchSize |Precision |FPS |IOU@0.5 |IOU@0.5:0.95 | --------|-----------|----------|----------|----------|---------------| -HRNet | 32 | FP16 | 64.282 | 0.491 | 0.326 | +| Model | BatchSize | Precision | FPS | IOU@0.5 | IOU@0.5:0.95 | +|-------|-----------|-----------|--------|---------|--------------| +| HRNet | 32 | FP16 | 64.282 | 0.491 | 0.326 | ## References -mmdetection: +- [mmdetection](https://github.com/open-mmlab/mmdetection.git) diff --git a/models/cv/object_detection/hrnet/ixrt/README.md b/models/cv/object_detection/hrnet/ixrt/README.md index f37e3743..cd173777 100644 --- a/models/cv/object_detection/hrnet/ixrt/README.md +++ b/models/cv/object_detection/hrnet/ixrt/README.md @@ -1,4 +1,4 @@ -# HRNet +# HRNet (IxRT) ## Model Description @@ -6,6 +6,12 @@ HRNet is an advanced deep learning architecture for human pose estimation, chara ## Model Preparation +### Prepare Resources + +Pretrained model: + +Dataset: to download the validation dataset. + ### Install Dependencies ```bash @@ -18,12 +24,6 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Prepare Resources - -Pretrained model: - -Dataset: to download the validation dataset. - ### Model Conversion ```bash @@ -51,10 +51,10 @@ bash scripts/infer_hrnet_fp16_performance.sh ## Model Results -Model |BatchSize |Precision |FPS |IOU@0.5 |IOU@0.5:0.95 | --------|-----------|----------|----------|----------|---------------| -HRNet | 32 | FP16 | 75.199 | 0.491 | 0.327 | +| Model | BatchSize | Precision | FPS | IOU@0.5 | IOU@0.5:0.95 | +|-------|-----------|-----------|--------|---------|--------------| +| HRNet | 32 | FP16 | 75.199 | 0.491 | 0.327 | ## References -mmdetection: +- [mmdetection](https://github.com/open-mmlab/mmdetection.git) diff --git a/models/cv/object_detection/paa/igie/README.md b/models/cv/object_detection/paa/igie/README.md index eeaf5615..f9797fa8 100644 --- a/models/cv/object_detection/paa/igie/README.md +++ b/models/cv/object_detection/paa/igie/README.md @@ -1,4 +1,4 @@ -# PAA +# PAA (IGIE) ## Model Description @@ -6,6 +6,12 @@ PAA (Probabilistic Anchor Assignment) is an algorithm for object detection that ## Model Preparation +### Prepare Resources + +Pretrained model: + +Dataset: to download the validation dataset. + ### Install Dependencies ```bash @@ -18,12 +24,6 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Prepare Resources - -Pretrained model: - -Dataset: to download the validation dataset. - ### Model Conversion ```bash @@ -57,4 +57,4 @@ bash scripts/infer_paa_fp16_performance.sh ## References -mmdetection: +- [mmdetection](https://github.com/open-mmlab/mmdetection.git) diff --git a/models/cv/object_detection/retinaface/igie/README.md b/models/cv/object_detection/retinaface/igie/README.md index a2928ae7..0f0da855 100755 --- a/models/cv/object_detection/retinaface/igie/README.md +++ b/models/cv/object_detection/retinaface/igie/README.md @@ -1,4 +1,4 @@ -# RetinaFace +# RetinaFace (IGIE) ## Model Description @@ -6,6 +6,12 @@ RetinaFace is an efficient single-stage face detection model that employs a mult ## Model Preparation +### Prepare Resources + +Pretrained model: + +Dataset: to download the validation dataset. + ### Install Dependencies ```bash @@ -18,12 +24,6 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Prepare Resources - -Pretrained model: - -Dataset: to download the validation dataset. - ```bash wget https://github.com/biubug6/Face-Detector-1MB-with-landmark/raw/master/weights/mobilenet0.25_Final.pth ``` @@ -55,10 +55,10 @@ bash scripts/infer_retinaface_fp16_performance.sh ## Model Results -| Model | BatchSize | Precision | FPS | Easy AP(%) | Medium AP (%) | Hard AP(%) | -| :--------: | :-------: | :-------: | :------: | :--------: | :-----------: | :--------: | -| RetinaFace | 32 | FP16 | 8304.626 | 80.13 | 68.52 | 36.59 | +| Model | BatchSize | Precision | FPS | Easy AP(%) | Medium AP (%) | Hard AP(%) | +|------------|-----------|-----------|----------|------------|---------------|------------| +| RetinaFace | 32 | FP16 | 8304.626 | 80.13 | 68.52 | 36.59 | ## References -Face-Detector-1MB-with-landmark: +- [Face-Detector-1MB-with-landmark](https://github.com/biubug6/Face-Detector-1MB-with-landmark) diff --git a/models/cv/object_detection/retinaface/ixrt/README.md b/models/cv/object_detection/retinaface/ixrt/README.md index 4ac37220..fcb4e480 100644 --- a/models/cv/object_detection/retinaface/ixrt/README.md +++ b/models/cv/object_detection/retinaface/ixrt/README.md @@ -1,4 +1,4 @@ -# RetinaFace +# RetinaFace (IxRT) ## Model Description @@ -6,6 +6,16 @@ RetinaFace is an efficient single-stage face detection model that employs a mult ## Model Preparation +### Prepare Resources + +Pretrained model: + +Dataset: to download the validation dataset. + +```bash +wget https://github.com/biubug6/Face-Detector-1MB-with-landmark/raw/master/weights/mobilenet0.25_Final.pth +``` + ### Install Dependencies ```bash @@ -20,21 +30,12 @@ pip3 install -r requirements.txt python3 setup.py build_ext --inplace ``` -### Prepare Resources - -Pretrained model: - -Dataset: to download the validation dataset. - -```bash -wget https://github.com/biubug6/Face-Detector-1MB-with-landmark/raw/master/weights/mobilenet0.25_Final.pth -``` - ### Model Conversion ```bash # export onnx model python3 torch2onnx.py --model mobilenet0.25_Final.pth --onnx_model mnetv1_retinaface.onnx +``` ## Model Inference @@ -54,10 +55,10 @@ bash scripts/infer_retinaface_fp16_performance.sh ## Model Results -| Model | BatchSize | Precision | FPS | Easy AP(%) | Medium AP (%) | Hard AP(%) | -| :--------: | :-------: | :-------: | :------: | :--------: | :-----------: | :--------: | -| RetinaFace | 32 | FP16 | 8536.367 | 80.84 | 69.34 | 37.31 | +| Model | BatchSize | Precision | FPS | Easy AP(%) | Medium AP (%) | Hard AP(%) | +|------------|-----------|-----------|----------|------------|---------------|------------| +| RetinaFace | 32 | FP16 | 8536.367 | 80.84 | 69.34 | 37.31 | ## References -Face-Detector-1MB-with-landmark: +- [Face-Detector-1MB-with-landmark](https://github.com/biubug6/Face-Detector-1MB-with-landmark) diff --git a/models/cv/object_detection/retinanet/igie/README.md b/models/cv/object_detection/retinanet/igie/README.md index f8b4fa09..35dfcbfb 100644 --- a/models/cv/object_detection/retinanet/igie/README.md +++ b/models/cv/object_detection/retinanet/igie/README.md @@ -1,4 +1,4 @@ -# RetinaNet +# RetinaNet (IGIE) ## Model Description @@ -6,6 +6,12 @@ RetinaNet, an innovative object detector, challenges the conventional trade-off ## Model Preparation +### Prepare Resources + +Pretrained model: + +Dataset: to download the validation dataset. + ### Install Dependencies ```bash @@ -18,12 +24,6 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Prepare Resources - -Pretrained model: - -Dataset: to download the validation dataset. - ### Model Conversion ```bash @@ -51,10 +51,10 @@ bash scripts/infer_retinanet_fp16_performance.sh ## Model Results -Model |BatchSize |Precision |FPS |IOU@0.5 |IOU@0.5:0.95 | -----------|-----------|----------|----------|----------|---------------| -RetinaNet | 32 | FP16 | 160.52 | 0.515 | 0.335 | +| Model | BatchSize | Precision | FPS | IOU@0.5 | IOU@0.5:0.95 | +|-----------|-----------|-----------|--------|---------|--------------| +| RetinaNet | 32 | FP16 | 160.52 | 0.515 | 0.335 | ## References -mmdetection: +- [mmdetection](https://github.com/open-mmlab/mmdetection.git) diff --git a/models/cv/object_detection/rtmdet/igie/README.md b/models/cv/object_detection/rtmdet/igie/README.md index 76f47bc0..d1f0fc26 100644 --- a/models/cv/object_detection/rtmdet/igie/README.md +++ b/models/cv/object_detection/rtmdet/igie/README.md @@ -1,4 +1,4 @@ -# RTMDet +# RTMDet (IGIE) ## Model Description @@ -6,6 +6,16 @@ RTMDet, presented by the Shanghai AI Laboratory, is a novel framework for real-t ## Model Preparation +### Prepare Resources + +Pretrained model: + +Dataset: to download the validation dataset. + +```bash +wget https://download.openmmlab.com/mmpose/v1/projects/rtmpose/rtmdet_nano_8xb32-100e_coco-obj365-person-05d8511e.pth +``` + ### Install Dependencies ```bash @@ -18,16 +28,6 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Prepare Resources - -Pretrained model: - -Dataset: to download the validation dataset. - -```bash -wget https://download.openmmlab.com/mmpose/v1/projects/rtmpose/rtmdet_nano_8xb32-100e_coco-obj365-person-05d8511e.pth -``` - ### Model Conversion ```bash @@ -54,10 +54,11 @@ bash scripts/infer_rtmdet_fp16_performance.sh ``` ## Model Results -Model |BatchSize |Precision |FPS |IOU@0.5 |IOU@0.5:0.95 | -----------|-----------|----------|----------|----------|---------------| -RTMDet | 32 | FP16 | 2627.15 | 0.619 | 0.403 | + +| Model | BatchSize | Precision | FPS | IOU@0.5 | IOU@0.5:0.95 | +|--------|-----------|-----------|---------|---------|--------------| +| RTMDet | 32 | FP16 | 2627.15 | 0.619 | 0.403 | ## References -mmdetection: +- [mmdetection](https://github.com/open-mmlab/mmdetection.git) diff --git a/models/cv/object_detection/sabl/igie/README.md b/models/cv/object_detection/sabl/igie/README.md index 3c363a9d..4cb475c2 100644 --- a/models/cv/object_detection/sabl/igie/README.md +++ b/models/cv/object_detection/sabl/igie/README.md @@ -1,4 +1,4 @@ -# SABL +# SABL (IGIE) ## Model Description @@ -6,6 +6,16 @@ SABL (Side-Aware Boundary Localization) is an innovative approach in object dete ## Model Preparation +### Prepare Resources + +Pretrained model: + +Dataset: to download the validation dataset. + +```bash +wget https://download.openmmlab.com/mmdetection/v2.0/sabl/sabl_retinanet_r50_fpn_1x_coco/sabl_retinanet_r50_fpn_1x_coco-6c54fd4f.pth +``` + ### Install Dependencies ```bash @@ -18,16 +28,6 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Prepare Resources - -Pretrained model: - -Dataset: to download the validation dataset. - -```bash -wget https://download.openmmlab.com/mmdetection/v2.0/sabl/sabl_retinanet_r50_fpn_1x_coco/sabl_retinanet_r50_fpn_1x_coco-6c54fd4f.pth -``` - ### Model Conversion ```bash @@ -55,10 +55,10 @@ bash scripts/infer_sabl_fp16_performance.sh ## Model Results -Model |BatchSize |Precision |FPS |IOU@0.5 |IOU@0.5:0.95 | --------|-----------|----------|----------|----------|---------------| -SABL | 32 | FP16 | 189.42 | 0.530 | 0.356 | +| Model | BatchSize | Precision | FPS | IOU@0.5 | IOU@0.5:0.95 | +|-------|-----------|-----------|--------|---------|--------------| +| SABL | 32 | FP16 | 189.42 | 0.530 | 0.356 | ## References -mmdetection: +- [mmdetection](https://github.com/open-mmlab/mmdetection.git) diff --git a/models/cv/object_detection/yolov10/igie/README.md b/models/cv/object_detection/yolov10/igie/README.md index 78e214fc..f94a3c1e 100644 --- a/models/cv/object_detection/yolov10/igie/README.md +++ b/models/cv/object_detection/yolov10/igie/README.md @@ -1,4 +1,4 @@ -# YOLOv10 +# YOLOv10 (IGIE) ## Model Description @@ -6,23 +6,23 @@ YOLOv10, built on the Ultralytics Python package by researchers at Tsinghua Univ ## Model Preparation +### Prepare Resources + +Pretrained model: + ### Install Dependencies ```bash pip3 install -r requirements.txt ``` -### Prepare Resources - -Pretrained model: - ## Model Conversion ```bash git clone --depth 1 https://github.com/THU-MIG/yolov10.git -cd yolov10 +cd yolov10/ pip3 install -e . --no-deps -cd .. +cd ../ python3 export.py --weight yolov10s.pt --batch 32 @@ -51,4 +51,4 @@ bash scripts/infer_yolov10_fp16_performance.sh ## References -YOLOv10: +- [YOLOv10](https://docs.ultralytics.com/models/yolov10) diff --git a/models/cv/object_detection/yolov11/igie/README.md b/models/cv/object_detection/yolov11/igie/README.md index 9b93f426..96cb5385 100644 --- a/models/cv/object_detection/yolov11/igie/README.md +++ b/models/cv/object_detection/yolov11/igie/README.md @@ -1,4 +1,4 @@ -# YOLOv11 +# YOLOv11 (IGIE) ## Model Description @@ -6,16 +6,16 @@ YOLOv11 is the latest generation of the YOLO (You Only Look