diff --git a/ACL_PyTorch/contrib/cv/classfication/Wide_ResNet101_2/README.md b/ACL_PyTorch/contrib/cv/classfication/Wide_ResNet101_2/README.md index d5f9345d1af2034ac48d08f5ebd9d99b6dbaf0e8..8cf0f797cd38353865f9f8e6417ad2ddff49885f 100644 --- a/ACL_PyTorch/contrib/cv/classfication/Wide_ResNet101_2/README.md +++ b/ACL_PyTorch/contrib/cv/classfication/Wide_ResNet101_2/README.md @@ -5,10 +5,6 @@ - [输入输出数据](#section540883920406) - - -- [推理环境准备](#ZH-CN_TOPIC_0000001126281702) - - [快速上手](#ZH-CN_TOPIC_0000001126281700) - [获取源码](#section4622531142816) @@ -17,7 +13,7 @@ - [模型推理性能&精度](#ZH-CN_TOPIC_0000001172201573) - ****** +****** @@ -50,35 +46,6 @@ | output1 | FLOAT32 | 1 x 1000 | ND | -# 推理环境准备 - -- 该模型需要以下插件与驱动 - - **表 1** 版本配套表 - - | 配套 | 版本 | 环境准备指导 | - | ------------------------------------------------------------ | ------- | ------------------------------------------------------------ | - | 固件与驱动 | 1.0.17 | [Pytorch框架推理环境准备](https://www.hiascend.com/document/detail/zh/ModelZoo/pytorchframework/pies) | - | CANN | 6.0.RC1 | - | - | Python | 3.7.5 | - | - | PyTorch | 1.8.1 | - | - | 说明：Atlas 300I Duo 推理卡请以CANN版本选择实际固件与驱动版本。 | \ | \ | - -- 该模型需要以下依赖 - - **表 2** 依赖列表 - - | 依赖名称 | 版本 | - | ------------- | -------- | - | onnx | 1.7.0 | - | Torch | 1.8.1 | - | TorchVision | 0.9.1 | - | numpy | 1.18.5 | - | Pillow | 7.2.0 | - | opencv-python | 4.2.0.34 | - - - # 快速上手 ## 获取源码 diff --git a/ACL_PyTorch/contrib/cv/classfication/Wide_ResNet50_2_for_Pytorch/README.md b/ACL_PyTorch/contrib/cv/classfication/Wide_ResNet50_2_for_Pytorch/README.md index 38fc2752d7fe1dbcc0c3c2f9de5d966f3859413c..ab14e9244b098c95cb0a2ae9573d88387184b1b3 100644 --- a/ACL_PyTorch/contrib/cv/classfication/Wide_ResNet50_2_for_Pytorch/README.md +++ b/ACL_PyTorch/contrib/cv/classfication/Wide_ResNet50_2_for_Pytorch/README.md @@ -5,10 +5,6 @@ - [输入输出数据](#section540883920406) - - -- [推理环境准备](#ZH-CN_TOPIC_0000001126281702) - - [快速上手](#ZH-CN_TOPIC_0000001126281700) - [获取源码](#section4622531142816) @@ -17,7 +13,7 @@ - [模型推理性能&精度](#ZH-CN_TOPIC_0000001172201573) - ****** +****** @@ -52,35 +48,6 @@ | output1 | FLOAT32 | 1 x 1000 | NCHW | -# 推理环境准备 - -- 该模型需要以下插件与驱动 - - **表 1** 版本配套表 - - | 配套 | 版本 | 环境准备指导 | - | ------------------------------------------------------------ | ------- | ------------------------------------------------------------ | - | 固件与驱动 | 1.0.17 | [Pytorch框架推理环境准备](https://www.hiascend.com/document/detail/zh/ModelZoo/pytorchframework/pies) | - | CANN | 6.0.RC1 | - | - | Python | 3.7.5 | - | - | PyTorch | 1.8.1 | - | - | 说明：Atlas 300I Duo 推理卡请以CANN版本选择实际固件与驱动版本。 | \ | \ | - -- 该模型需要以下依赖 - - **表 2** 依赖列表 - - | 依赖名称 | 版本 | - | ------------- | -------- | - | onnx | 1.7.0 | - | Torch | 1.8.1 | - | TorchVision | 0.9.1 | - | numpy | 1.18.5 | - | Pillow | 7.2.0 | - | opencv-python | 4.2.0.34 | - - - # 快速上手 ## 获取源码 diff --git a/ACL_PyTorch/contrib/cv/classfication/volo/public_address_statement.md b/ACL_PyTorch/contrib/cv/classfication/volo/public_address_statement.md new file mode 100644 index 0000000000000000000000000000000000000000..473ec015716ad4762ba03b54ab344a2f90df401c --- /dev/null +++ b/ACL_PyTorch/contrib/cv/classfication/volo/public_address_statement.md @@ -0,0 +1,5 @@ +| 类型 | 开源代码地址 | 文件名 | 公网IP地址/公网URL地址/域名/邮箱地 | 用途说明 | +| ---- | ----------- | ----- | -------------------------------- | --------| +| 开源代码引入 | https://github.com/sail-sg/volo/blob/main/models/volo.py | ACL_PyTorch/contrib/cv/classfication/volo/volo.py | https://github.com/zihangJiang/TokenLabeling | 函数用途说明 | +| 开源代码引入 | https://github.com/sail-sg/volo/blob/main/models/volo.py | ACL_PyTorch/contrib/cv/classfication/volo/volo.py | https://github.com/zihangJiang/TokenLabeling | 参数说明 | +| 开源代码引入 | https://github.com/sail-sg/volo/blob/main/models/volo.py | ACL_PyTorch/contrib/cv/classfication/volo/volo.py | https://github.com/zihangJiang/TokenLabeling | 参数说明 | \ No newline at end of file diff --git a/ACL_PyTorch/contrib/cv/classfication/volo/readme.md b/ACL_PyTorch/contrib/cv/classfication/volo/readme.md index cb8a89e35a3b36b69f170e8a2ce45afcac0710f7..2734ec3ce0ed5a940b5b660f72fa0cbddde1d611 100644 --- a/ACL_PyTorch/contrib/cv/classfication/volo/readme.md +++ b/ACL_PyTorch/contrib/cv/classfication/volo/readme.md @@ -1,7 +1,6 @@ # VOLO Onnx模型端到端推理指导 - [概述](#概述) - [输入输出数据](#输入输出数据) -- [推理环境准备](#推理环境准备) - [快速上手](#快速上手) @@ -11,7 +10,7 @@ - [模型推理性能](#模型推理性能) - ****** +****** @@ -46,22 +45,6 @@ VOLO采用两阶段架构设计，同时考虑了更具细粒度的token表示 | output | batchsize x 1000 | FLOAT32 | ND | -# 推理环境准备 - -- 该模型需要以下插件与驱动 - - **表 1** 版本配套表 - -| 配套 | 版本 | 环境准备指导 | -| ------------------------------------------------------------ |---------| ------------------------------------------------------------ | -| 固件与驱动 | 22.0.2 | [Pytorch框架推理环境准备](https://gitee.com/link?target=https%3A%2F%2Fwww.hiascend.com%2Fdocument%2Fdetail%2Fzh%2FModelZoo%2Fpytorchframework%2Fpies) | -| CANN | 6.0.RC1 | - | -| Python | 3.7.5 | - | -| PyTorch | 1.10.0 | - | -| 说明：Atlas 300I Duo 推理卡请以CANN版本选择实际固件与驱动版本。 | | | - - - # 快速上手 ## 获取源码 diff --git a/ACL_PyTorch/contrib/cv/classfication/vovnet39/README.md b/ACL_PyTorch/contrib/cv/classfication/vovnet39/README.md index 31d2c1f7b08f889c40f7f954947236f97b702869..864252d2c843b28c2373c4070aee4641687349db 100644 --- a/ACL_PyTorch/contrib/cv/classfication/vovnet39/README.md +++ b/ACL_PyTorch/contrib/cv/classfication/vovnet39/README.md @@ -5,8 +5,6 @@ - [输入输出数据](#section540883920406) -- [推理环境准备](#ZH-CN_TOPIC_0000001126281702) - - [快速上手](#ZH-CN_TOPIC_0000001126281700) - [获取源码](#section4622531142816) @@ -15,7 +13,7 @@ - [模型推理性能&精度](#ZH-CN_TOPIC_0000001172201573) - ****** +****** # 概述 @@ -44,17 +42,6 @@ | -------- | -------- | -------- | ------------ | | output | FLOAT32 | 1 x 1000 | ND | -# 推理环境准备 - -- 该模型需要以下插件与驱动 - - **表 1** 版本配套表 - - | 配套 | 版本 | 环境准备指导 | - | ---------- | ------- | ----------------------------------------------------------------------------------------------------- | - | 固件与驱动 | 22.0.2 | [Pytorch框架推理环境准备](https://www.hiascend.com/document/detail/zh/ModelZoo/pytorchframework/pies) | - | CANN | 5.1.RC2 | - | - | Python | 3.7.5 | - | # 快速上手 diff --git a/ACL_PyTorch/contrib/cv/classfication/xception/README.md b/ACL_PyTorch/contrib/cv/classfication/xception/README.md index e89b8ff5355ab15df054fd2f437fa7879500cf56..d5269882b64b15354ccf1deb60b5f6c9f0fc7a23 100644 --- a/ACL_PyTorch/contrib/cv/classfication/xception/README.md +++ b/ACL_PyTorch/contrib/cv/classfication/xception/README.md @@ -2,7 +2,6 @@ - [概述](#概述) - [输入输出数据](#输入输出数据) -- [推理环境](#推理环境) - [快速上手](#快速上手) - [获取源码](#获取源码) - [准备数据集](#准备数据集) @@ -35,20 +34,7 @@ Xception是Google公司继Inception后提出的对 Inception-v3 的另一种改 ---- -# 推理环境 -- 该模型推理所需配套的软件如下： - - | 配套 | 版本 | 环境准备指导 | - | --------- | ------- | ---------- | - | 固件与驱动 | 1.0.17 | [Pytorch框架推理环境准备](https://www.hiascend.com/document/detail/zh/ModelZoo/pytorchframework/pies) | - | CANN | 6.0.RC1 | - | - | Python | 3.7.5 | - | - - 说明：请根据推理卡型号与 CANN 版本选择相匹配的固件与驱动版本。 - - ----- # 快速上手 ## 安装 diff --git a/ACL_PyTorch/contrib/cv/classfication/xcit/README.md b/ACL_PyTorch/contrib/cv/classfication/xcit/README.md index 3df1f5a34726a2290e803b1f7036f8b57075fb0f..04b697a18fa9f56811698f3eaeda84540b2e9c6d 100644 --- a/ACL_PyTorch/contrib/cv/classfication/xcit/README.md +++ b/ACL_PyTorch/contrib/cv/classfication/xcit/README.md @@ -3,8 +3,6 @@ - [概述](#ZH-CN_TOPIC_0000001172161501) -- [推理环境准备](#ZH-CN_TOPIC_0000001126281702) - - [快速上手](#ZH-CN_TOPIC_0000001126281700) - [获取源码](#section4622531142816) @@ -13,9 +11,7 @@ - [模型推理性能](#ZH-CN_TOPIC_0000001172201573) -- [配套环境](#ZH-CN_TOPIC_0000001126121892) - - ****** +****** # 概述 @@ -57,22 +53,6 @@ Xcit是针对于图片处理设计的基于Transformer架构的神经网络。 | output1 | batchsize x 1000 | FLOAT32 | ND | - - -# 推理环境准备\[所有版本\] - -- 该模型需要以下插件与驱动 - - **表 1** 版本配套表 - -| 配套 | 版本 | 环境准备指导 | -| ------------------------------------------------------------ | ------- | ------------------------------------------------------------ | -| 固件与驱动 | 1.0.15 | [Pytorch框架推理环境准备](https://www.hiascend.com/document/detail/zh/ModelZoo/pytorchframework/pies) | -| CANN | 5.1.RC1 | - | -| Python | 3.7.5 | - | -| PyTorch | 1.8.0 | - | -| 说明：Atlas 300I Duo 推理卡请以CANN版本选择实际固件与驱动版本。 | \ | \ | - # 快速上手 diff --git a/ACL_PyTorch/contrib/cv/detection/3DUnet/README.md b/ACL_PyTorch/contrib/cv/detection/3DUnet/README.md index c14869723a67218f9b5af76873282bafaba6f77c..284a3450fd4adb8b673ab25c5e2be63465b36e9f 100644 --- a/ACL_PyTorch/contrib/cv/detection/3DUnet/README.md +++ b/ACL_PyTorch/contrib/cv/detection/3DUnet/README.md @@ -46,8 +46,6 @@ ### 2.1 深度学习框架 ``` -CANN 5.0.4 - pytorch >= 1.4.0 torchvision >= 0.6.0 onnx >= 1.7.0 diff --git a/ACL_PyTorch/contrib/cv/detection/AdvancedEAST/README.md b/ACL_PyTorch/contrib/cv/detection/AdvancedEAST/README.md index e09f125447f6a43a5bc9be692b0faa005b8ac86c..4dc5708ff4988a075808672c610921e668081980 100644 --- a/ACL_PyTorch/contrib/cv/detection/AdvancedEAST/README.md +++ b/ACL_PyTorch/contrib/cv/detection/AdvancedEAST/README.md @@ -5,8 +5,6 @@ - [输入输出数据](#section540883920406) -- [推理环境准备](#ZH-CN_TOPIC_0000001126281702) - - [快速上手](#ZH-CN_TOPIC_0000001126281700) - [获取源码](#section4622531142816) @@ -50,22 +48,6 @@ AdvancedEAST是一种用于场景图像文本检测的算法，它主要基于EA | output1 | FLOAT32 | batchsize x 7 x 184 x 184 | ND | - - -# 推理环境准备 - -- 该模型需要以下插件与驱动 - - **表 1** 版本配套表 - - | 配套 | 版本 | 环境准备指导 | - | ---------- | ---------------------------------- | ------------------------------------------------------------ | - | 固件与驱动 | 