Once) series object ## Model Preparation +### Prepare Resources + +Pretrained model: + ### Install Dependencies ```bash pip3 install -r requirements.txt ``` -### Prepare Resources - -Pretrained model: - ## Model Conversion ```bash diff --git a/models/cv/object_detection/yolov3/igie/README.md b/models/cv/object_detection/yolov3/igie/README.md index fb487dcc..566e8052 100644 --- a/models/cv/object_detection/yolov3/igie/README.md +++ b/models/cv/object_detection/yolov3/igie/README.md @@ -1,4 +1,4 @@ -# YOLOv3 +# YOLOv3 (IGIE) ## Model Description @@ -6,6 +6,12 @@ YOLOv3 is a influential object detection algorithm.The key innovation of YOLOv3 ## Model Preparation +### Prepare Resources + +Pretrained model: + +Dataset: to download the validation dataset. + ### Install Dependencies ```bash @@ -18,12 +24,6 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Prepare Resources - -Pretrained model: - -Dataset: to download the validation dataset. - ### Model Conversion ```bash @@ -59,7 +59,7 @@ bash scripts/infer_yolov3_int8_performance.sh ## Model Results -Model |BatchSize |Precision |FPS |MAP@0.5 |MAP@0.5:0.95 | ---------|-----------|----------|---------|---------|-------------| -YOLOv3 | 32 | FP16 | 312.47 | 0.658 | 0.467 | -YOLOv3 | 32 | INT8 | 711.72 | 0.639 | 0.427 | +| Model | BatchSize | Precision | FPS | MAP@0.5 | MAP@0.5:0.95 | +|--------|-----------|-----------|--------|---------|--------------| +| YOLOv3 | 32 | FP16 | 312.47 | 0.658 | 0.467 | +| YOLOv3 | 32 | INT8 | 711.72 | 0.639 | 0.427 | diff --git a/models/cv/object_detection/yolov3/ixrt/README.md b/models/cv/object_detection/yolov3/ixrt/README.md index 1f9b85c2..fd429df1 100644 --- a/models/cv/object_detection/yolov3/ixrt/README.md +++ b/models/cv/object_detection/yolov3/ixrt/README.md @@ -1,4 +1,4 @@ -# YOLOv3 +# YOLOv3 (IxRT) ## Model Description @@ -6,6 +6,15 @@ YOLOv3 is a influential object detection algorithm.The key innovation of YOLOv3 ## Model Preparation +### Prepare Resources + +Pretrained model: + +Dataset: to download the validation dataset. + +- val2017: Path/To/val2017/*.jpg +- annotations: Path/To/annotations/instances_val2017.json + ### Install Dependencies ```bash @@ -18,15 +27,6 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Prepare Resources - -Pretrained model: - -Dataset: to download the validation dataset. - -- 图片目录: Path/To/val2017/*.jpg -- 标注文件目录: Path/To/annotations/instances_val2017.json - ### Model Conversion ```bash @@ -73,7 +73,7 @@ bash scripts/infer_yolov3_int8_performance.sh ## Model Results -Model |BatchSize |Precision |FPS |MAP@0.5 |MAP@0.5:0.95 | ---------|-----------|----------|---------|----------|-------------| -YOLOv3 | 32 | FP16 | 757.11 | 0.663 | 0.381 | -YOLOv3 | 32 | INT8 | 1778.34 | 0.659 | 0.356 | +| Model | BatchSize | Precision | FPS | MAP@0.5 | MAP@0.5:0.95 | +|--------|-----------|-----------|---------|---------|--------------| +| YOLOv3 | 32 | FP16 | 757.11 | 0.663 | 0.381 | +| YOLOv3 | 32 | INT8 | 1778.34 | 0.659 | 0.356 | diff --git a/models/cv/object_detection/yolov4/igie/README.md b/models/cv/object_detection/yolov4/igie/README.md index 5be19a01..cdb0c58e 100644 --- a/models/cv/object_detection/yolov4/igie/README.md +++ b/models/cv/object_detection/yolov4/igie/README.md @@ -1,4 +1,4 @@ -# YOLOv4 +# YOLOv4 (IGIE) ## Model Description @@ -6,6 +6,13 @@ YOLOv4 employs a two-step process, involving regression for bounding box positio ## Model Preparation +### Prepare Resources + +Pretrained cfg: +Pretrained model: + +Dataset: to download the validation dataset. + ### Install Dependencies ```bash @@ -18,13 +25,6 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Prepare Resources - -Pretrained cfg: -Pretrained model: - -Dataset: to download the validation dataset. - ### Model Conversion ```bash @@ -64,12 +64,12 @@ bash scripts/infer_yolov4_int8_performance.sh ## Model Results -Model |BatchSize |Precision |FPS |MAP@0.5 |MAP@0.5:0.95 | ---------|-----------|----------|----------|----------|-------------| -yolov4 | 32 | FP16 |285.218 | 0.741 | 0.506 | -yolov4 | 32 | INT8 |413.320 | 0.721 | 0.463 | +| Model | BatchSize | Precision | FPS | MAP@0.5 | MAP@0.5:0.95 | +|--------|-----------|-----------|---------|---------|--------------| +| YOLOv4 | 32 | FP16 | 285.218 | 0.741 | 0.506 | +| YOLOv4 | 32 | INT8 | 413.320 | 0.721 | 0.463 | ## References -DarkNet: -Pytorch-YOLOv4: +- [darknet](https://github.com/AlexeyAB/darknet) +- [pytorch-YOLOv4](https://github.com/Tianxiaomo/pytorch-YOLOv4) diff --git a/models/cv/object_detection/yolov4/ixrt/README.md b/models/cv/object_detection/yolov4/ixrt/README.md index 6bffbbdb..4bf799c8 100644 --- a/models/cv/object_detection/yolov4/ixrt/README.md +++ b/models/cv/object_detection/yolov4/ixrt/README.md @@ -1,4 +1,4 @@ -# YOLOv4 +# YOLOv4 (IxRT) ## Model Description @@ -6,6 +6,13 @@ YOLOv4 employs a two-step process, involving regression for bounding box positio ## Model Preparation +### Prepare Resources + +Pretrained cfg: +Pretrained model: + +Dataset: to download the validation dataset. + ### Install Dependencies ```bash @@ -18,13 +25,6 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Prepare Resources - -Pretrained cfg: -Pretrained model: - -Dataset: to download the validation dataset. - ### Model Conversion ```bash @@ -74,5 +74,5 @@ bash scripts/infer_yolov4_int8_performance.sh ## References -DarkNet: -Pytorch-YOLOv4: +- [darknet](https://github.com/AlexeyAB/darknet) +- [pytorch-YOLOv4](https://github.com/Tianxiaomo/pytorch-YOLOv4) diff --git a/models/cv/object_detection/yolov5/igie/README.md b/models/cv/object_detection/yolov5/igie/README.md index 1465d40b..07f8ef3c 100644 --- a/models/cv/object_detection/yolov5/igie/README.md +++ b/models/cv/object_detection/yolov5/igie/README.md @@ -1,4 +1,4 @@ -# YOLOv5-m +# YOLOv5-m (IGIE) ## Model Description @@ -6,6 +6,12 @@ The YOLOv5 architecture is designed for efficient and accurate object detection ## Model Preparation +### Prepare Resources + +Pretrained model: + +Dataset: to download the validation dataset. + ### Install Dependencies ```bash @@ -18,12 +24,6 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Prepare Resources - -Pretrained model: - -Dataset: to download the validation dataset. - ### Model Conversion ```bash @@ -59,7 +59,7 @@ bash scripts/infer_yolov5_int8_performance.sh ## Model Results -Model |BatchSize |Precision |FPS |MAP@0.5 |MAP@0.5:0.95 | ---------|-----------|----------|---------|----------|-------------| -YOLOv5m | 32 | FP16 | 533.53 | 0.639 | 0.451 | -YOLOv5m | 32 | INT8 | 969.53 | 0.624 | 0.428 | +| Model | BatchSize | Precision | FPS | MAP@0.5 | MAP@0.5:0.95 | +|---------|-----------|-----------|--------|---------|--------------| +| YOLOv5m | 32 | FP16 | 533.53 | 0.639 | 0.451 | +| YOLOv5m | 32 | INT8 | 969.53 | 0.624 | 0.428 | diff --git a/models/cv/object_detection/yolov5/ixrt/README.md b/models/cv/object_detection/yolov5/ixrt/README.md index d55114a5..57ebca96 100644 --- a/models/cv/object_detection/yolov5/ixrt/README.md +++ b/models/cv/object_detection/yolov5/ixrt/README.md @@ -1,4 +1,4 @@ -# YOLOv5-m +# YOLOv5-m (IxRT) ## Model Description @@ -6,6 +6,15 @@ The YOLOv5 architecture is designed for efficient and accurate object detection ## Model Preparation +### Prepare Resources + +Pretrained model: + +Dataset: to download the validation dataset. + +- val2017: Path/To/val2017/*.jpg +- annotations: Path/To/annotations/instances_val2017.json + ### Install Dependencies ```bash @@ -18,15 +27,6 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Prepare Resources - -Pretrained model: - -Dataset: to download the validation dataset. - -- 图片目录: Path/To/val2017/*.jpg -- 标注文件目录: Path/To/annotations/instances_val2017.json - ### Model Conversion ```bash @@ -77,7 +77,7 @@ bash scripts/infer_yolov5_int8_performance.sh ## Model Results -Model |BatchSize |Precision |FPS |MAP@0.5 |MAP@0.5:0.95 | ---------|-----------|----------|---------|----------|-------------| -YOLOv5 | 32 | FP16 | 680.93 | 0.637 | 0.447 | -YOLOv5 | 32 | INT8 | 1328.50 | 0.627 | 0.425 | +| Model | BatchSize | Precision | FPS | MAP@0.5 | MAP@0.5:0.95 | +|--------|-----------|-----------|---------|---------|--------------| +| YOLOv5 | 32 | FP16 | 680.93 | 0.637 | 0.447 | +| YOLOv5 | 32 | INT8 | 1328.50 | 0.627 | 0.425 | diff --git a/models/cv/object_detection/yolov5s/ixrt/README.md b/models/cv/object_detection/yolov5s/ixrt/README.md index a1f5cb8e..b4082db0 100755 --- a/models/cv/object_detection/yolov5s/ixrt/README.md +++ b/models/cv/object_detection/yolov5s/ixrt/README.md @@ -1,4 +1,4 @@ -# YOLOv5s +# YOLOv5s (IxRT) ## Model Description @@ -6,6 +6,12 @@ The YOLOv5 architecture is designed for efficient and accurate object detection ## Model Preparation +### Prepare Resources + +Pretrained model: + +Dataset: to download the validation dataset. + ### Install Dependencies ```bash @@ -18,12 +24,6 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Prepare Resources - -Pretrained model: - -Dataset: to download the validation dataset. - ### Model Conversion ```bash @@ -76,7 +76,7 @@ bash scripts/infer_yolov5s_int8_performance.sh ## Model Results -Model |BatchSize |Precision |FPS |MAP@0.5 |MAP@0.5:0.95 | ---------|-----------|----------|---------|----------|-------------| -YOLOv5s | 32 | FP16 | 1112.66 | 0.565 | 0.370 | -YOLOv5s | 32 | INT8 | 2440.54 | 0.557 | 0.351 | +| Model | BatchSize | Precision | FPS | MAP@0.5 | MAP@0.5:0.95 | +|---------|-----------|-----------|---------|---------|--------------| +| YOLOv5s | 32 | FP16 | 1112.66 | 0.565 | 0.370 | +| YOLOv5s | 32 | INT8 | 2440.54 | 0.557 | 0.351 | diff --git a/models/cv/object_detection/yolov6/igie/README.md b/models/cv/object_detection/yolov6/igie/README.md index eb186bdd..4d2982ac 100644 --- a/models/cv/object_detection/yolov6/igie/README.md +++ b/models/cv/object_detection/yolov6/igie/README.md @@ -1,4 +1,4 @@ -# YOLOv6 +# YOLOv6 (IGIE) ## Model Description @@ -6,6 +6,12 @@ YOLOv6 integrates cutting-edge object detection advancements from industry and a ## Model Preparation +### Prepare Resources + +Pretrained model: + +Dataset: to download the validation dataset. + ### Install Dependencies ```bash @@ -18,12 +24,6 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Prepare Resources - -Pretrained model: - -Dataset: to download the validation dataset. - ### Model Conversion ```bash @@ -55,10 +55,10 @@ bash scripts/infer_yolov6_fp16_performance.sh ## Model Results -Model |BatchSize |Precision |FPS |MAP@0.5 |MAP@0.5:0.95 | ----------|-----------|----------|----------|----------|-------------| -yolov6 | 32 | FP16 | 994.902 | 0.617 | 0.448 | +| Model | BatchSize | Precision | FPS | MAP@0.5 | MAP@0.5:0.95 | +|--------|-----------|-----------|---------|---------|--------------| +| YOLOv6 | 32 | FP16 | 994.902 | 0.617 | 0.448 | ## References -YOLOv6: +- [YOLOv6](https://github.com/meituan/YOLOv6) diff --git a/models/cv/object_detection/yolov6/ixrt/README.md b/models/cv/object_detection/yolov6/ixrt/README.md index cdcbe306..3df05941 100644 --- a/models/cv/object_detection/yolov6/ixrt/README.md +++ b/models/cv/object_detection/yolov6/ixrt/README.md @@ -1,4 +1,4 @@ -# YOLOv6 +# YOLOv6 (IxRT) ## Model Description @@ -6,6 +6,12 @@ YOLOv6 integrates cutting-edge object detection advancements from industry and a ## Model Preparation +### Prepare Resources + +Pretrained model: + +Dataset: to download the validation dataset. + ### Install Dependencies ```bash @@ -18,12 +24,6 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Prepare Resources - -Pretrained model: - -Dataset: to download the validation dataset. - ```bash # get yolov6s.pt wget https://github.com/meituan/YOLOv6/releases/download/0.4.0/yolov6s.pt @@ -73,10 +73,10 @@ bash scripts/infer_yolov6_int8_performance.sh ## Model Results | Model | BatchSize | Precision | FPS | MAP@0.5 | -| ------ | --------- | --------- | -------- | ------- | +|--------|-----------|-----------|----------|---------| | YOLOv6 | 32 | FP16 | 1107.511 | 0.617 | | YOLOv6 | 32 | INT8 | 2080.475 | 0.583 | ## References -YOLOv6: +- [YOLOv6](https://github.com/meituan/YOLOv6) diff --git a/models/cv/object_detection/yolov7/igie/README.md b/models/cv/object_detection/yolov7/igie/README.md index 6c97ab60..bfad733e 100644 --- a/models/cv/object_detection/yolov7/igie/README.md +++ b/models/cv/object_detection/yolov7/igie/README.md @@ -1,4 +1,4 @@ -# YOLOv7 +# YOLOv7 (IGIE) ## Model Description @@ -6,6 +6,12 @@ YOLOv7 is a state-of-the-art real-time object detector that surpasses all known ## Model Preparation +### Prepare Resources + +Pretrained model: + +Dataset: to download the validation dataset. + ### Install Dependencies ```bash @@ -18,12 +24,6 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Prepare Resources - -Pretrained model: - -Dataset: to download the validation dataset. - ### Model Conversion ```bash @@ -63,11 +63,11 @@ bash scripts/infer_yolov7_int8_performance.sh ## Model Results -Model |BatchSize |Precision |FPS |MAP@0.5 |MAP@0.5:0.95 | ---------|-----------|----------|----------|----------|-------------| -yolov7 | 32 | FP16 |341.681 | 0.695 | 0.509 | -yolov7 | 32 | INT8 |669.783 | 0.685 | 0.473 | +| Model | BatchSize | Precision | FPS | MAP@0.5 | MAP@0.5:0.95 | +|--------|-----------|-----------|---------|---------|--------------| +| YOLOv7 | 32 | FP16 | 341.681 | 0.695 | 0.509 | +| YOLOv7 | 32 | INT8 | 669.783 | 0.685 | 0.473 | ## References -YOLOv7: +- [YOLOv7](https://github.com/WongKinYiu/yolov7) diff --git a/models/cv/object_detection/yolov7/ixrt/README.md b/models/cv/object_detection/yolov7/ixrt/README.md index 1ea58544..b3b62a6a 100644 --- a/models/cv/object_detection/yolov7/ixrt/README.md +++ b/models/cv/object_detection/yolov7/ixrt/README.md @@ -1,4 +1,4 @@ -# YOLOv7 +# YOLOv7 (IxRT) ## Model Description @@ -6,6 +6,15 @@ YOLOv7 is an object detection model based on the YOLO (You Only Look Once) serie ## Model Preparation +### Prepare Resources + +Pretrained model: + +Dataset: to download the validation dataset. + +- val2017: Path/To/val2017/*.jpg +- annotations: Path/To/annotations/instances_val2017.json + ### Install Dependencies ```bash @@ -18,15 +27,6 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Prepare Resources - -Pretrained model: - -Dataset: to download the validation dataset. - -- 图片目录: Path/To/val2017/*.jpg -- 标注文件目录: Path/To/annotations/instances_val2017.json - ### Model Conversion ```bash @@ -70,7 +70,11 @@ bash scripts/infer_yolov7_int8_performance.sh ## Model Results -Model |BatchSize |Precision |FPS |MAP@0.5 |MAP@0.5:0.95 | ---------|-----------|----------|---------|----------|-------------| -YOLOv7 | 32 | FP16 | 375.41 | 0.693 | 0.506 | -YOLOv7 | 32 | INT8 | 816.71 | 0.688 | 0.471 | +| Model | BatchSize | Precision | FPS | MAP@0.5 | MAP@0.5:0.95 | +|--------|-----------|-----------|--------|---------|--------------| +| YOLOv7 | 32 | FP16 | 375.41 | 0.693 | 0.506 | +| YOLOv7 | 32 | INT8 | 816.71 | 0.688 | 0.471 | + +## References + +- [YOLOv7](https://github.com/WongKinYiu/yolov7) diff --git a/models/cv/object_detection/yolov8/igie/README.md b/models/cv/object_detection/yolov8/igie/README.md index fc8fcaf4..eff4ecdf 100644 --- a/models/cv/object_detection/yolov8/igie/README.md +++ b/models/cv/object_detection/yolov8/igie/README.md @@ -1,4 +1,4 @@ -# YOLOv8 +# YOLOv8 (IGIE) ## Model Description @@ -6,6 +6,12 @@ Yolov8 combines speed and accuracy in real-time object detection tasks. With a f ## Model Preparation +### Prepare Resources + +Pretrained model: + +Dataset: to download the validation dataset. + ### Install Dependencies ```bash @@ -18,12 +24,6 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Prepare Resources - -Pretrained model: - -Dataset: to download the validation dataset. - ### Model Conversion ```bash @@ -56,7 +56,7 @@ bash scripts/infer_yolov8_int8_performance.sh ## Model Results -Model |BatchSize |Precision |FPS |MAP@0.5 |MAP@0.5:0.95 | ---------|-----------|----------|----------|----------|-------------| -yolov8 | 32 | FP16 | 1002.98 | 0.617 | 0.449 | -yolov8 | 32 | INT8 | 1392.29 | 0.604 | 0.429 | +| Model | BatchSize | Precision | FPS | MAP@0.5 | MAP@0.5:0.95 | +|--------|-----------|-----------|---------|---------|--------------| +| YOLOv8 | 32 | FP16 | 1002.98 | 0.617 | 0.449 | +| YOLOv8 | 32 | INT8 | 1392.29 | 0.604 | 0.429 | diff --git a/models/cv/object_detection/yolov8/ixrt/README.md b/models/cv/object_detection/yolov8/ixrt/README.md index fdf1ef95..09f2cc99 100644 --- a/models/cv/object_detection/yolov8/ixrt/README.md +++ b/models/cv/object_detection/yolov8/ixrt/README.md @@ -1,4 +1,4 @@ -# YOLOv8 +# YOLOv8 (IxRT) ## Model Description @@ -6,6 +6,12 @@ Yolov8 combines speed and accuracy in real-time object detection tasks. With a f ## Model Preparation +### Prepare Resources + +Pretrained model: + +Dataset: to download the validation dataset. + ### Install Dependencies ```bash @@ -18,12 +24,6 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Prepare Resources - -Pretrained model: - -Dataset: to download the validation dataset. - ### Model Conversion ```bash @@ -63,6 +63,6 @@ bash scripts/infer_yolov8_int8_performance.sh ## Model Results | Model | BatchSize | Precision | FPS | MAP@0.5 | -| ------ | --------- | --------- | -------- | ------- | +|--------|-----------|-----------|----------|---------| | YOLOv8 | 32 | FP16 | 1511.366 | 0.525 | | YOLOv8 | 32 | INT8 | 1841.017 | 0.517 | diff --git a/models/cv/object_detection/yolov9/igie/README.md b/models/cv/object_detection/yolov9/igie/README.md index c8ef1785..5a11d80b 100644 --- a/models/cv/object_detection/yolov9/igie/README.md +++ b/models/cv/object_detection/yolov9/igie/README.md @@ -1,4 +1,4 @@ -# YOLOv9 +# YOLOv9 (IGIE) ## Model Description @@ -6,16 +6,16 @@ YOLOv9 represents a major leap in real-time object detection by introducing inno ## Model Preparation +### Prepare Resources + +Pretrained model: + ### Install Dependencies ```bash pip3 install -r requirements.txt ``` -### Prepare Resources - -Pretrained model: - ## Model Conversion ```bash @@ -45,4 +45,4 @@ bash scripts/infer_yolov9_fp16_performance.sh ## References -YOLOv9: +- [YOLOv9](https://docs.ultralytics.com/models/yolov9) diff --git a/models/cv/object_detection/yolox/igie/README.md b/models/cv/object_detection/yolox/igie/README.md index 919f1bc7..598c97b2 100644 --- a/models/cv/object_detection/yolox/igie/README.md +++ b/models/cv/object_detection/yolox/igie/README.md @@ -1,4 +1,4 @@ -# YOLOX +# YOLOX (IGIE) ## Model Description @@ -6,6 +6,12 @@ YOLOX is an anchor-free version of YOLO, with a simpler design but better perfor ## Model Preparation +### Prepare Resources + +Pretrained model: + +Dataset: to download the validation dataset. + ### Install Dependencies ```bash @@ -21,24 +27,18 @@ pip3 install -r requirements.txt source /opt/rh/devtoolset-7/enable ``` -### Prepare Resources - -Pretrained model: - -Dataset: to download the validation dataset. - ### Model Conversion ```bash # install yolox git clone https://github.com/Megvii-BaseDetection/YOLOX.git -cd YOLOX +cd YOLOX/ python3 setup.py develop # export onnx model python3 tools/export_onnx.py -c ../yolox_m.pth -o 13 -n yolox-m --input input --output output --dynamic --output-name ../yolox.onnx -cd .. +cd ../ ``` ## Model Inference @@ -67,11 +67,11 @@ bash scripts/infer_yolox_int8_performance.sh ## Model Results -Model |BatchSize |Precision |FPS |MAP@0.5 | ---------|-----------|----------|----------|----------| -yolox | 32 | FP16 |409.517 | 0.656 | -yolox | 32 | INT8 |844.991 | 0.637 | +| Model | BatchSize | Precision | FPS | MAP@0.5 | +|-------|-----------|-----------|---------|---------| +| YOLOX | 32 | FP16 | 409.517 | 0.656 | +| YOLOX | 32 | INT8 | 844.991 | 0.637 | ## References -YOLOX: +- [YOLOX](https://github.com/Megvii-BaseDetection/YOLOX) diff --git a/models/cv/object_detection/yolox/ixrt/README.md b/models/cv/object_detection/yolox/ixrt/README.md index 42313aa8..9104b2e8 100644 --- a/models/cv/object_detection/yolox/ixrt/README.md +++ b/models/cv/object_detection/yolox/ixrt/README.md @@ -1,4 +1,4 @@ -# YOLOX +# YOLOX (IxRT) ## Model Description @@ -7,6 +7,12 @@ For more details, please refer to our [report on Arxiv](https://arxiv.org/abs/21 ## Model Preparation +### Prepare Resources + +Pretrained model: + +Dataset: to download the validation dataset. + ### Install Dependencies ```bash @@ -19,12 +25,6 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Prepare Resources - -Pretrained model: - -Dataset: to download the validation dataset. - ### Model Conversion ```bash @@ -75,11 +75,11 @@ bash scripts/infer_yolox_int8_performance.sh ## Model Results -Model |BatchSize |Precision |FPS |MAP@0.5 | ---------|-----------|----------|----------|----------| -yolox | 32 | FP16 | 424.53 | 0.656 | -yolox | 32 | INT8 | 832.16 | 0.647 | +| Model | BatchSize | Precision | FPS | MAP@0.5 | +|-------|-----------|-----------|--------|---------| +| YOLOX | 32 | FP16 | 424.53 | 0.656 | +| YOLOX | 32 | INT8 | 832.16 | 0.647 | ## References -YOLOX: +- [YOLOX](https://github.com/Megvii-BaseDetection/YOLOX) diff --git a/models/cv/ocr/kie_layoutxlm/igie/README.md b/models/cv/ocr/kie_layoutxlm/igie/README.md index c22a573a..4ef5301c 100644 --- a/models/cv/ocr/kie_layoutxlm/igie/README.md +++ b/models/cv/ocr/kie_layoutxlm/igie/README.md @@ -1,4 +1,4 @@ -# LayoutXLM +# LayoutXLM (IGIE) ## Model Description @@ -6,20 +6,19 @@ LayoutXLM is a groundbreaking multimodal pre-trained model for multilingual docu ## Model Preparation -```shell -pip3 install -r requirements.txt -``` - -## Download +### Prepare Resources Pretrained model: Dataset: to download the XFUND_zh dataset. -## Model Conversion +```bash +pip3 install -r requirements.txt +``` -```shell +## Model Conversion +```bash tar -xf ser_vi_layoutxlm_xfund_pretrained.tar tar -xf XFUND.tar @@ -35,7 +34,7 @@ python3 tools/export_model.py -c configs/kie/vi_layoutxlm/ser_vi_layoutxlm_xfund # Export the inference model to onnx model paddle2onnx --model_dir ./inference/ser_vi_layoutxlm --model_filename inference.pdmodel --params_filename inference.pdiparams --save_file ../kie_ser.onnx --opset_version 11 --enable_onnx_checker True -cd .. +cd ../ # Use onnxsim optimize onnx model onnxsim kie_ser.onnx kie_ser_opt.onnx @@ -49,7 +48,7 @@ export DATASETS_DIR=/Path/to/XFUND/ ### FP16 -```shell +```bash # Accuracy bash scripts/infer_kie_layoutxlm_fp16_accuracy.sh # Performance @@ -64,4 +63,4 @@ bash scripts/infer_kie_layoutxlm_fp16_performance.sh ## References -PaddleOCR: +- [PaddleOCR](https://github.com/PaddlePaddle/PaddleOCR/blob/main/docs/algorithm/kie/algorithm_kie_layoutxlm.md) diff --git a/models/cv/ocr/svtr/igie/README.md b/models/cv/ocr/svtr/igie/README.md index 5502ef33..790e3799 100644 --- a/models/cv/ocr/svtr/igie/README.md +++ b/models/cv/ocr/svtr/igie/README.md @@ -1,9 +1,18 @@ -# SVTR +# SVTR (IGIE) + ## Model Description + SVTR proposes a single vision model for scene text recognition. This model completely abandons sequence modeling within the patch-wise image tokenization framework. Under the premise of competitive accuracy, the model has fewer parameters and faster speed. ## Model Preparation -```shell + +### Prepare Resources + +Pretrained model: + +Dataset: to download the lmdb evaluation datasets. + +```bash # Install libGL ## CentOS yum install -y mesa-libGL @@ -13,18 +22,14 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -## Download -Pretrained model: - -Dataset: to download the lmdb evaluation datasets. - ## Model Conversion -```shell + +```bash tar -xf rec_svtr_tiny_none_ctc_en_train.tar git clone -b release/2.6 https://github.com/PaddlePaddle/PaddleOCR.git --depth=1 -cd PaddleOCR +cd PaddleOCR/ # Export the trained model into inference model python3 tools/export_model.py -c ../rec_svtr_tiny_6local_6global_stn_en.yml -o Global.pretrained_model=../rec_svtr_tiny_none_ctc_en_train/best_accuracy Global.save_inference_dir=./inference/rec_svtr_tiny @@ -32,18 +37,21 @@ python3 tools/export_model.py -c ../rec_svtr_tiny_6local_6global_stn_en.yml -o G # Export the inference model to onnx model paddle2onnx --model_dir ./inference/rec_svtr_tiny --model_filename inference.pdmodel --params_filename inference.pdiparams --save_file ../SVTR.onnx --opset_version 13 --enable_onnx_checker True -cd .. +cd ../ # Use onnxsim optimize onnx model onnxsim SVTR.onnx SVTR_opt.onnx -``` +``` ## Model Inference -```shell + +```bash export DATASETS_DIR=/Path/to/lmdb_evaluation/ ``` + ### FP16 -```shell + +```bash # Accuracy bash scripts/infer_svtr_fp16_accuracy.sh # Performance @@ -51,9 +59,11 @@ bash scripts/infer_svtr_fp16_performance.sh ``` ## Model Results -Model |BatchSize |Precision |FPS |Acc | ---------|-----------|----------|----------|----------| -SVTR | 32 | FP16 | 4936.47 | 88.29% | + +| Model | BatchSize | Precision | FPS | Acc | +|-------|-----------|-----------|---------|--------| +| SVTR | 32 | FP16 | 4936.47 | 88.29% | ## References -PaddleOCR: https://github.com/PaddlePaddle/PaddleOCR/blob/main/docs/algorithm/text_recognition/algorithm_rec_svtr.md + +- [PaddleOCR](https://github.com/PaddlePaddle/PaddleOCR/blob/main/docs/algorithm/text_recognition/algorithm_rec_svtr.md) diff --git a/models/cv/pose_estimation/hrnetpose/igie/README.md b/models/cv/pose_estimation/hrnetpose/igie/README.md index 3247e11f..7833e893 100644 --- a/models/cv/pose_estimation/hrnetpose/igie/README.md +++ b/models/cv/pose_estimation/hrnetpose/igie/README.md @@ -1,4 +1,4 @@ -# HRNetPose +# HRNetPose (IGIE) ## Model Description @@ -6,6 +6,16 @@ HRNetPose (High-Resolution Network for Pose Estimation) is a high-performance hu ## Model Preparation +### Prepare Resources + +Pretrained model: + +Dataset: to download the validation dataset. + +```bash +wget https://download.openmmlab.com/mmpose/top_down/hrnet/hrnet_w32_coco_256x192-c78dce93_20200708.pth +``` + ### Install Dependencies ```bash @@ -18,16 +28,6 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Prepare Resources - -Pretrained model: - -Dataset: to download the validation dataset. - -```bash -wget https://download.openmmlab.com/mmpose/top_down/hrnet/hrnet_w32_coco_256x192-c78dce93_20200708.pth -``` - ### Model Conversion ```bash @@ -55,10 +55,10 @@ bash scripts/infer_hrnetpose_fp16_performance.sh ## Model Results -| Model | BatchSize | Input Shape | Precision | FPS | mAP@0.5(%) | -| :---------: | :-------: | :---------: | :-------: | :-------: | :--------: | -| HRNetPose | 32 | 252x196 | FP16 | 1831.20 | 0.926 | +| Model | BatchSize | Input Shape | Precision | FPS | mAP@0.5(%) | +|-----------|-----------|-------------|-----------|---------|------------| +| HRNetPose | 32 | 252x196 | FP16 | 1831.20 | 0.926 | ## References -mmpose: +- [mmpose](https://github.com/open-mmlab/mmpose.git) diff --git a/models/cv/pose_estimation/lightweight_openpose/ixrt/README.md b/models/cv/pose_estimation/lightweight_openpose/ixrt/README.md index 414d6bcd..d335f055 100644 --- a/models/cv/pose_estimation/lightweight_openpose/ixrt/README.md +++ b/models/cv/pose_estimation/lightweight_openpose/ixrt/README.md @@ -1,4 +1,4 @@ -# Lightweight OpenPose +# Lightweight OpenPose (IxRT) ## Model Description @@ -10,6 +10,11 @@ inference (no flip or any post-processing done). ## Model Preparation +### Prepare Resources + +- dataset: +- checkpoints: + ### Install Dependencies ```bash @@ -22,11 +27,6 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Prepare Resources - -- dataset: -- checkpoints: - ### Model Conversion ```bash @@ -64,4 +64,4 @@ bash scripts/infer_lightweight_openpose_fp16_performance.sh ## References - +- [lightweight-human-pose-estimation](https://github.com/Daniil-Osokin/lightweight-human-pose-estimation.pytorch) diff --git a/models/cv/pose_estimation/rtmpose/igie/README.md b/models/cv/pose_estimation/rtmpose/igie/README.md index 3681d7a3..9fdc4996 100644 --- a/models/cv/pose_estimation/rtmpose/igie/README.md +++ b/models/cv/pose_estimation/rtmpose/igie/README.md @@ -1,4 +1,4 @@ -# RTMPose +# RTMPose (IGIE) ## Model Description @@ -6,6 +6,16 @@ RTMPose, a state-of-the-art framework developed by Shanghai AI Laboratory, excel ## Model Preparation +### Prepare Resources + +Pretrained model: + +Dataset: to download the validation dataset. + +```bash +wget https://download.openmmlab.com/mmpose/v1/projects/rtmposev1/rtmpose-m_simcc-aic-coco_pt-aic-coco_420e-256x192-63eb25f7_20230126.pth +``` + ### Install Dependencies ```bash @@ -18,16 +28,6 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Prepare Resources - -Pretrained model: - -Dataset: to download the validation dataset. - -```bash -wget https://download.openmmlab.com/mmpose/v1/projects/rtmposev1/rtmpose-m_simcc-aic-coco_pt-aic-coco_420e-256x192-63eb25f7_20230126.pth -``` - ### Model Conversion ```bash @@ -55,11 +55,10 @@ bash scripts/infer_rtmpose_fp16_performance.sh ## Model Results -Model |BatchSize |Precision |FPS |IOU@0.5 |IOU@0.5:0.95 | -----------|-----------|----------|----------|----------|---------------| -RTMPose | 32 | FP16 | 2313.33 | 0.936 | 0.773 | - +| Model | BatchSize | Precision | FPS | IOU@0.5 | IOU@0.5:0.95 | +|---------|-----------|-----------|---------|---------|--------------| +| RTMPose | 32 | FP16 | 2313.33 | 0.936 | 0.773 | ## References -mmpose: +- [mmpose](https://github.com/open-mmlab/mmpose.git) diff --git a/models/cv/pose_estimation/rtmpose/ixrt/README.md b/models/cv/pose_estimation/rtmpose/ixrt/README.md index 529b9fae..a11d6e08 100644 --- a/models/cv/pose_estimation/rtmpose/ixrt/README.md +++ b/models/cv/pose_estimation/rtmpose/ixrt/README.md @@ -1,4 +1,4 @@ -# RTMPose +# RTMPose (IxRT) ## Model Description @@ -6,6 +6,12 @@ RTMPose, a state-of-the-art framework developed by Shanghai AI Laboratory, excel ## Model Preparation +### Prepare Resources + +Pretrained model: + +Dataset: to download the validation dataset. + ### Install Dependencies ```bash @@ -18,12 +24,6 @@ apt install -y libgl1-mesa-glx pip3 install -r requirements.txt ``` -### Prepare Resources - -Pretrained model: - -Dataset: to download the validation dataset. - ## Model Conversion ```bash diff --git a/models/multimodal/diffusion_model/stable-diffusion/README.md b/models/multimodal/diffusion_model/stable-diffusion/README.md index 378081a2..4d6de94f 100644 --- a/models/multimodal/diffusion_model/stable-diffusion/README.md +++ b/models/multimodal/diffusion_model/stable-diffusion/README.md @@ -6,6 +6,16 @@ Stable Diffusion is a latent text-to-image diffusion model capable of generating ## Model Preparation +### Prepare Resources + +Download the runwayml/stable-diffusion-v1-5 from [huggingface page](https://huggingface.co/runwayml/stable-diffusion-v1-5). + +```bash +cd stable-diffusion +mkdir -p data/ +ln -s /path/to/stable-diffusion-v1-5 ./data/ +``` + ### Install Dependencies ```bash @@ -19,16 +29,6 @@ pip3 install http://files.deepspark.org.cn:880/deepspark/add-ons/diffusers-0.31. pip3 install -r requirements.txt ``` -### Prepare Resources - -Download the runwayml/stable-diffusion-v1-5 from [huggingface page](https://huggingface.co/runwayml/stable-diffusion-v1-5). - -```bash -cd stable-diffusion -mkdir -p data/ -ln -s /path/to/stable-diffusion-v1-5 ./data/ -``` - ## Model Inference ```bash diff --git a/models/multimodal/vision_language_model/chameleon_7b/vllm/README.md b/models/multimodal/vision_language_model/chameleon_7b/vllm/README.md index a7ee5fbc..b98b6c75 100755 --- a/models/multimodal/vision_language_model/chameleon_7b/vllm/README.md +++ b/models/multimodal/vision_language_model/chameleon_7b/vllm/README.md @@ -6,6 +6,15 @@ Chameleon, an AI system that mitigates these limitations by augmenting LLMs with ## Model Preparation +### Prepare Resources + +- Model: + +```bash +# Download model from the website and make sure the model's path is "data/chameleon-7b" +mkdir data +``` + ### Install Dependencies In order to run the model smoothly, you need to get the sdk from [resource center](https://support.iluvatar.com/#/ProductLine?id=2) of Iluvatar CoreX official website. @@ -18,15 +27,6 @@ yum install -y mesa-libGL apt install -y libgl1-mesa-glx ``` -### Prepare Resources - -- Model: - -```bash -# Download model from the website and make sure the model's path is "data/chameleon-7b" -mkdir data -``` - ## Model Inference ```bash diff --git a/models/multimodal/vision_language_model/clip/ixformer/README.md b/models/multimodal/vision_language_model/clip/ixformer/README.md index 2d768606..3a8a9c9d 100644 --- a/models/multimodal/vision_language_model/clip/ixformer/README.md +++ b/models/multimodal/vision_language_model/clip/ixformer/README.md @@ -6,6 +6,16 @@ CLIP (Contrastive Language-Image Pre-Training) is a neural network trained on a ## Model Preparation +### Prepare Resources + +Pretrained model: Go to the website to find the pre-trained model you need. Here, we choose clip-vit-base-patch32. + +```bash +# Download model from the website and make sure the model's path is "data/clip-vit-base-patch32" +mkdir -p data +unzip clip-vit-base-patch32.zip -d data/ +``` + ### Install Dependencies In order to run the model smoothly, you need to get the sdk from [resource center](https://support.iluvatar.com/#/ProductLine?id=2) of Iluvatar CoreX official website. @@ -20,17 +30,7 @@ apt install -y libgl1-mesa-glx pip3 install -U transformers==4.27.1 ``` -### Prepare Resources - -Pretrained model: Go to the website to find the pre-trained model you need. Here, we choose clip-vit-base-patch32. - -```bash -# Download model from the website and make sure the model's path is "data/clip-vit-base-patch32" -mkdir -p data -unzip clip-vit-base-patch32.zip -d data/ -``` - -## Run model +## Model Inference ### Test using the OpenAI interface diff --git a/models/multimodal/vision_language_model/fuyu_8b/vllm/README.md b/models/multimodal/vision_language_model/fuyu_8b/vllm/README.md index e0dbfcc0..c8992bd4 100755 --- a/models/multimodal/vision_language_model/fuyu_8b/vllm/README.md +++ b/models/multimodal/vision_language_model/fuyu_8b/vllm/README.md @@ -8,6 +8,15 @@ Architecturally, Fuyu is a vanilla decoder-only transformer - there is no image ## Model Preparation +### Prepare Resources + +- Model: + +```bash +# Download model from the website and make sure the model's path is "data/fuyu-8b" +mkdir data/ +``` + ### Install Dependencies In order to run the model smoothly, you need to get the sdk from [resource center](https://support.iluvatar.com/#/ProductLine?id=2) of Iluvatar CoreX official website. @@ -20,15 +29,6 @@ yum install -y mesa-libGL apt install -y libgl1-mesa-glx ``` -### Prepare Resources - -- Model: - -```bash -# Download model from the website and make sure the model's path is "data/fuyu-8b" -mkdir data -``` - ## Model Inference ```bash diff --git a/models/multimodal/vision_language_model/intern_vl/vllm/README.md b/models/multimodal/vision_language_model/intern_vl/vllm/README.md index 033860af..c7fdc256 100644 --- a/models/multimodal/vision_language_model/intern_vl/vllm/README.md +++ b/models/multimodal/vision_language_model/intern_vl/vllm/README.md @@ -6,6 +6,16 @@ InternVL2-4B is a large-scale multimodal model developed by WeTab AI, designed t ## Model Preparation +### Prepare Resources + +- Model: + +```bash +cd ${DeepSparkInference}/models/vision-language-understanding/Intern_VL/vllm +mkdir -p data/intern_vl +ln -s /path/to/InternVL2-4B ./data/intern_vl +``` + ### Install Dependencies In order to run the model smoothly, you need to get the sdk from [resource center](https://support.iluvatar.com/#/ProductLine?id=2) of Iluvatar CoreX official website. @@ -23,16 +33,6 @@ pip3 install triton pip3 install ixformer ``` -### Prepare Resources - -- Model: - -```bash -cd ${DeepSparkInference}/models/vision-language-understanding/Intern_VL/vllm -mkdir -p data/intern_vl -ln -s /path/to/InternVL2-4B ./data/intern_vl -``` - ## Model Inference ```bash diff --git a/models/multimodal/vision_language_model/llava/vllm/README.md b/models/multimodal/vision_language_model/llava/vllm/README.md index db7639e6..d8895797 100644 --- a/models/multimodal/vision_language_model/llava/vllm/README.md +++ b/models/multimodal/vision_language_model/llava/vllm/README.md @@ -6,6 +6,15 @@ LLaVA is an open-source chatbot trained by fine-tuning LLaMA/Vicuna on GPT-gener ## Model Preparation +### Prepare Resources + +-llava-v1.6-vicuna-7b-hf: + +```bash +# Download model from the website and make sure the model's path is "data/llava" +mkdir data/ +``` + ### Install Dependencies In order to run the model smoothly, you need to get the sdk from [resource center](https://support.iluvatar.com/#/ProductLine?id=2) of Iluvatar CoreX official website. @@ -19,16 +28,6 @@ apt install -y libgl1-mesa-glx pip3 install transformers ``` -### Prepare Resources - --llava-v1.6-vicuna-7b-hf: - -```bash -# Download model from the website and make sure the model's path is "data/llava" -mkdir data - -``` - ## Model Inference ```bash diff --git a/models/multimodal/vision_language_model/llava_next_video_7b/vllm/README.md b/models/multimodal/vision_language_model/llava_next_video_7b/vllm/README.md index b860fbc8..584a3603 100755 --- a/models/multimodal/vision_language_model/llava_next_video_7b/vllm/README.md +++ b/models/multimodal/vision_language_model/llava_next_video_7b/vllm/README.md @@ -6,6 +6,15 @@ LLaVA-Next-Video is an open-source chatbot trained by fine-tuning LLM on multimo ## Model Preparation +### Prepare Resources + +- Model: + +```bash +# Download model from the website and make sure the model's path is "data/LLaVA-NeXT-Video-7B-hf" +mkdir data/ +``` + ### Install Dependencies In order to run the model smoothly, you need to get the sdk from [resource center](https://support.iluvatar.com/#/ProductLine?id=2) of Iluvatar CoreX official website. @@ -18,15 +27,6 @@ yum install -y mesa-libGL apt install -y libgl1-mesa-glx ``` -### Prepare Resources - -- Model: - -```bash -# Download model from the website and make sure the model's path is "data/LLaVA-NeXT-Video-7B-hf" -mkdir data -``` - ## Model Inference ```bash diff --git a/models/multimodal/vision_language_model/minicpm_v_2/vllm/README.md b/models/multimodal/vision_language_model/minicpm_v_2/vllm/README.md index 50f17266..d5032bee 100644 --- a/models/multimodal/vision_language_model/minicpm_v_2/vllm/README.md +++ b/models/multimodal/vision_language_model/minicpm_v_2/vllm/README.md @@ -6,6 +6,16 @@ MiniCPM V2 is a compact and efficient language model designed for various natura ## Model Preparation +### Prepare Resources + +- Model: +Note: Due to the official weights missing some necessary files for vllm execution, you can download the additional files from here: to ensure that the file directory matches the structure shown here: . + +```bash +# Download model from the website and make sure the model's path is "data/MiniCPM-V-2" +mkdir data/ +``` + ### Install Dependencies In order to run the model smoothly, you need to get the sdk from [resource center](https://support.iluvatar.com/#/ProductLine?id=2) of Iluvatar CoreX official website. @@ -21,17 +31,6 @@ pip3 install transformers pip3 install --user --upgrade pillow -i https://pypi.tuna.tsinghua.edu.cn/simple ``` -### Prepare Resources - -- Model: -Note: Due to the official weights missing some necessary files for vllm execution, you can download the additional files from here: to ensure that the file directory matches the structure shown here: . - -```bash -# Download model from the website and make sure the model's path is "data/MiniCPM-V-2" -mkdir data - -``` - ## Model Inference ```bash diff --git a/models/nlp/llm/baichuan2-7b/vllm/README.md b/models/nlp/llm/baichuan2-7b/vllm/README.md index 930e7662..e79fb7c7 100755 --- a/models/nlp/llm/baichuan2-7b/vllm/README.md +++ b/models/nlp/llm/baichuan2-7b/vllm/README.md @@ -9,6 +9,16 @@ its excellent capabilities in language understanding and generation.This release ## Model Preparation +### Prepare Resources + +Pretrained model: +[https://huggingface.co/baichuan-inc/Baichuan2-7B-Base/tree/main](https://huggingface.co/baichuan-inc/Baichuan2-7B-Base/tree/main) + +```bash +mkdir /data/baichuan/ +mv Baichuan2-7B-Base.tar/zip /data/baichuan/ +``` + ### Install Dependencies In order to run the model smoothly, you need to get the sdk from [resource @@ -24,25 +34,15 @@ apt install -y libgl1-mesa-glx pip3 install transformers ``` -### Prepare Resources - -Pretrained model: -[https://huggingface.co/baichuan-inc/Baichuan2-7B-Base/tree/main](https://huggingface.co/baichuan-inc/Baichuan2-7B-Base/tree/main) - -```bash -mkdir /data/baichuan/ -mv Baichuan2-7B-Base.tar/zip /data/baichuan/ -``` - -## Run model +## Model Inference ```bash python3 offline_inference.py --model /data/baichuan/Baichuan2-7B-Base/ --max-tokens 256 --trust-remote-code --chat_template template_baichuan.jinja --temperature 0.0 ``` -## Run Baichuan w8a16 quantization +### Run Baichuan w8a16 quantization -### Retrieve int8 weights +Retrieve int8 weights. Int8 weights will be saved at /data/baichuan/Baichuan2-7B-Base/int8 @@ -50,8 +50,6 @@ Int8 weights will be saved at /data/baichuan/Baichuan2-7B-Base/int8 python3 convert2int8.py --model-path /data/baichuan/Baichuan2-7B-Base/ ``` -### Run - ```bash python3 offline_inference.py --model /data/baichuan/Baichuan2-7B-Base/int8/ --chat_template template_baichuan.jinja --quantization w8a16 --max-num-seqs 1 --max-model-len 256 --trust-remote-code --temperature 0.0 --max-tokens 256 ``` diff --git a/models/nlp/llm/chatglm3-6b-32k/vllm/README.md b/models/nlp/llm/chatglm3-6b-32k/vllm/README.md index ff3f125b..1fa1f415 100644 --- a/models/nlp/llm/chatglm3-6b-32k/vllm/README.md +++ b/models/nlp/llm/chatglm3-6b-32k/vllm/README.md @@ -10,6 +10,15 @@ we recommend using ChatGLM3-6B-32K. ## Model Preparation +### Prepare Resources + +Pretrained model: + +```bash +mkdir -p /data/chatglm/ +mv chatglm3-6b-32k.zip/tar /data/chatglm/ +``` + ### Install Dependencies In order to run the model smoothly, you need to get the sdk from [resource @@ -25,31 +34,22 @@ apt install -y libgl1-mesa-glx pip3 install transformers ``` -### Prepare Resources - -Pretrained model: - -```bash -mkdir -p /data/chatglm/ -mv chatglm3-6b-32k.zip/tar /data/chatglm/ -``` - -## Run model +## Model Inference ```bash python3 offline_inference.py --model /data/chatglm/chatglm3-6b-32k --trust-remote-code --temperature 0.0 --max-tokens 256 ``` -## Use the server +### Use the server -### Start the server +Start the server. ```bash python3 -m vllm.entrypoints.openai.api_server --model /data/chatglm/chatglm3-6b-32k --gpu-memory-utilization 0.9 --max-num-batched-tokens 8193 \ --max-num-seqs 32 --disable-log-requests --host 127.0.0.1 --port 12345 --trust-remote-code ``` -### Test using the OpenAI interface +Test using the OpenAI interface. ```bash python3 server_inference.py --host 127.0.0.1 --port 12345 --model_path /data/chatglm/chatglm3-6b-32k diff --git a/models/nlp/llm/chatglm3-6b/vllm/README.md b/models/nlp/llm/chatglm3-6b/vllm/README.md index 0a5ee9a0..7ca28a53 100644 --- a/models/nlp/llm/chatglm3-6b/vllm/README.md +++ b/models/nlp/llm/chatglm3-6b/vllm/README.md @@ -8,6 +8,15 @@ translation. ## Model Preparation +### Prepare Resources + +Pretrained model: + +```bash +mkdir /data/chatglm/ +mv chatglm3-6b.zip/tar /data/chatglm/ +``` + ### Install Dependencies In order to run the model smoothly, you need to get the sdk from [resource @@ -24,24 +33,15 @@ pip3 install vllm pip3 install transformers ``` -### Prepare Resources - -Pretrained model: - -```bash -mkdir /data/chatglm/ -mv chatglm3-6b.zip/tar /data/chatglm/ -``` - -## Run model +## Model Inference ```bash python3 offline_inference.py --model /data/chatglm/chatglm3-6b --trust-remote-code --temperature 0.0 --max-tokens 256 ``` -## Use the server +### Use the server -### Start the server +Start the server. ```bash python3 -m vllm.entrypoints.openai.api_server --model /data/chatglm/chatglm3-6b --gpu-memory-utilization 0.9 --max-num-batched-tokens 8193 \ @@ -54,30 +54,24 @@ python3 -m vllm.entrypoints.openai.api_server --model /data/chatglm/chatglm3-6b python3 server_inference.py --host 127.0.0.1 --port 12345 --model_path /data/chatglm/chatglm3-6b ``` -## Benchmarking vLLM - -### Downloading the ShareGPT dataset +### Benchmarking vLLM ```bash +# Downloading the ShareGPT dataset. wget https://huggingface.co/datasets/anon8231489123/ShareGPT_Vicuna_unfiltered/resolve/main/ShareGPT_V3_unfiltered_cleaned_split.json -``` - -### Cloning the vllm project -```bash +# Cloning the vllm project git clone https://github.com/vllm-project/vllm.git -b v0.5.4 --depth=1 ``` -### Benchmarking - -#### Starting server +Starting server. ```bash python3 -m vllm.entrypoints.openai.api_server --model /data/chatglm/chatglm3-6b --gpu-memory-utilization 0.9 --max-num-batched-tokens 8193 \ --max-num-seqs 32 --disable-log-requests --host 127.0.0.1 --trust-remote-code ``` -#### Starting benchmark client +Starting benchmark client. ```bash python3 benchmark_serving.py --host 127.0.0.1 --num-prompts 16 --model /data/chatglm/chatglm3-6b --dataset-name sharegpt \ diff --git a/models/nlp/llm/deepseek-r1-distill-llama-70b/vllm/README.md b/models/nlp/llm/deepseek-r1-distill-llama-70b/vllm/README.md index 1191913f..b5f28f20 100644 --- a/models/nlp/llm/deepseek-r1-distill-llama-70b/vllm/README.md +++ b/models/nlp/llm/deepseek-r1-distill-llama-70b/vllm/README.md @@ -1,4 +1,4 @@ -# DeepSeek-R1-Distill-Llama-70B +# DeepSeek-R1-Distill-Llama-70B (vLLM) ## Model Description @@ -8,6 +8,16 @@ based on Qwen2.5 and Llama3 series to the community. ## Model Preparation +### Prepare Resources + +- Model: + +```bash +cd deepSeek-r1-distill-llama-70b/vllm +mkdir -p data/ +ln -s /path/to/DeepSeek-R1-Distill-Llama-70B ./data/ +``` + ### Install Dependencies ```bash @@ -18,23 +28,15 @@ yum install -y mesa-libGL apt install -y libgl1-mesa-glx ``` -### Prepare Resources - -- Model: - -```bash -cd deepSeek-r1-distill-llama-70b/vllm -mkdir -p data/ -ln -s /path/to/DeepSeek-R1-Distill-Llama-70B ./data/ -``` +## Model Inference -## Inference with offline +### Inference with offline ```bash python3 offline_inference.py --model ./data/DeepSeek-R1-Distill-Llama-70B --max-tokens 256 -tp 8 --temperature 0.0 --max-model-len 3096 ``` -## Inference with serve +### Inference with serve ```bash vllm serve data/DeepSeek-R1-Distill-Llama-70B --tensor-parallel-size 8 --max-model-len 32768 --enforce-eager --trust-remote-code @@ -42,4 +44,4 @@ vllm serve data/DeepSeek-R1-Distill-Llama-70B --tensor-parallel-size 8 --max-mod ## References -[DeepSeek-R1](https://github.com/deepseek-ai/DeepSeek-R1) +- [DeepSeek-R1](https://github.com/deepseek-ai/DeepSeek-R1) diff --git a/models/nlp/llm/deepseek-r1-distill-llama-8b/vllm/README.md b/models/nlp/llm/deepseek-r1-distill-llama-8b/vllm/README.md index 96dd42d0..44516490 100644 --- a/models/nlp/llm/deepseek-r1-distill-llama-8b/vllm/README.md +++ b/models/nlp/llm/deepseek-r1-distill-llama-8b/vllm/README.md @@ -1,4 +1,4 @@ -# DeepSeek-R1-Distill-Llama-8B +# DeepSeek-R1-Distill-Llama-8B (vLLM) ## Model Description @@ -8,6 +8,16 @@ based on Qwen2.5 and Llama3 series to the community. ## Model Preparation +### Prepare Resources + +- Model: + +```bash +cd deepSeek-r1-distill-llama-8b/vllm +mkdir -p data/ +ln -s /path/to/DeepSeek-R1-Distill-Llama-8B ./data/ +``` + ### Install Dependencies ```bash @@ -18,23 +28,15 @@ yum install -y mesa-libGL apt install -y libgl1-mesa-glx ``` -### Prepare Resources - -- Model: - -```bash -cd deepSeek-r1-distill-llama-8b/vllm -mkdir -p data/ -ln -s /path/to/DeepSeek-R1-Distill-Llama-8B ./data/ -``` +## Model Inference -## Inference with offline +### Inference with offline ```bash python3 offline_inference.py --model ./data/DeepSeek-R1-Distill-Llama-8B --max-tokens 256 -tp 1 --temperature 0.0 --max-model-len 3096 ``` -## Inference with serve +### Inference with serve ```bash vllm serve data/DeepSeek-R1-Distill-Llama-8B --tensor-parallel-size 2 --max-model-len 32768 --enforce-eager --trust-remote-code @@ -48,4 +50,4 @@ vllm serve data/DeepSeek-R1-Distill-Llama-8B --tensor-parallel-size 2 --max-mode ## References -[DeepSeek-R1](https://github.com/deepseek-ai/DeepSeek-R1) +- [DeepSeek-R1](https://github.com/deepseek-ai/DeepSeek-R1) diff --git a/models/nlp/llm/deepseek-r1-distill-qwen-1.5b/vllm/README.md b/models/nlp/llm/deepseek-r1-distill-qwen-1.5b/vllm/README.md index 1c711cbb..32c97ebe 100644 --- a/models/nlp/llm/deepseek-r1-distill-qwen-1.5b/vllm/README.md +++ b/models/nlp/llm/deepseek-r1-distill-qwen-1.5b/vllm/README.md @@ -1,4 +1,4 @@ -# DeepSeek-R1-Distill-Qwen-1.5B +# DeepSeek-R1-Distill-Qwen-1.5B (vLLM) ## Model Description @@ -8,6 +8,16 @@ based on Qwen2.5 and Llama3 series to the community. ## Model Preparation +### Prepare Resources + +- Model: + +```bash +cd deepseek-r1-distill-qwen-1.5b/vllm +mkdir -p data/ +ln -s /path/to/DeepSeek-R1-Distill-Qwen-1.5B ./data/ +``` + ### Install Dependencies ```bash @@ -18,23 +28,15 @@ yum install -y mesa-libGL apt install -y libgl1-mesa-glx ``` -### Prepare Resources - -- Model: - -```bash -cd deepseek-r1-distill-qwen-1.5b/vllm -mkdir -p data/ -ln -s /path/to/DeepSeek-R1-Distill-Qwen-1.5B ./data/ -``` +## Model Inference -## Inference with offline +### Inference with offline ```bash python3 offline_inference.py --model ./data/DeepSeek-R1-Distill-Qwen-1.5B --max-tokens 256 -tp 1 --temperature 0.0 --max-model-len 3096 ``` -## Inference with serve +### Inference with serve ```bash vllm serve data/DeepSeek-R1-Distill-Qwen-1.5B --tensor-parallel-size 2 --max-model-len 32768 --enforce-eager --trust-remote-code @@ -48,4 +50,4 @@ vllm serve data/DeepSeek-R1-Distill-Qwen-1.5B --tensor-parallel-size 2 --max-mod ## References -[DeepSeek-R1](https://github.com/deepseek-ai/DeepSeek-R1) +- [DeepSeek-R1](https://github.com/deepseek-ai/DeepSeek-R1) diff --git a/models/nlp/llm/deepseek-r1-distill-qwen-14b/vllm/README.md b/models/nlp/llm/deepseek-r1-distill-qwen-14b/vllm/README.md index b3307bcc..b6c19863 100644 --- a/models/nlp/llm/deepseek-r1-distill-qwen-14b/vllm/README.md +++ b/models/nlp/llm/deepseek-r1-distill-qwen-14b/vllm/README.md @@ -1,4 +1,4 @@ -# DeepSeek-R1-Distill-Qwen-14B +# DeepSeek-R1-Distill-Qwen-14B (vLLM) ## Model Description @@ -8,6 +8,16 @@ DeepSeek-R1. We slightly change their configs and tokenizers. We open-source di ## Model Preparation +### Prepare Resources + +- Model: + +```bash +cd deepseek-r1-distill-qwen-14b/vllm +mkdir -p data/ +ln -s /path/to/DeepSeek-R1-Distill-Qwen-14B ./data/ +``` + ### Install Dependencies ```bash @@ -18,23 +28,15 @@ yum install -y mesa-libGL apt install -y libgl1-mesa-glx ``` -### Prepare Resources - -- Model: - -```bash -cd deepseek-r1-distill-qwen-14b/vllm -mkdir -p data/ -ln -s /path/to/DeepSeek-R1-Distill-Qwen-14B ./data/ -``` +## Model Inference -## Inference with offline +### Inference with offline ```bash python3 offline_inference.py --model ./data/DeepSeek-R1-Distill-Qwen-14B --max-tokens 256 -tp 2 --temperature 0.0 --max-model-len 3096 ``` -## Inference with serve +### Inference with serve ```bash vllm serve data/DeepSeek-R1-Distill-Qwen-14B --tensor-parallel-size 2 --max-model-len 32768 --enforce-eager --trust-remote-code @@ -48,4 +50,4 @@ vllm serve data/DeepSeek-R1-Distill-Qwen-14B --tensor-parallel-size 2 --max-mode ## References -[DeepSeek-R1](https://github.com/deepseek-ai/DeepSeek-R1) +- [DeepSeek-R1](https://github.com/deepseek-ai/DeepSeek-R1) diff --git a/models/nlp/llm/deepseek-r1-distill-qwen-32b/vllm/README.md b/models/nlp/llm/deepseek-r1-distill-qwen-32b/vllm/README.md index 75e9eb2d..bda03579 100644 --- a/models/nlp/llm/deepseek-r1-distill-qwen-32b/vllm/README.md +++ b/models/nlp/llm/deepseek-r1-distill-qwen-32b/vllm/README.md @@ -1,4 +1,4 @@ -# DeepSeek-R1-Distill-Qwen-32B +# DeepSeek-R1-Distill-Qwen-32B (vLLM) ## Model Description @@ -8,6 +8,16 @@ DeepSeek-R1. We slightly change their configs and tokenizers. We open-source di ## Model Preparation +### Prepare Resources + +- Model: + +```bash +cd deepseek-r1-distill-qwen-32b/vllm +mkdir -p data/ +ln -s /path/to/DeepSeek-R1-Distill-Qwen-32B ./data/ +``` + ### Install Dependencies ```bash @@ -18,23 +28,15 @@ yum install -y mesa-libGL apt install -y libgl1-mesa-glx ``` -### Prepare Resources - -- Model: - -```bash -cd deepseek-r1-distill-qwen-32b/vllm -mkdir -p data/ -ln -s /path/to/DeepSeek-R1-Distill-Qwen-32B ./data/ -``` +## Model Inference -## Inference with offline +### Inference with offline ```bash python3 offline_inference.py --model ./data/DeepSeek-R1-Distill-Qwen-32B --max-tokens 256 -tp 4 --temperature 0.0 --max-model-len 3096 ``` -## Inference with serve +### Inference with serve ```bash vllm serve data/DeepSeek-R1-Distill-Qwen-32B --tensor-parallel-size 4 --max-model-len 32768 --enforce-eager --trust-remote-code @@ -48,4 +50,4 @@ vllm serve data/DeepSeek-R1-Distill-Qwen-32B --tensor-parallel-size 4 --max-mode ## References -[DeepSeek-R1](https://github.com/deepseek-ai/DeepSeek-R1) +- [DeepSeek-R1](https://github.com/deepseek-ai/DeepSeek-R1) diff --git a/models/nlp/llm/deepseek-r1-distill-qwen-7b/vllm/README.md b/models/nlp/llm/deepseek-r1-distill-qwen-7b/vllm/README.md index d50cb9e4..b5d57e19 100644 --- a/models/nlp/llm/deepseek-r1-distill-qwen-7b/vllm/README.md +++ b/models/nlp/llm/deepseek-r1-distill-qwen-7b/vllm/README.md @@ -1,4 +1,4 @@ -# DeepSeek-R1-Distill-Qwen-7B +# DeepSeek-R1-Distill-Qwen-7B (vLLM) ## Model Description @@ -8,6 +8,16 @@ based on Qwen2.5 and Llama3 series to the community. ## Model Preparation +### Prepare Resources + +- Model: + +```bash +cd deepseek-r1-distill-qwen-7b/vllm +mkdir -p data/ +ln -s /path/to/DeepSeek-R1-Distill-Qwen-7B ./data/ +``` + ### Install Dependencies ```bash @@ -18,23 +28,15 @@ yum install -y mesa-libGL apt install -y libgl1-mesa-glx ``` -### Prepare Resources - -- Model: - -```bash -cd deepseek-r1-distill-qwen-7b/vllm -mkdir -p data/ -ln -s /path/to/DeepSeek-R1-Distill-Qwen-7B ./data/ -``` +## Model Inference -## Inference with offline +### Inference with offline ```bash python3 offline_inference.py --model ./data/DeepSeek-R1-Distill-Qwen-7B --max-tokens 256 -tp 1 --temperature 0.0 --max-model-len 3096 ``` -## Inference with serve +### Inference with serve ```bash vllm serve data/DeepSeek-R1-Distill-Qwen-7B --tensor-parallel-size 2 --max-model-len 32768 --enforce-eager --trust-remote-code @@ -48,4 +50,4 @@ vllm serve data/DeepSeek-R1-Distill-Qwen-7B --tensor-parallel-size 2 --max-model ## References -[DeepSeek-R1](https://github.com/deepseek-ai/DeepSeek-R1) +- [DeepSeek-R1](https://github.com/deepseek-ai/DeepSeek-R1) diff --git a/models/nlp/llm/llama2-13b/trtllm/README.md b/models/nlp/llm/llama2-13b/trtllm/README.md index 003d90bb..6bfa1abf 100755 --- a/models/nlp/llm/llama2-13b/trtllm/README.md +++ b/models/nlp/llm/llama2-13b/trtllm/README.md @@ -9,18 +9,6 @@ from 7B to 70B. ## Model Preparation -### Install Dependencies - -```bash -# Install libGL -## CentOS -yum install -y mesa-libGL -## Ubuntu -apt install -y libgl1-mesa-glx - -bash scripts/set_environment.sh . -``` - ### Prepare Resources - Model: @@ -29,18 +17,29 @@ bash scripts/set_environment.sh . ```bash # Download model from the website and make sure the model's path is "data/llama2-13b-chat" # Download dataset from the website and make sure the dataset's path is "data/datasets_cnn_dailymail" -mkdir data +mkdir data/ # Please download rouge.py to this path if your server can't attach huggingface.co. mkdir -p rouge/ wget --no-check-certificate https://raw.githubusercontent.com/huggingface/evaluate/main/metrics/rouge/rouge.py -P rouge ``` +### Install Dependencies + +```bash +# Install libGL +## CentOS +yum install -y mesa-libGL +## Ubuntu +apt install -y libgl1-mesa-glx + +bash scripts/set_environment.sh . +``` + ## Model Inference ```bash export CUDA_VISIBLE_DEVICES=0,1 - ``` ### FP16 diff --git a/models/nlp/llm/llama2-70b/trtllm/README.md b/models/nlp/llm/llama2-70b/trtllm/README.md index 080fe85d..d01031ca 100644 --- a/models/nlp/llm/llama2-70b/trtllm/README.md +++ b/models/nlp/llm/llama2-70b/trtllm/README.md @@ -11,18 +11,6 @@ and contribute to the responsible development of LLMs. ## Model Preparation -### Install Dependencies - -```bash -# Install libGL -## CentOS -yum install -y mesa-libGL -## Ubuntu -apt install -y libgl1-mesa-glx - -bash scripts/set_environment.sh . -``` - ### Prepare Resources - Model: @@ -39,6 +27,18 @@ mkdir -p rouge/ wget --no-check-certificate https://raw.githubusercontent.com/huggingface/evaluate/main/metrics/rouge/rouge.py -P rouge ``` +### Install Dependencies + +```bash +# Install libGL +## CentOS +yum install -y mesa-libGL +## Ubuntu +apt install -y libgl1-mesa-glx + +bash scripts/set_environment.sh . +``` + ## Model Inference ### FP16 diff --git a/models/nlp/llm/llama2-7b/trtllm/README.md b/models/nlp/llm/llama2-7b/trtllm/README.md index bde69ca7..210420ed 100644 --- a/models/nlp/llm/llama2-7b/trtllm/README.md +++ b/models/nlp/llm/llama2-7b/trtllm/README.md @@ -11,21 +11,6 @@ and contribute to the responsible development of LLMs. ## Model Preparation -### Install Dependencies - -In order to run the model smoothly, you need to get the sdk from [resource -center](https://support.iluvatar.com/#/ProductLine?id=2) of Iluvatar CoreX official website. - -```bash -# Install libGL -## CentOS -yum install -y mesa-libGL -## Ubuntu -apt install -y libgl1-mesa-glx - -bash scripts/set_environment.sh . -``` - ### Prepare Resources - Model: @@ -42,6 +27,21 @@ mkdir -p rouge/ wget --no-check-certificate https://raw.githubusercontent.com/huggingface/evaluate/main/metrics/rouge/rouge.py -P rouge ``` +### Install Dependencies + +In order to run the model smoothly, you need to get the sdk from [resource +center](https://support.iluvatar.com/#/ProductLine?id=2) of Iluvatar CoreX official website. + +```bash +# Install libGL +## CentOS +yum install -y mesa-libGL +## Ubuntu +apt install -y libgl1-mesa-glx + +bash scripts/set_environment.sh . +``` + ## Model Inference ### FP16 diff --git a/models/nlp/llm/llama2-7b/vllm/README.md b/models/nlp/llm/llama2-7b/vllm/README.md index 71e37bff..82eafa3f 100755 --- a/models/nlp/llm/llama2-7b/vllm/README.md +++ b/models/nlp/llm/llama2-7b/vllm/README.md @@ -11,6 +11,16 @@ and contribute to the responsible development of LLMs. ## Model Preparation +### Prepare Resources + +- Model: + +```bash +cd ${DeepSparkInference}/models/nlp/large_language_model/llama2-7b/vllm +mkdir -p data/llama2 +ln -s /path/to/llama2-7b ./data/llama2 +``` + ### Install Dependencies In order to run the model smoothly, you need to get the sdk from [resource @@ -29,16 +39,6 @@ pip3 install triton pip3 install ixformer ``` -### Prepare Resources - -- Model: - -```bash -cd ${DeepSparkInference}/models/nlp/large_language_model/llama2-7b/vllm -mkdir -p data/llama2 -ln -s /path/to/llama2-7b ./data/llama2 -``` - ## Model Inference ```bash diff --git a/models/nlp/llm/llama3-70b/vllm/README.md b/models/nlp/llm/llama3-70b/vllm/README.md index 96cc8c50..789f1066 100644 --- a/models/nlp/llm/llama3-70b/vllm/README.md +++ b/models/nlp/llm/llama3-70b/vllm/README.md @@ -2,23 +2,23 @@ ## Model Description -This model is the Meta Llama 3 large language model series (LLMs) released by Meta, which is a series of pre-trained and -instruction-tuned generative text models, available in 8B and 70B models. The model is 70B in size and is designed for -large-scale AI applications. +Llama 3 is Meta's latest large language model series, representing a significant advancement in open-source AI +technology. Available in 8B and 70B parameter versions, it's trained on a dataset seven times larger than its +predecessor, Llama 2. The model features an expanded 8K context window and a 128K token vocabulary for more efficient +language encoding. Optimized for conversational AI, Llama 3 demonstrates superior performance across various industry +benchmarks while maintaining strong safety and beneficialness standards. Its 70B version is particularly designed for +large-scale AI applications, offering enhanced reasoning and instruction-following capabilities. -The Llama 3 command-tuned model is optimized for conversational use cases and outperforms many available open source -chat models on common industry benchmarks. In addition, when developing these models, the research team paid great -attention to optimizing beneficialness and safety. - -Llama 3 is a major improvement over Llama 2 and other publicly available models: - ---Trained on a dataset seven times larger than Llama 2 +## Model Preparation ---Llama 2 has twice the context length of 8K +### Prepare Resources ---Encode the language more efficiently using a larger token vocabulary with 128K tokens +- Model: -## Model Preparation +```bash +# Download model from the website and make sure the model's path is "data/Meta-Llama-3-70B-Instruct" +mkdir data/ +``` ### Install Dependencies @@ -33,16 +33,6 @@ yum install -y mesa-libGL apt install -y libgl1-mesa-glx ``` -### Prepare Resources - -- Model: - -```bash -# Download model from the website and make sure the model's path is "data/Meta-Llama-3-70B-Instruct" -mkdir data - -``` - ## Model Inference ```bash diff --git a/models/nlp/llm/qwen-7b/vllm/README.md b/models/nlp/llm/qwen-7b/vllm/README.md index ca2d482d..69340ba2 100644 --- a/models/nlp/llm/qwen-7b/vllm/README.md +++ b/models/nlp/llm/qwen-7b/vllm/README.md @@ -2,21 +2,25 @@ ## Model Description -Large language models (LLMs) have revolutionized the field of artificial intelligence, enabling natural language -processing tasks that were previously thought to be exclusive to humans. In this work, we introduce Qwen, the first -installment of our large language model series. Qwen is a comprehensive language model series that encompasses distinct -models with varying parameter counts. It includes Qwen, the base pretrained language models, and Qwen-Chat, the chat -models finetuned with human alignment techniques. The base language models consistently demonstrate superior performance -across a multitude of downstream tasks, and the chat models, particularly those trained using Reinforcement Learning -from Human Feedback (RLHF), are highly competitive. The chat models possess advanced tool-use and planning capabilities -for creating agent applications, showcasing impressive performance even when compared to bigger models on complex tasks -like utilizing a code interpreter. Furthermore, we have developed coding-specialized models, Code-Qwen and -Code-Qwen-Chat, as well as mathematics-focused models, Math-Qwen-Chat, which are built upon base language models. These -models demonstrate significantly improved performance in comparison with open-source models, and slightly fall behind -the proprietary models. +Qwen-7B is a cutting-edge large language model developed as part of the Qwen series, offering advanced natural language +processing capabilities. With 7 billion parameters, it demonstrates exceptional performance across various downstream +tasks. The model comes in two variants: the base pretrained version and the Qwen-Chat version, which is fine-tuned using +human alignment techniques. Notably, Qwen-7B exhibits strong tool-use and planning abilities, making it suitable for +developing intelligent agent applications. It also includes specialized versions for coding (Code-Qwen) and mathematics +(Math-Qwen), showcasing improved performance in these domains compared to other open-source models. ## Model Preparation +### Prepare Resources + +- Model: - Model: + +```bash +cd ${DeepSparkInference}/models/nlp/large_language_model/qwen-7b/vllm +mkdir -p data/qwen +ln -s /path/to/Qwen-7B ./data/qwen +``` + ### Install Dependencies In order to run the model smoothly, you need to get the sdk from [resource @@ -35,16 +39,6 @@ pip3 install triton pip3 install ixformer ``` -### Prepare Resources - -- Model: - Model: - -```bash -cd ${DeepSparkInference}/models/nlp/large_language_model/qwen-7b/vllm -mkdir -p data/qwen -ln -s /path/to/Qwen-7B ./data/qwen -``` - ## Model Inference ```bash diff --git a/models/nlp/llm/qwen1.5-14b/vllm/README.md b/models/nlp/llm/qwen1.5-14b/vllm/README.md index a08adf77..eb429d04 100644 --- a/models/nlp/llm/qwen1.5-14b/vllm/README.md +++ b/models/nlp/llm/qwen1.5-14b/vllm/README.md @@ -10,16 +10,6 @@ not include GQA (except for 32B) and the mixture of SWA and full attention. ## Model Preparation -### Install Dependencies - -```bash -# Install libGL -## CentOS -yum install -y mesa-libGL -## Ubuntu -apt install -y libgl1-mesa-glx -``` - ### Prepare Resources - Model: @@ -30,6 +20,16 @@ mkdir data/qwen1.5 ln -s /path/to/Qwen1.5-14B ./data/qwen1.5 ``` +### Install Dependencies + +```bash +# Install libGL +## CentOS +yum install -y mesa-libGL +## Ubuntu +apt install -y libgl1-mesa-glx +``` + ## Model Inference ```bash diff --git a/models/nlp/llm/qwen1.5-32b/vllm/README.md b/models/nlp/llm/qwen1.5-32b/vllm/README.md index 634ce9e7..9b111e19 100755 --- a/models/nlp/llm/qwen1.5-32b/vllm/README.md +++ b/models/nlp/llm/qwen1.5-32b/vllm/README.md @@ -9,6 +9,16 @@ have an improved tokenizer adaptive to multiple natural languages and codes. ## Model Preparation +### Prepare Resources + +- Model: + +```bash +cd ${DeepSparkInference}/models/nlp/large_language_model/qwen1.5-32b/vllm +mkdir -p data/qwen1.5 +ln -s /path/to/Qwen1.5-32B ./data/qwen1.5 +``` + ### Install Dependencies ```bash @@ -24,16 +34,6 @@ pip3 install triton pip3 install ixformer ``` -### Prepare Resources - -- Model: - -```bash -cd ${DeepSparkInference}/models/nlp/large_language_model/qwen1.5-32b/vllm -mkdir -p data/qwen1.5 -ln -s /path/to/Qwen1.5-32B ./data/qwen1.5 -``` - ## Model Inference ```bash diff --git a/models/nlp/llm/qwen1.5-72b/vllm/README.md b/models/nlp/llm/qwen1.5-72b/vllm/README.md index d1a3108c..6cc7c2ad 100644 --- a/models/nlp/llm/qwen1.5-72b/vllm/README.md +++ b/models/nlp/llm/qwen1.5-72b/vllm/README.md @@ -10,16 +10,6 @@ not include GQA (except for 32B) and the mixture of SWA and full attention. ## Model Preparation -### Install Dependencies - -```bash -# Install libGL -## CentOS -yum install -y mesa-libGL -## Ubuntu -apt install -y libgl1-mesa-glx -``` - ### Prepare Resources - Model: @@ -30,6 +20,16 @@ mkdir data/qwen1.5 ln -s /path/to/Qwen1.5-72B ./data/qwen1.5 ``` +### Install Dependencies + +```bash +# Install libGL +## CentOS +yum install -y mesa-libGL +## Ubuntu +apt install -y libgl1-mesa-glx +``` + ## Model Inference ```bash diff --git a/models/nlp/llm/qwen1.5-7b/tgi/README.md b/models/nlp/llm/qwen1.5-7b/tgi/README.md index 198d7438..97cca488 100644 --- a/models/nlp/llm/qwen1.5-7b/tgi/README.md +++ b/models/nlp/llm/qwen1.5-7b/tgi/README.md @@ -10,16 +10,6 @@ not include GQA (except for 32B) and the mixture of SWA and full attention. ## Model Preparation -### Install Dependencies - -```bash -# Install libGL -## CentOS -yum install -y mesa-libGL -## Ubuntu -apt install -y libgl1-mesa-glx -``` - ### Prepare Resources - Model: @@ -30,6 +20,16 @@ mkdir -p data/qwen1.5 ln -s /path/to/Qwen1.5-7B ./data/qwen1.5 ``` +### Install Dependencies + +```bash +# Install libGL +## CentOS +yum install -y mesa-libGL +## Ubuntu +apt install -y libgl1-mesa-glx +``` + ## Model Inference ### Start webserver diff --git a/models/nlp/llm/qwen1.5-7b/vllm/README.md b/models/nlp/llm/qwen1.5-7b/vllm/README.md index e30773cb..7b5eac5d 100644 --- a/models/nlp/llm/qwen1.5-7b/vllm/README.md +++ b/models/nlp/llm/qwen1.5-7b/vllm/README.md @@ -10,16 +10,6 @@ not include GQA (except for 32B) and the mixture of SWA and full attention. ## Model Preparation -### Install Dependencies - -```bash -# Install libGL -## CentOS -yum install -y mesa-libGL -## Ubuntu -apt install -y libgl1-mesa-glx -``` - ### Prepare Resources - Model: @@ -30,6 +20,16 @@ mkdir -p data/qwen1.5 ln -s /path/to/Qwen1.5-7B ./data/qwen1.5 ``` +### Install Dependencies + +```bash +# Install libGL +## CentOS +yum install -y mesa-libGL +## Ubuntu +apt install -y libgl1-mesa-glx +``` + ## Model Inference ```bash diff --git a/models/nlp/llm/qwen2-72b/vllm/README.md b/models/nlp/llm/qwen2-72b/vllm/README.md index d28c55ab..b3a7a7a5 100755 --- a/models/nlp/llm/qwen2-72b/vllm/README.md +++ b/models/nlp/llm/qwen2-72b/vllm/README.md @@ -16,6 +16,16 @@ Please refer to this section for detailed instructions on how to deploy Qwen2 fo ## Model Preparation +### Prepare Resources + +- Model: + +```bash +cd ${DeepSparkInference}/models/nlp/large_language_model/qwen2-72b/vllm +mkdir -p data/qwen2 +ln -s /path/to/Qwen2-72B ./data/qwen2 +``` + ### Install Dependencies ```bash @@ -31,16 +41,6 @@ pip3 install triton pip3 install ixformer ``` -### Prepare Resources - -- Model: - -```bash -cd ${DeepSparkInference}/models/nlp/large_language_model/qwen2-72b/vllm -mkdir -p data/qwen2 -ln -s /path/to/Qwen2-72B ./data/qwen2 -``` - ## Model Inference ```bash diff --git a/models/nlp/llm/qwen2-7b/vllm/README.md b/models/nlp/llm/qwen2-7b/vllm/README.md index 419bfd4f..b9433934 100755 --- a/models/nlp/llm/qwen2-7b/vllm/README.md +++ b/models/nlp/llm/qwen2-7b/vllm/README.md @@ -15,6 +15,16 @@ Qwen2-7B-Instruct supports a context length of up to 131,072 tokens, enabling th ## Model Preparation +### Prepare Resources + +- Model: + +```bash +cd models/nlp/large_language_model/qwen2-7b/vllm +mkdir -p data/qwen2 +ln -s /path/to/Qwen2-7B-Instruct ./data/qwen2 +``` + ### Install Dependencies ```bash @@ -30,16 +40,6 @@ pip3 install triton pip3 install ixformer ``` -### Prepare Resources - -- Model: https://modelscope.cn/models/Qwen/Qwen2-7B-Instruct - -```bash -cd models/nlp/large_language_model/qwen2-7b/vllm -mkdir -p data/qwen2 -ln -s /path/to/Qwen2-7B-Instruct ./data/qwen2 -``` - ## Model Inference ```bash diff --git a/models/nlp/llm/stablelm/vllm/README.md b/models/nlp/llm/stablelm/vllm/README.md index 0ea5b1a5..7b498638 100644 --- a/models/nlp/llm/stablelm/vllm/README.md +++ b/models/nlp/llm/stablelm/vllm/README.md @@ -10,6 +10,15 @@ contextual relationships, which enhances the quality and accuracy of the generat ## Model Preparation +### Prepare Resources + +- Model: + +```bash +# Download model from the website and make sure the model's path is "data/stablelm/stablelm-2-1_6b" +mkdir -p data/stablelm/stablelm-2-1_6b +``` + ### Install Dependencies ```bash @@ -21,15 +30,6 @@ apt install -y libgl1-mesa-glx pip3 install transformers ``` -### Prepare Resources - -- Model: - -```bash -# Download model from the website and make sure the model's path is "data/stablelm/stablelm-2-1_6b" -mkdir -p data/stablelm/stablelm-2-1_6b -``` - ## Model Inference ```bash diff --git a/models/nlp/plm/albert/ixrt/README.md b/models/nlp/plm/albert/ixrt/README.md index 8b032619..9552148c 100644 --- a/models/nlp/plm/albert/ixrt/README.md +++ b/models/nlp/plm/albert/ixrt/README.md @@ -1,4 +1,4 @@ -# ALBERT +# ALBERT (IxRT) ## Model Description @@ -6,14 +6,6 @@ Albert (A Lite BERT) is a variant of the BERT (Bidirectional Encoder Representat ## Model Preparation -### Install Dependencies - -```bash -apt install -y libnuma-dev - -pip3 install -r requirements.txt -``` - ### Prepare Resources Pretrained model: @@ -29,6 +21,14 @@ cd ${MODEL_PATH} bash ./scripts/prepare_model_and_dataset.sh ``` +### Install Dependencies + +```bash +apt install -y libnuma-dev + +pip3 install -r requirements.txt +``` + ### Model Conversion Please correct the paths in the following commands or files. @@ -52,7 +52,6 @@ export PROJ_PATH=./ ### Performance ```bash - bash scripts/infer_albert_fp16_performance.sh ``` diff --git a/models/nlp/plm/bert_base_ner/igie/README.md b/models/nlp/plm/bert_base_ner/igie/README.md index b4511ba5..8a6f826f 100644 --- a/models/nlp/plm/bert_base_ner/igie/README.md +++ b/models/nlp/plm/bert_base_ner/igie/README.md @@ -1,4 +1,4 @@ -# BERT Base NER +# BERT Base NER (IGIE) ## Model Description @@ -6,18 +6,18 @@ BERT is designed to pre-train deep bidirectional representations from unlabeled ## Model Preparation -### Install Dependencies - -```bash -pip3 install -r requirements.txt -``` - ### Prepare Resources Pretrained model: Dataset: +### Install Dependencies + +```bash +pip3 install -r requirements.txt +``` + ### Model Conversion ```bash @@ -27,11 +27,10 @@ export DATASETS_DIR=/Path/to/china-people-daily-ner-corpus/ python3 get_weights.py # Do QAT for INT8 test, will take a long time -cd Int8QAT +cd Int8QAT/ python3 run_qat.py --model_dir ../test/ --datasets_dir ${DATASETS_DIR} python3 export_hdf5.py --model quant_base/pytorch_model.bin -cd .. - +cd ../ ``` ## Model Inference @@ -47,6 +46,6 @@ bash scripts/infer_bert_base_ner_int8_performance.sh ## Model Results -Model |BatchSize |SeqLength |Precision |FPS | F1 Score ------------------|-----------|----------|----------|----------|-------- -Bertbase(NER) | 8 | 256 | INT8 | 2067.252 | 96.2 +| Model | BatchSize | SeqLength | Precision | FPS | F1 Score | +|---------------|-----------|-----------|-----------|----------|----------| +| BERT Base NER | 8 | 256 | INT8 | 2067.252 | 96.2 | diff --git a/models/nlp/plm/bert_base_squad/igie/README.md b/models/nlp/plm/bert_base_squad/igie/README.md index 3114a1c0..5c8d9e9d 100644 --- a/models/nlp/plm/bert_base_squad/igie/README.md +++ b/models/nlp/plm/bert_base_squad/igie/README.md @@ -1,4 +1,4 @@ -# BERT Base SQuAD +# BERT Base SQuAD (IGIE) ## Model Description @@ -6,18 +6,18 @@ BERT is designed to pre-train deep bidirectional representations from unlabeled ## Model Preparation -### Install Dependencies - -```bash -pip3 install -r requirements.txt -``` - ### Prepare Resources Pretrained model: Dataset: +### Install Dependencies + +```bash +pip3 install -r requirements.txt +``` + ### Model Conversion ```bash diff --git a/models/nlp/plm/bert_base_squad/ixrt/README.md b/models/nlp/plm/bert_base_squad/ixrt/README.md index 3ba12c02..e3c9aac3 100644 --- a/models/nlp/plm/bert_base_squad/ixrt/README.md +++ b/models/nlp/plm/bert_base_squad/ixrt/README.md @@ -1,4 +1,4 @@ -# BERT Base SQuAD +# BERT Base SQuAD (IxRT) ## Model Description @@ -6,37 +6,39 @@ BERT is designed to pre-train deep bidirectional representations from unlabeled ## Model Preparation -### T4 requirement(tensorrt_version >= 8.6) +### Prepare Resources ```bash -docker pull nvcr.io/nvidia/tensorrt:23.04-py3 +cd python +bash script/prepare.sh v1_1 ``` -## Install +### Install Dependencies -```bash -pip3 install -r requirements.txt -``` - -### Install on Iluvatar +#### Install on Iluvatar ```bash cmake -S . -B build cmake --build build -j16 ``` -### Install on T4 +#### Install on NV + +Require tensorrt_version >= 8.6 ```bash -cmake -S . -B build -DUSE_TENSORRT=true -cmake --build build -j16 +# Get TensorRT docker image +docker pull nvcr.io/nvidia/tensorrt:23.04-py3 +# Run TensorRT docker ``` -## Download - ```bash -cd python -bash script/prepare.sh v1_1 +# Install requirements.txt in TensorRT docker +pip3 install -r requirements.txt + +# Build +cmake -S . -B build -DUSE_TENSORRT=true +cmake --build build -j16 ``` ## Model Inference @@ -46,7 +48,7 @@ bash script/prepare.sh v1_1 #### FP16 ```bash -cd script +cd script/ # FP16 bash infer_bert_base_squad_fp16_ixrt.sh diff --git a/models/nlp/plm/bert_large_squad/igie/README.md b/models/nlp/plm/bert_large_squad/igie/README.md index 96efec50..aba63da2 100644 --- a/models/nlp/plm/bert_large_squad/igie/README.md +++ b/models/nlp/plm/bert_large_squad/igie/README.md @@ -1,4 +1,4 @@ -# BERT Large SQuAD +# BERT Large SQuAD (IGIE) ## Model Description @@ -6,22 +6,21 @@ BERT is designed to pre-train deep bidirectional representations from unlabeled ## Model Preparation -### Install Dependencies - -```bash -pip3 install -r requirements.txt -``` - ### Prepare Resources Pretrained model: Dataset: -### Model Conversion +### Install Dependencies ```bash +pip3 install -r requirements.txt +``` +### Model Conversion + +```bash # Get FP16 Onnx Model python3 export.py --output bert-large-uncased-squad-v1.onnx @@ -40,8 +39,7 @@ bash run_qat.sh # model: quant_bert_large/pytorch_model.bin or quant_bert_large/model.safetensors python3 export_hdf5.py --model quant_bert_large/pytorch_model.bin --model_name large -cd .. - +cd ../ ``` ## Model Inference @@ -70,7 +68,7 @@ bash scripts/infer_bert_large_squad_int8_performance.sh ## Model Results -Model |BatchSize |SeqLength |Precision |FPS | F1 Score ------------------|-----------|----------|----------|----------|-------- -Bertlarge(Squad) | 8 | 256 | FP16 | 302.273 | 91.102 -Bertlarge(Squad) | 8 | 256 | INT8 | 723.169 | 89.899 +| Model | BatchSize | SeqLength | Precision | FPS | F1 Score | +|------------------|-----------|-----------|-----------|---------|----------| +| BERT Large SQuAD | 8 | 256 | FP16 | 302.273 | 91.102 | +| BERT Large SQuAD | 8 | 256 | INT8 | 723.169 | 89.899 | diff --git a/models/nlp/plm/bert_large_squad/ixrt/README.md b/models/nlp/plm/bert_large_squad/ixrt/README.md index e15a1345..47d9c62b 100644 --- a/models/nlp/plm/bert_large_squad/ixrt/README.md +++ b/models/nlp/plm/bert_large_squad/ixrt/README.md @@ -1,4 +1,4 @@ -# BERT Large SQuAD +# BERT Large SQuAD (IxRT) ## Model Description @@ -6,40 +6,42 @@ BERT is designed to pre-train deep bidirectional representations from unlabeled ## Model Preparation +### Prepare Resources + Get `bert-large-uncased.zip` from [Google Drive](https://drive.google.com/file/d/1eD8QBkbK6YN-_YXODp3tmpp3cZKlrPTA/view?usp=drive_link) -### NV requirement(tensorrt_version >= 8.6) - ```bash -docker pull nvcr.io/nvidia/tensorrt:23.04-py3 +cd python/ +bash script/prepare.sh v1_1 ``` -## Install +### Install Dependencies -```bash -pip3 install -r requirements.txt -``` - -### On Iluvatar +#### Install on Iluvatar ```bash cmake -S . -B build cmake --build build -j16 ``` -### On NV +#### Install on NV + +Require tensorrt_version >= 8.6 ```bash -cmake -S . -B build -DUSE_TENSORRT=true -cmake --build build -j16 +# Get TensorRT docker image +docker pull nvcr.io/nvidia/tensorrt:23.04-py3 +# Run TensorRT docker ``` -## Download - ```bash -cd python -bash script/prepare.sh v1_1 +# Install requirements.txt in TensorRT docker +pip3 install -r requirements.txt + +# Build +cmake -S . -B build -DUSE_TENSORRT=true +cmake --build build -j16 ``` ## Model Inference @@ -47,7 +49,7 @@ bash script/prepare.sh v1_1 ### FP16 ```bash -cd python +cd python/ # use --bs to set max_batch_size (dynamic) bash script/build_engine.sh --bs 32 @@ -62,10 +64,11 @@ pip install onnx pycuda bash script/build_engine.sh --bs 32 --int8 bash script/inference_squad.sh --bs 32 --int8 ``` -| Model | BatchSize | Precision | Latency QPS | exact_match | f1 | -|------------------|-----------|-----------|---------------------|-------------|-------| -| BERT-Large-SQuAD | 32 | FP16 | 470.26 sentences/s | 82.36 | 89.68 | -| BERT-Large-SQuAD | 32 | INT8 | 1490.47 sentences/s | 80.92 | 88.20 | -|------------------|-----------|-----------|---------------------|-------------|-------| -| BERT-Large-SQuAD | 32 | FP16 | 470.26 sentences/s | 82.36 | 89.68 | -| BERT-Large-SQuAD | 32 | INT8 | 1490.47 sentences/s | 80.92 | 88.20 | + +| Model | BatchSize | Precision | Latency QPS | exact_match | f1 | +|--------------------|-------------|-------------|-----------------------|---------------|---------| +| BERT-Large-SQuAD | 32 | FP16 | 470.26 sentences/s | 82.36 | 89.68 | +| BERT-Large-SQuAD | 32 | INT8 | 1490.47 sentences/s | 80.92 | 88.20 | +| ------------------ | ----------- | ----------- | --------------------- | ------------- | ------- | +| BERT-Large-SQuAD | 32 | FP16 | 470.26 sentences/s | 82.36 | 89.68 | +| BERT-Large-SQuAD | 32 | INT8 | 1490.47 sentences/s | 80.92 | 88.20 | diff --git a/models/nlp/plm/deberta/ixrt/README.md b/models/nlp/plm/deberta/ixrt/README.md index b2b5bf0a..e2b41d2b 100644 --- a/models/nlp/plm/deberta/ixrt/README.md +++ b/models/nlp/plm/deberta/ixrt/README.md @@ -1,4 +1,4 @@ -# DeBERTa +# DeBERTa (IxRT) ## Model Description @@ -11,6 +11,16 @@ fine-tuning to better suit specific downstream tasks, thereby improving the mode ## Model Preparation +### Prepare Resources + +Pretrained model: < > + +Dataset: < > to download the squad dataset. + +```bash +bash ./scripts/prepare_model_and_dataset.sh +``` + ### Install Dependencies ```bash @@ -23,16 +33,6 @@ apt install -y libnuma-dev pip3 install -r requirements.txt ``` -### Prepare Resources - -Pretrained model: < > - -Dataset: < > to download the squad dataset. - -```bash -bash ./scripts/prepare_model_and_dataset.sh -``` - ### Model Conversion ```bash diff --git a/models/nlp/plm/roberta/ixrt/README.md b/models/nlp/plm/roberta/ixrt/README.md index 246b9079..2f9455c9 100644 --- a/models/nlp/plm/roberta/ixrt/README.md +++ b/models/nlp/plm/roberta/ixrt/README.md @@ -1,4 +1,4 @@ -# RoBERTa +# RoBERTa (IxRT) ## Model Description @@ -13,6 +13,12 @@ our models and code. ## Model Preparation +### Prepare Resources + +Pretrained model: + +Dataset: + ### Install Dependencies ```bash @@ -23,11 +29,7 @@ cd ${MODEL_PATH} pip3 install -r requirements.txt ``` -### Prepare Resources - -Pretrained model: - -Dataset: +### Model Conversion ```bash # Go to path of this model diff --git a/models/nlp/plm/roformer/ixrt/README.md b/models/nlp/plm/roformer/ixrt/README.md index 20d3938a..627eb639 100644 --- a/models/nlp/plm/roformer/ixrt/README.md +++ b/models/nlp/plm/roformer/ixrt/README.md @@ -1,4 +1,4 @@ -# RoFormer +# RoFormer (IxRT) ## Model Description @@ -15,15 +15,6 @@ datasets. ## Model Preparation -### Install Dependencies - -```bash -apt install -y libnuma-dev - -pip3 install -r requirements.txt - -``` - ### Prepare Resources Pretrained model: @@ -45,7 +36,16 @@ rm -f open_roformer.tar popd ``` -### Deal with ONNX +### Install Dependencies + +```bash +apt install -y libnuma-dev + +pip3 install -r requirements.txt + +``` + +### Model Conversion ```bash # export onnx diff --git a/models/nlp/plm/videobert/ixrt/README.md b/models/nlp/plm/videobert/ixrt/README.md index 3a00c0c7..dde6c249 100644 --- a/models/nlp/plm/videobert/ixrt/README.md +++ b/models/nlp/plm/videobert/ixrt/README.md @@ -1,4 +1,4 @@ -# VideoBERT +# VideoBERT (IxRT) ## Model Description @@ -8,14 +8,6 @@ and textual information into a unified framework. ## Model Preparation -### Install Dependencies - -```bash -apt install -y libnuma-dev - -pip3 install -r requirements.txt -``` - ### Prepare Resources Pretrained model: @@ -31,6 +23,14 @@ cd ${MODEL_PATH} bash ./scripts/prepare_model_and_dataset.sh ``` +### Install Dependencies + +```bash +apt install -y libnuma-dev + +pip3 install -r requirements.txt +``` + ## Model Inference ```bash diff --git a/models/others/recommendation/wide_and_deep/ixrt/README.md b/models/others/recommendation/wide_and_deep/ixrt/README.md index 2482b5ed..62c39ed0 100644 --- a/models/others/recommendation/wide_and_deep/ixrt/README.md +++ b/models/others/recommendation/wide_and_deep/ixrt/README.md @@ -1,4 +1,4 @@ -# Wide&Deep +# Wide & Deep (IxRT) ## Model Description @@ -6,6 +6,12 @@ Generalized linear models with nonlinear feature transformations are widely used ## Model Preparation +### Prepare Resources + +Pretrained model: + +Dataset: + ### Install Dependencies ```bash @@ -14,11 +20,7 @@ apt install -y libnuma-dev pip3 install -r requirements.txt ``` -### Prepare Resources - -Pretrained model: - -Dataset: +### Model Conversion ```bash # Go to path of this model @@ -82,6 +84,6 @@ python3 core/perf_engine.py --hardware_type ILUVATAR --task widedeep-tf-fp32 ## Model Results -| Model | BatchSize | Precision | FPS | ACC | -| --------- | --------- | --------- | -------- | ------- | -| Wide&Deep | 1024 | FP16 | 77073.93 | 0.74597 | +| Model | BatchSize | Precision | FPS | ACC | +|-------------|-----------|-----------|----------|---------| +| Wide & Deep | 1024 | FP16 | 77073.93 | 0.74597 | -- Gitee