1.0.16（NPU驱动固件版本为5.1.RC2） | [Pytorch框架推理环境准备](https://www.hiascend.com/document/detail/zh/ModelZoo/pytorchframework/pies) | - | CANN | 5.1.RC2 | - | - | Python | 3.7.5 | - | - - - # 快速上手 ## 获取源码 diff --git a/ACL_PyTorch/contrib/cv/detection/AlphaPose/README.md b/ACL_PyTorch/contrib/cv/detection/AlphaPose/README.md index 5911ab05e2cde7cab877ebcb086ca0878a17ca26..03442a661f679cc48067553a0ebd9ee90211d5b6 100644 --- a/ACL_PyTorch/contrib/cv/detection/AlphaPose/README.md +++ b/ACL_PyTorch/contrib/cv/detection/AlphaPose/README.md @@ -4,8 +4,6 @@ - [输入输出数据](#section540883920406) -- [推理环境准备](#ZH-CN_TOPIC_0000001126281702) - - [快速上手](#ZH-CN_TOPIC_0000001126281700) - [获取源码](#section4622531142816) @@ -14,7 +12,6 @@ - [模型推理性能&精度](#ZH-CN_TOPIC_0000001172201573) -- [配套环境](#ZH-CN_TOPIC_0000001126121892) # 概述 @@ -43,19 +40,6 @@ | -------- | -------- | -------- | ------------ | | output | batch_size x 17 x 64 x 48 | FLOAT32 | NCHW | -# 推理环境准备\[所有版本\] - -- 该模型需要以下插件与驱动 - - **表 1** 版本配套表 - -| 配套 | 版本 | 环境准备指导 | -| ------------------------------------------------------------ | ------- | ------------------------------------------------------------ | -| 固件与驱动 | 1.0.17 | [Pytorch框架推理环境准备](https://www.hiascend.com/document/detail/zh/ModelZoo/pytorchframework/pies) | -| CANN | 6.0.RC1 | - | -| Python | 3.7.5 | - | -| PyTorch | 1.5.0+ | - | -| 说明：Atlas 300I Duo 推理卡请以CANN版本选择实际固件与驱动版本。 | \ | \ | # 快速上手 diff --git a/ACL_PyTorch/contrib/cv/detection/BSN/README.md b/ACL_PyTorch/contrib/cv/detection/BSN/README.md index bb2cbdc2e036bb9756754bc3f59cbffd93c0a2f7..19a4db7b1b4ca92992e0b48dddb16b5fa6f807be 100644 --- a/ACL_PyTorch/contrib/cv/detection/BSN/README.md +++ b/ACL_PyTorch/contrib/cv/detection/BSN/README.md @@ -3,8 +3,6 @@ - [概述](#ZH-CN_TOPIC_0000001172161501) -- [推理环境准备](#ZH-CN_TOPIC_0000001126281702) - - [快速上手](#ZH-CN_TOPIC_0000001126281700) - [获取源码](#section4622531142816) @@ -13,10 +11,6 @@ - [模型推理性能](#ZH-CN_TOPIC_0000001172201573) -- [配套环境](#ZH-CN_TOPIC_0000001126121892) - - - # 概述 @@ -70,20 +64,6 @@ code_path=ACL_PyTorch/contrib/cv/detection | PEM model | FLOAT32 | batchsize x 1000 x 1 | ND | -# 推理环境准备\[所有版本\] - -- 该模型需要以下插件与驱动 - - **表 1** 版本配套表 - - | 配套 | 版本 | 环境准备指导 | - | ------------------------------------------------------------ | ------------------- | ------------------------------------------------------------ | - | 固件与驱动 | 1.0.17 | [Pytorch框架推理环境准备](https://www.hiascend.com/document/detail/zh/ModelZoo/pytorchframework/pies) | - | CANN | 6.0.RC1 | - | - | Python | 3.7.5 | - | - | PyTorch | 1.5.0 | - | - | 说明：Atlas 300I Duo 推理卡请以CANN版本选择实际固件与驱动版本。 | | | - # 快速上手 ## 获取源码 diff --git a/ACL_PyTorch/contrib/cv/detection/CTPN/README.md b/ACL_PyTorch/contrib/cv/detection/CTPN/README.md index a6ebc1d46ef7d4f3de6aef37cf16142cf9da0abd..f1734d13fbe6c2624bd3a4c1c703514da43000b9 100644 --- a/ACL_PyTorch/contrib/cv/detection/CTPN/README.md +++ b/ACL_PyTorch/contrib/cv/detection/CTPN/README.md @@ -5,10 +5,6 @@ - [输入输出数据](#section540883920406) - - -- [推理环境准备](#ZH-CN_TOPIC_0000001126281702) - - [快速上手](#ZH-CN_TOPIC_0000001126281700) - [获取源码](#section4622531142816) @@ -57,21 +53,6 @@ CTPN是一种文字检测算法，它结合了CNN与LSTM深度网络，能有效 - -# 推理环境准备 - -- 该模型需要以下插件与驱动 - - **表 1** 版本配套表 - - | 配套 | 版本 | 环境准备指导 | - | :------------------------------------------------------------: | :-------: | :------------------------------------------------------------: | - | 固件与驱动 | 1.0.16 | [Pytorch框架推理环境准备](https://www.hiascend.com/document/detail/zh/ModelZoo/pytorchframework/pies) | - | CANN | 5.1.RC2 | - | - | Python | 3.7.5 | \ | - | 说明：Atlas 300I Duo 推理卡请以CANN版本选择实际固件与驱动版本。 | \ | \ | - - # 快速上手 ## 获取源码 diff --git a/ACL_PyTorch/contrib/cv/detection/Cascade-RCNN-Resnet101-FPN-DCN/README.md b/ACL_PyTorch/contrib/cv/detection/Cascade-RCNN-Resnet101-FPN-DCN/README.md index 6988d3b8d6d954f2609bbbdb1197d120c7fd9dd0..13ef929f6aa9c1ad8d3b178edff3c736685eaf8f 100644 --- a/ACL_PyTorch/contrib/cv/detection/Cascade-RCNN-Resnet101-FPN-DCN/README.md +++ b/ACL_PyTorch/contrib/cv/detection/Cascade-RCNN-Resnet101-FPN-DCN/README.md @@ -5,10 +5,6 @@ - [输入输出数据](#section540883920406) - - -- [推理环境准备](#ZH-CN_TOPIC_0000001126281702) - - [快速上手](#ZH-CN_TOPIC_0000001126281700) - [获取源码](#section4622531142816) @@ -17,7 +13,7 @@ - [模型推理性能&精度](#ZH-CN_TOPIC_0000001172201573) - ****** +****** @@ -56,21 +52,6 @@ Cascade-RCNN-Resnet101-FPN-DCN是利用Deformable Conv（可变形卷积）和De | output | FLOAT32 | 100 x 5 | ND | -# 推理环境准备 - -- 该模型需要以下插件与驱动 - - **表 1** 版本配套表 - - | 配套 | 版本 | 环境准备指导 | - | ------------------------------------------------------------ | ------- | ------------------------------------------------------------ | - | 固件与驱动 | 1.0.17(NPU驱动固件版本为6.0.RC1) | [Pytorch框架推理环境准备](https://www.hiascend.com/document/detail/zh/ModelZoo/pytorchframework/pies) | - | CANN | 6.0.RC1 | - | - | Python | 3.7.5 | - | - | Pytorch | 1.7.0 | - | - - - # 快速上手 ## 获取源码 diff --git a/ACL_PyTorch/contrib/cv/detection/Cascade-RCNN-Resnet50-FPN/README.md b/ACL_PyTorch/contrib/cv/detection/Cascade-RCNN-Resnet50-FPN/README.md index fd65d97f0b5b02c0789383c22e12f7614ff2c752..f3017331a3f6fede67994a0622ae2f07b4f15f9e 100644 --- a/ACL_PyTorch/contrib/cv/detection/Cascade-RCNN-Resnet50-FPN/README.md +++ b/ACL_PyTorch/contrib/cv/detection/Cascade-RCNN-Resnet50-FPN/README.md @@ -5,10 +5,6 @@ - [输入输出数据](#section540883920406) - - -- [推理环境准备](#ZH-CN_TOPIC_0000001126281702) - - [快速上手](#ZH-CN_TOPIC_0000001126281700) - [获取源码](#section4622531142816) @@ -17,9 +13,7 @@ - [模型推理性能&精度](#ZH-CN_TOPIC_0000001172201573) - ****** - - +****** # 概述 @@ -56,19 +50,6 @@ Cascade-RCNN_DCN在之前的cascade-RCNN的基础上，采用形变卷积算子 | boxes | FLOAT32 | 100 x 5 | ND | | labels | INT64 | 100 x 1 | ND | -# 推理环境准备 - -- 该模型需要以下插件与驱动 - - **表 1** 版本配套表 - - | 配套 | 版本 | 环境准备指导 | - | ------------------------------------------------------------ | ------- | ------------------------------------------------------------ | - | 固件与驱动 | 1.0.17(NPU驱动固件版本为6.0.RC1) | [Pytorch框架推理环境准备](https://www.hiascend.com/document/detail/zh/ModelZoo/pytorchframework/pies) | - | CANN | 6.0.RC1 | - | - | Python | 3.7.5 | - | - - # 快速上手 diff --git a/ACL_PyTorch/contrib/cv/detection/Cascade_RCNN_R101_FPN/README.md b/ACL_PyTorch/contrib/cv/detection/Cascade_RCNN_R101_FPN/README.md index b7b6e4ccf8a3a5f3f5eedf3ff958e407b4f309b1..2f114ab2b2f7f62072b6e15b5b45af2501c5f4f0 100644 --- a/ACL_PyTorch/contrib/cv/detection/Cascade_RCNN_R101_FPN/README.md +++ b/ACL_PyTorch/contrib/cv/detection/Cascade_RCNN_R101_FPN/README.md @@ -5,10 +5,6 @@ - [输入输出数据](#section540883920406) - - -- [推理环境准备](#ZH-CN_TOPIC_0000001126281702) - - [快速上手](#ZH-CN_TOPIC_0000001126281700) - [获取源码](#section4622531142816) @@ -17,7 +13,7 @@ - [模型推理性能&精度](#ZH-CN_TOPIC_0000001172201573) - ****** +****** @@ -56,20 +52,6 @@ Cascade R-CNN是目标检测two-stage算法的代表之一，使用cascade回归 | boxes | FLOAT32 | 100 x 5 | ND | | labels | INT64 | 100 x 1 | ND | -# 推理环境准备 - -- 该模型需要以下插件与驱动 - - **表 1** 版本配套表 - - | 配套 | 版本 | 环境准备指导 | - | ------------------------------------------------------------ | ------- | ------------------------------------------------------------ | - | 固件与驱动 | 1.0.17(NPU驱动固件版本为6.0.RC1) | [Pytorch框架推理环境准备](https://www.hiascend.com/document/detail/zh/ModelZoo/pytorchframework/pies) | - | CANN | 6.0.RC1 | - | - | Python | 3.7.5 | - | - - - # 快速上手 diff --git a/ACL_PyTorch/contrib/cv/detection/CenterFace/README.md b/ACL_PyTorch/contrib/cv/detection/CenterFace/README.md index 233b625e7de60659668f1148f75472005c7d4a58..b7aa2f14519c426c780e97029a09c711afc49c6a 100644 --- a/ACL_PyTorch/contrib/cv/detection/CenterFace/README.md +++ b/ACL_PyTorch/contrib/cv/detection/CenterFace/README.md @@ -5,8 +5,6 @@ - [输入输出数据](#section540883920406) -- [推理环境准备](#ZH-CN_TOPIC_0000001126281702) - - [快速上手](#ZH-CN_TOPIC_0000001126281700) - [获取源码](#section4622531142816) @@ -49,19 +47,6 @@ | output4 | FLOAT32 | 1 x 400000 | ND | -# 推理环境准备 - -- 该模型需要以下插件与驱动 - - **表 1** 版本配套表 - - | 配套 | 版本 | 环境准备指导 | - | ----------- | ------- | ------------------------------------------------------------ | - | 固件与驱动 | 1.0.17（NPU驱动固件版本为6.0.RC1） | [Pytorch框架推理环境准备](https://www.hiascend.com/document/detail/zh/ModelZoo/pytorchframework/pies) | - | CANN | 6.0.RC1 | - | - | Python | 3.7.5 | - | - - # 快速上手 ## 获取源码 diff --git a/ACL_PyTorch/contrib/cv/detection/CenterNet/README.md b/ACL_PyTorch/contrib/cv/detection/CenterNet/README.md index e8d67023d7986102877f49ae0b4b640fc87ba5e6..f3d9a934de96fc15bdb6e281917b758e1ed47288 100644 --- a/ACL_PyTorch/contrib/cv/detection/CenterNet/README.md +++ b/ACL_PyTorch/contrib/cv/detection/CenterNet/README.md @@ -5,8 +5,6 @@ - [输入输出数据](#section540883920406) -- [推理环境准备](#ZH-CN_TOPIC_0000001126281702) - - [快速上手](#ZH-CN_TOPIC_0000001126281700) - [获取源码](#section4622531142816) @@ -52,20 +50,6 @@ CenterNet 是在 2019 年提出的用于目标检测的模型，相比传统依 | output3 | FLOAT32 | batchsize x 2 x 128 x 128 | ND | -# 推理环境准备 - -- 该模型需要以下插件与驱动 - - **表 1** 版本配套表 - - | 配套 | 版本 | 环境准备指导 | - | ---------- | ------- | ------------------------------------------------------------ | - | 固件与驱动 | 22.0.2 | [Pytorch框架推理环境准备](https://www.hiascend.com/document/detail/zh/ModelZoo/pytorchframework/pies) | - | CANN | 5.1.RC2 | - | - | Python | 3.7.5 | - | - - - # 快速上手 ## 获取源码 diff --git a/ACL_PyTorch/contrib/cv/detection/DSFD/public_address_statement.md b/ACL_PyTorch/contrib/cv/detection/DSFD/public_address_statement.md new file mode 100644 index 0000000000000000000000000000000000000000..da10bcab0d5ce9b3b6eed76b3ca75b67ef1fee93 --- /dev/null +++ b/ACL_PyTorch/contrib/cv/detection/DSFD/public_address_statement.md @@ -0,0 +1,6 @@ +| 类型 | 开源代码地址 | 文件名 | 公网IP地址/公网URL地址/域名/邮箱地 | 用途说明 | +| ---- | ----------- | ----- | -------------------------------- | --------| +| 开发引入 | / | ACL_PyTorch/contrib/cv/detection/DSFD/DSFD.patch | https://github.com/Hakuyume/chainer-ssd | 说明源码地址 | +| 开发引入 | / | ACL_PyTorch/contrib/cv/detection/DSFD/DSFD.patch | https://github.com/fmassa/object-detection.torch | 说明源码地址 | +| 开发引入 | / | ACL_PyTorch/contrib/cv/detection/DSFD/DSFD.patch | https://arxiv.org/pdf/1512.02325.pdf | 论文链接地址 | +| 开发引入 | / | ACL_PyTorch/contrib/cv/detection/DSFD/DSFD.patch | https://arxiv.org/pdf/1512.02325.pdf | 论文链接地址 | \ No newline at end of file diff --git a/ACL_PyTorch/contrib/cv/detection/Deepspeech/README.md b/ACL_PyTorch/contrib/cv/detection/Deepspeech/README.md index d431ebb170d81d718c10090e1257cac80fe2a82b..b6d0cbaac6f18bbcd5550b857869a63647db91b0 100644 --- a/ACL_PyTorch/contrib/cv/detection/Deepspeech/README.md +++ b/ACL_PyTorch/contrib/cv/detection/Deepspeech/README.md @@ -29,8 +29,6 @@ 深度学习框架与第三方库 ``` -python3.7.5 - torch == 1.8.0 torchaudio == 0.8.0 torchvision == 0.9.0 diff --git a/ACL_PyTorch/contrib/cv/detection/Detr/README.md b/ACL_PyTorch/contrib/cv/detection/Detr/README.md index f0ed2969a1b479ce929bfa9de0945e92838dcbc8..b3d53d5376651c83d2db8509a5f9cb25a5702027 100755 --- a/ACL_PyTorch/contrib/cv/detection/Detr/README.md +++ b/ACL_PyTorch/contrib/cv/detection/Detr/README.md @@ -2,8 +2,6 @@ - [概述](##概述) -- [推理环境准备](##推理环境准备) - - [快速上手](##快速上手) - [获取源码](##获取源码) @@ -65,19 +63,6 @@ DETR是将目标检测视为一个集合预测问题（集合其实和anchors的 | Pred_logits | 1 x 100 x 4 | FLOAT32 | NCHW | -## 推理环境准备[所有版本] - -- 该模型需要以下插件与驱动。 - - **表 1** 版本配套表 - -| 配套 | 版本 |环境准备指导 -| -------- | ------- |------------- -|固件与驱动 | 22.0.2 |[Pytorch框架推理环境准备](https://www.hiascend.com/document/detail/zh/ModelZoo/pytorchframework/pies) -| CANN | 5.1.RC2 |- -| PyTorch | 1.5.0 |- - - ## 快速上手 ## 获取源码 diff --git a/ACL_PyTorch/contrib/cv/detection/Detr/public_address_statement.md b/ACL_PyTorch/contrib/cv/detection/Detr/public_address_statement.md new file mode 100644 index 0000000000000000000000000000000000000000..1863588b77b9f04b158c43074e0ce5ca080adba4 --- /dev/null +++ b/ACL_PyTorch/contrib/cv/detection/Detr/public_address_statement.md @@ -0,0 +1,3 @@ +| 类型 | 开源代码地址 | 文件名 | 公网IP地址/公网URL地址/域名/邮箱地 | 用途说明 | +| ---- | ----------- | ----- | -------------------------------- | --------| +| 开发引入 | / | ACL_PyTorch/contrib/cv/detection/Detr/detr.patch | https://dl.fbaipublicfiles.com/detr/detr-r50-e632da11.pth | 权重下载链接 | \ No newline at end of file diff --git a/ACL_PyTorch/contrib/cv/detection/EAST_MobileNetV3/README.md b/ACL_PyTorch/contrib/cv/detection/EAST_MobileNetV3/README.md index 7602b49f0a2a75030279f902382d6b1d3425e382..86b098edbc7cefee92b3333633a95edf13a6d8a3 100644 --- a/ACL_PyTorch/contrib/cv/detection/EAST_MobileNetV3/README.md +++ b/ACL_PyTorch/contrib/cv/detection/EAST_MobileNetV3/README.md @@ -1,7 +1,6 @@ # EAST_MobileNetV3 模型推理指导 - [概述](#概述) -- [推理环境](#推理环境) - [快速上手](#快速上手) - [获取源码](#获取源码) - [准备数据集](#准备数据集) @@ -39,21 +38,6 @@ EAST是一个高效准确的场景文本检测器，通过两步进行文本检 | score | FLOAT32 | ND | batchsize x 1 x 176 x 320 | - ----- -# 推理环境 - -- 该模型推理所需配套的软件如下： - - | 配套 | 版本 | 环境准备指导 | - | --------- | ------- | ---------- | - | 固件与驱动 | 1.0.17 | [Pytorch框架推理环境准备](https://www.hiascend.com/document/detail/zh/ModelZoo/pytorchframework/pies) | - | CANN | 6.0.RC1 | - | - | Python | 3.7.5 | - | - - 说明：请根据 CANN 版本选择相匹配的固件与驱动版本。 - - ---- # 快速上手 diff --git a/ACL_PyTorch/contrib/cv/detection/EAST_ResNet50_vd/README.md b/ACL_PyTorch/contrib/cv/detection/EAST_ResNet50_vd/README.md index 89b4401097106729ade98b6db4282fea1f35f15b..e0f50bcdcaaf820843b21e4a5fda699df4de7ede 100644 --- a/ACL_PyTorch/contrib/cv/detection/EAST_ResNet50_vd/README.md +++ b/ACL_PyTorch/contrib/cv/detection/EAST_ResNet50_vd/README.md @@ -5,8 +5,6 @@ - [输入输出数据](#section540883920406) -- [推理环境准备](#ZH-CN_TOPIC_0000001126281702) - - [快速上手](#ZH-CN_TOPIC_0000001126281700) - [获取源码](#section4622531142816) @@ -15,7 +13,7 @@ - [模型推理性能&精度](#ZH-CN_TOPIC_0000001172201573) - ****** +****** # 概述 @@ -48,20 +46,6 @@ EAST是一个高效准确的场景文本检测器，通过两步进行文本检 | output2 | FLOAT32 | batchsize x 8 x 176 x 320 | NCHW | -# 推理环境准备\[所有版本\] - -- 该模型需要以下插件与驱动 - - **表 1** 版本配套表 - -| 配套 | 版本 | 环境准备指导 | -| ------------------------------------------------------------ | ------- | ------------------------------------------------------------ | -| 固件与驱动 | 1.0.17 | [Pytorch框架推理环境准备](https://www.hiascend.com/document/detail/zh/ModelZoo/pytorchframework/pies) | -| CANN | 6.0.RC1 | - | -| Python | 3.7.5 | - | -| paddlepaddle | 2.3.2 | - | -| 说明：Atlas 300I Duo 推理卡请以CANN版本选择实际固件与驱动版本。 | \ | \ | - # 快速上手 ## 获取源码 diff --git a/ACL_PyTorch/contrib/cv/detection/EfficientDetD0/README.md b/ACL_PyTorch/contrib/cv/detection/EfficientDetD0/README.md index 50cbf513a8ccc5db09377ddfc7efe304f58d6b34..469b7d71e0dd07a52c32fb78253bfac4e24fbb3b 100755 --- a/ACL_PyTorch/contrib/cv/detection/EfficientDetD0/README.md +++ b/ACL_PyTorch/contrib/cv/detection/EfficientDetD0/README.md @@ -5,10 +5,6 @@ - [输入输出数据](#section540883920406) - - -- [推理环境准备](#ZH-CN_TOPIC_0000001126281702) - - [快速上手](#ZH-CN_TOPIC_0000001126281700) - [获取源码](#section4622531142816) @@ -17,7 +13,7 @@ - [模型推理性能&精度](#ZH-CN_TOPIC_0000001172201573) - ****** +****** @@ -66,24 +62,6 @@ EfficientDet是在EfficientNet基础上提出来的目标检测模型，它将Ef -# 推理环境准备 - -- 该模型需要以下插件与驱动 - - **表 1** 版本配套表 - - | 配套 | 版本 | 环境准备指导 | - | ------------------------------------------------------------ | ------- | ------------------------------------------------------------ | - | 固件与驱动 | 22.0.2 | [Pytorch框架推理环境准备](https://www.hiascend.com/document/detail/zh/ModelZoo/pytorchframework/pies) | - | CANN | 6.0.RC1 | - | - | Python | 3.7.5 | - | - | PyTorch | 1.8.0 | - | - | 说明：Atlas 300I Duo 推理卡请以CANN版本选择实际固件与驱动版本。 | \ | \ | - - - - - # 快速上手 ## 获取源码 diff --git a/ACL_PyTorch/contrib/cv/detection/EfficientDetD0/public_address_statement.md b/ACL_PyTorch/contrib/cv/detection/EfficientDetD0/public_address_statement.md new file mode 100644 index 0000000000000000000000000000000000000000..144f0301f8c9bf0a3072812a6e306d3f3c5f971c --- /dev/null +++ b/ACL_PyTorch/contrib/cv/detection/EfficientDetD0/public_address_statement.md @@ -0,0 +1,28 @@ +| 类型 | 开源代码地址 | 文件名 | 公网IP地址/公网URL地址/域名/邮箱地址 | 用途说明 | +| ---- | ------------ | ------ | ------------------------------------ | -------- | +| 开源代码引入 |https://github.com/rwightman/efficientdet-pytorch/| ACL_PyTorch/contrib/cv/detection/EfficientDetD0/effdet.patch | https://github.com/rwightman/efficientdet-pytorch/releases/download/v0.1/efficientdet_d0-f3276ba8.pth | 权重下载链接 | +| 开源代码引入 |https://github.com/rwightman/efficientdet-pytorch/| ACL_PyTorch/contrib/cv/detection/EfficientDetD0/effdet.patch | https://github.com/rwightman/efficientdet-pytorch/releases/download/v0.1/efficientdet_d1-bb7e98fe.pth | 重下载链接 | +| 开源代码引入 |https://github.com/rwightman/efficientdet-pytorch/| ACL_PyTorch/contrib/cv/detection/EfficientDetD0/effdet.patch | https://github.com/rwightman/efficientdet-pytorch/releases/download/v0.1/resdet50_416-08676892.pth | 重下载链接 | +| 开源代码引入 |https://github.com/rwightman/efficientdet-pytorch/| ACL_PyTorch/contrib/cv/detection/EfficientDetD0/effdet.patch | https://github.com/rwightman/efficientdet-pytorch/releases/download/v0.1/cspresdet50b-386da277.pth | 重下载链接 | +| 开源代码引入 |https://github.com/rwightman/efficientdet-pytorch/| ACL_PyTorch/contrib/cv/detection/EfficientDetD0/effdet.patch | https://github.com/rwightman/efficientdet-pytorch/releases/download/v0.1/cspresdext50pan-92fdd094.pth | 重下载链接 | +| 开源代码引入 |https://github.com/rwightman/efficientdet-pytorch/| ACL_PyTorch/contrib/cv/detection/EfficientDetD0/effdet.patch | https://github.com/rwightman/efficientdet-pytorch/releases/download/v0.1/cspdarkdet53m-79062b2d.pth | 重下载链接 | +| 开源代码引入 |https://github.com/rwightman/efficientdet-pytorch/| ACL_PyTorch/contrib/cv/detection/EfficientDetD0/effdet.patch | https://github.com/rwightman/efficientdet-pytorch/releases/download/v0.1/efficientdet_q0-bdf1bdb5.pth | 重下载链接 | +| 开源代码引入 |https://github.com/rwightman/efficientdet-pytorch/| ACL_PyTorch/contrib/cv/detection/EfficientDetD0/effdet.patch | https://github.com/rwightman/efficientdet-pytorch/releases/download/v0.1/efficientdet_q1b-d0612140.pth | 重下载链接 | +| 开源代码引入 |https://github.com/rwightman/efficientdet-pytorch/| ACL_PyTorch/contrib/cv/detection/EfficientDetD0/effdet.patch | https://github.com/rwightman/efficientdet-pytorch/releases/download/v0.1/efficientdet_q2-0f7564e5.pth | 重下载链接 | +| 开源代码引入 |https://github.com/rwightman/efficientdet-pytorch/| ACL_PyTorch/contrib/cv/detection/EfficientDetD0/effdet.patch | https://github.com/rwightman/efficientdet-pytorch/releases/download/v0.1/tf_efficientdet_d0_34-f153e0cf.pth | 重下载链接 | +| 开源代码引入 |https://github.com/rwightman/efficientdet-pytorch/| ACL_PyTorch/contrib/cv/detection/EfficientDetD0/effdet.patch | https://github.com/rwightman/efficientdet-pytorch/releases/download/v0.1/tf_efficientdet_d1_40-a30f94af.pth | 重下载链接 | +| 开源代码引入 |https://github.com/rwightman/efficientdet-pytorch/| ACL_PyTorch/contrib/cv/detection/EfficientDetD0/effdet.patch | https://github.com/rwightman/efficientdet-pytorch/releases/download/v0.1/tf_efficientdet_d2_43-8107aa99.pth | 重下载链接 | +| 开源代码引入 |https://github.com/rwightman/efficientdet-pytorch/| ACL_PyTorch/contrib/cv/detection/EfficientDetD0/effdet.patch | https://github.com/rwightman/efficientdet-pytorch/releases/download/v0.1/tf_efficientdet_d3_47-0b525f35.pth | 重下载链接 | +| 开源代码引入 |https://github.com/rwightman/efficientdet-pytorch/| ACL_PyTorch/contrib/cv/detection/EfficientDetD0/effdet.patch | https://github.com/rwightman/efficientdet-pytorch/releases/download/v0.1/tf_efficientdet_d4_49-f56376d9.pth | 重下载链接 | +| 开源代码引入 |https://github.com/rwightman/efficientdet-pytorch/| ACL_PyTorch/contrib/cv/detection/EfficientDetD0/effdet.patch | https://github.com/rwightman/efficientdet-pytorch/releases/download/v0.1/tf_efficientdet_d5_51-c79f9be6.pth | 重下载链接 | +| 开源代码引入 |https://github.com/rwightman/efficientdet-pytorch/| ACL_PyTorch/contrib/cv/detection/EfficientDetD0/effdet.patch | https://github.com/rwightman/efficientdet-pytorch/releases/download/v0.1/tf_efficientdet_d6_52-4eda3773.pth | 重下载链接 | +| 开源代码引入 |https://github.com/rwightman/efficientdet-pytorch/| ACL_PyTorch/contrib/cv/detection/EfficientDetD0/effdet.patch | https://github.com/rwightman/efficientdet-pytorch/releases/download/v0.1/tf_efficientdet_d7_53-6d1d7a95.pth | 重下载链接 | +| 开源代码引入 |https://github.com/rwightman/efficientdet-pytorch/| ACL_PyTorch/contrib/cv/detection/EfficientDetD0/effdet.patch | https://github.com/rwightman/efficientdet-pytorch/releases/download/v0.1/tf_efficientdet_d7x-f390b87c.pth | 重下载链接 | +| 开源代码引入 |https://github.com/rwightman/efficientdet-pytorch/| ACL_PyTorch/contrib/cv/detection/EfficientDetD0/effdet.patch | https://github.com/google/automl/blob/master/efficientdet/Det-AdvProp.md | 引用原网址 | +| 开源代码引入 |https://github.com/rwightman/efficientdet-pytorch/| ACL_PyTorch/contrib/cv/detection/EfficientDetD0/effdet.patch | https://github.com/rwightman/efficientdet-pytorch/releases/download/v0.1/tf_efficientdet_d0_ap-d0cdbd0a.pth | 重下载链接 | +| 开源代码引入 |https://github.com/rwightman/efficientdet-pytorch/| ACL_PyTorch/contrib/cv/detection/EfficientDetD0/effdet.patch | https://github.com/rwightman/efficientdet-pytorch/releases/download/v0.1/tf_efficientdet_d1_ap-7721d075.pth | 重下载链接 | +| 开源代码引入 |https://github.com/rwightman/efficientdet-pytorch/| ACL_PyTorch/contrib/cv/detection/EfficientDetD0/effdet.patch | https://github.com/rwightman/efficientdet-pytorch/releases/download/v0.1/tf_efficientdet_d2_ap-a2995c19.pth | 重下载链接 | +| 开源代码引入 |https://github.com/rwightman/efficientdet-pytorch/| ACL_PyTorch/contrib/cv/detection/EfficientDetD0/effdet.patch | https://github.com/rwightman/efficientdet-pytorch/releases/download/v0.1/tf_efficientdet_d3_ap-e4a2feab.pth | 重下载链接 | +| 开源代码引入 |https://github.com/rwightman/efficientdet-pytorch/| ACL_PyTorch/contrib/cv/detection/EfficientDetD0/effdet.patch | https://github.com/rwightman/efficientdet-pytorch/releases/download/v0.1/tf_efficientdet_d4_ap-f601a5fc.pth | 重下载链接 | +| 开源代码引入 |https://github.com/rwightman/efficientdet-pytorch/| ACL_PyTorch/contrib/cv/detection/EfficientDetD0/effdet.patch | https://github.com/rwightman/efficientdet-pytorch/releases/download/v0.1/tf_efficientdet_d5_ap-3673ae5d.pth | 重下载链接 | +| 开源代码引入 |https://github.com/rwightman/efficientdet-pytorch/| ACL_PyTorch/contrib/cv/detection/EfficientDetD0/effdet.patch | https://github.com/rwightman/efficientdet-pytorch/releases/download/v0.1/tf_efficientdet_lite0-f5f303a9.pth | 重下载链接 | \ No newline at end of file diff --git a/ACL_PyTorch/contrib/cv/detection/EfficientDetD7/README.md b/ACL_PyTorch/contrib/cv/detection/EfficientDetD7/README.md index ea2836d7a8c6c97b516cc4ea916f1a9f77cf0d66..ea0d8df9ab0ad593be0410765d5f37c59566f3d9 100644 --- a/ACL_PyTorch/contrib/cv/detection/EfficientDetD7/README.md +++ b/ACL_PyTorch/contrib/cv/detection/EfficientDetD7/README.md @@ -4,7 +4,6 @@ - [概述](#概述) - [输入输出数据](#输入输出数据) -- [推理环境准备](#推理环境准备) - [快速上手](#快速上手) - [获取源码](#获取源码) @@ -56,21 +55,6 @@ EfficientDet该论文首先提出了一种加权双向特征金字塔网络（Bi | boxout5 | batchsize x 36 x 12 x 12 | FLOAT32 | NCHW | -# 推理环境准备 - -- 该模型需要以下插件与驱动 - - **表 1** 版本配套表 - - | 配套 | 版本 | 环境准备指导 | - | ------------------------------------------------------------ | ------- | ------------------------------------------------------------ | - | 固件与驱动 | 22.0.2 | [Pytorch框架推理环境准备](https://www.hiascend.com/document/detail/zh/ModelZoo/pytorchframework/pies) | - | CANN | 6.0.RC1 | - | - | Python | 3.7.5 | - | - | PyTorch | 1.8.0 | - | - | 说明：Atlas 300I Duo 推理卡请以CANN版本选择实际固件与驱动版本。 | \ | \ | - - # 快速上手 diff --git a/ACL_PyTorch/contrib/cv/detection/FCENet/public_address_statement.md b/ACL_PyTorch/contrib/cv/detection/FCENet/public_address_statement.md index a5e4591f245b541fa546938251534aa350d4e2c6..7ff4d9b1724ec13303de8325cf2e2f3c342c7ba3 100644 --- a/ACL_PyTorch/contrib/cv/detection/FCENet/public_address_statement.md +++ b/ACL_PyTorch/contrib/cv/detection/FCENet/public_address_statement.md @@ -1,4 +1,3 @@ - | 类型 | 开源代码地址 | 文件名 | 公网IP地址/公网URL地址/域名/邮箱地址 | 用途说明 | | ---- | ------------ | ------ | ------------------------------------ | -------- | |开发引入|/|FCENet/url.ini|https://download.openmmlab.com/mmocr/textdet/|下载数据集| diff --git a/ACL_PyTorch/contrib/cv/detection/FCENet/readme.md b/ACL_PyTorch/contrib/cv/detection/FCENet/readme.md index a93f2c0121cde1ddfc505487ed2d2798118eb044..75c94967067755f092ad95f9eb725f268f0fcb43 100644 --- a/ACL_PyTorch/contrib/cv/detection/FCENet/readme.md +++ b/ACL_PyTorch/contrib/cv/detection/FCENet/readme.md @@ -2,7 +2,6 @@ - [概述](#概述) - [输入输出数据](#输入输出数据) -- [推理环境](#推理环境) - [快速上手](#快速上手) - [获取源码](#获取源码) - [准备数据集](#准备数据集) @@ -40,19 +39,6 @@ FCENet，使用傅里叶变换来得到文本的包围框，该方法在弯曲 | output5 | FLOAT32 | ND | bs x 4 x 40 x 71 | | output6 | FLOAT32 | ND | bs x 22 x 40 x 71 | ----- -# 推理环境 - -- 该模型推理所需配套的软件如下： - - | 配套 | 版本 | 环境准备指导 | - | --------- | ------- | ---------- | - | 固件与驱动 | 1.0.17 | [Pytorch框架推理环境准备](https://www.hiascend.com/document/detail/zh/ModelZoo/pytorchframework/pies) | - | CANN | 6.0.RC1 | - | - | Python | 3.7.5 | - | - - 说明：请根据推理卡型号与 CANN 版本选择相匹配的固件与驱动版本。 - ---- # 快速上手 diff --git a/ACL_PyTorch/contrib/cv/detection/FairMOT/README.md b/ACL_PyTorch/contrib/cv/detection/FairMOT/README.md index aad8081f4ddded6a395e948c727d96cb84273001..28cc9fec6814e38a561b71784ec990d4b809dbdc 100644 --- a/ACL_PyTorch/contrib/cv/detection/FairMOT/README.md +++ b/ACL_PyTorch/contrib/cv/detection/FairMOT/README.md @@ -5,8 +5,6 @@ - [输入输出数据](#section540883920406) -- [推理环境准备](#ZH-CN_TOPIC_0000001126281702) - - [快速上手](#ZH-CN_TOPIC_0000001126281700) - [获取源码](#section4622531142816) @@ -15,7 +13,7 @@ - [模型推理性能&精度](#ZH-CN_TOPIC_0000001172201573) - ****** +****** # 概述 @@ -50,24 +48,6 @@ FairMOT用于目标跟踪，它使用基于CenterNet的方法进行目标检测 - - -# 推理环境准备 - -- 该模型需要以下插件与驱动 - - **表 1** 版本配套表 - - | 配套 | 版本 | 环境准备指导 | - | ------------------------------------------------------------ | ------- | ------------------------------------------------------------ | - | 固件与驱动 | 22.0.3 | [Pytorch框架推理环境准备](https://www.hiascend.com/document/detail/zh/ModelZoo/pytorchframework/pies) | - | CANN | 6.0.RC1 | - | - | Python | 3.7.5 | - | - | PyTorch | 1.6.0 | - | - | 说明：Atlas 300I Duo 推理卡请以CANN版本选择实际固件与驱动版本。 | \ | \ | - - - # 快速上手 ## 获取源码 diff --git a/ACL_PyTorch/contrib/cv/detection/Faster_R-CNN_DCN_Res101/readme.md b/ACL_PyTorch/contrib/cv/detection/Faster_R-CNN_DCN_Res101/readme.md index 7bb5e4f6be89cbecee9156033303b9e3588ad9ae..a71be6525da532d0df05ce4bd0f4f0c43fc95e26 100644 --- a/ACL_PyTorch/contrib/cv/detection/Faster_R-CNN_DCN_Res101/readme.md +++ b/ACL_PyTorch/contrib/cv/detection/Faster_R-CNN_DCN_Res101/readme.md @@ -3,8 +3,6 @@ - [概述](#ZH-CN_TOPIC_0000001172161501) -- [推理环境准备](#ZH-CN_TOPIC_0000001126281702) - - [快速上手](#ZH-CN_TOPIC_0000001126281700) - [获取源码](#section4622531142816) @@ -13,10 +11,6 @@ - [模型推理性能](#ZH-CN_TOPIC_0000001172201573) -- [配套环境](#ZH-CN_TOPIC_0000001126121892) - - - # 概述 @@ -53,21 +47,6 @@ FasterRCNN-DCN是FasterRCNN与DCN可行变卷积相结合得到的网络模型 - -# 推理环境准备\[所有版本\] - -- 该模型需要以下插件与驱动 - - **表 1** 版本配套表 - -| 配套 | 版本 | 环境准备指导 | -| ------------------------------------------------------------ | ------- | ------------------------------------------------------------ | -| 固件与驱动 | 1.0.17 | [Pytorch框架推理环境准备](https://www.hiascend.com/document/detail/zh/ModelZoo/pytorchframework/pies) | -| CANN | 6.0.RC1 | - | -| Python | 3.7.5 | - | -| PyTorch | 1.8.0 | - | -| 说明：Atlas 300I Duo 推理卡请以CANN版本选择实际固件与驱动版本。 | \ | \ | - # 快速上手 1. 下载本模型代码包，并上传至服务器解压至用户目录下 diff --git a/ACL_PyTorch/contrib/cv/detection/Faster_R-CNN_DCN_Res50/README.md b/ACL_PyTorch/contrib/cv/detection/Faster_R-CNN_DCN_Res50/README.md index 69917024ef13a570dd9d68645e9927f763fe7f87..d3976865260eff99c92441be8f3b82b8320206f9 100644 --- a/ACL_PyTorch/contrib/cv/detection/Faster_R-CNN_DCN_Res50/README.md +++ b/ACL_PyTorch/contrib/cv/detection/Faster_R-CNN_DCN_Res50/README.md @@ -3,8 +3,6 @@ - [概述](#ZH-CN_TOPIC_0000001172161501) -- [推理环境准备](#ZH-CN_TOPIC_0000001126281702) - - [快速上手](#ZH-CN_TOPIC_0000001126281700) - [获取源码](#section4622531142816) @@ -13,7 +11,6 @@ - [模型推理性能](#ZH-CN_TOPIC_0000001172201573) -- [配套环境](#ZH-CN_TOPIC_0000001126121892) # 概述 @@ -47,21 +44,6 @@ FasterRCNN-DCN是FasterRCNN与DCN可行变卷积相结合得到的网络模型 | labels | 100 × 1 | INT64 | ND | - -# 推理环境准备\[所有版本\] - -- 该模型需要以下插件与驱动 - - **表 1** 版本配套表 - -| 配套 | 版本 | 环境准备指导 | -| ------------------------------------------------------------ | ------- | ------------------------------------------------------------ | -| 固件与驱动 | 1.0.17 | [Pytorch框架推理环境准备](https://www.hiascend.com/document/detail/zh/ModelZoo/pytorchframework/pies) | -| CANN | 6.0.RC1 | - | -| Python | 3.7.5 | - | -| PyTorch | 1.8.0 | - | -| 说明：Atlas 300I Duo 推理卡请以CANN版本选择实际固件与驱动版本。 | \ | \ | - # 快速上手 1. 下载本模型代码包，并上传至服务器解压至用户目录下 diff --git a/ACL_PyTorch/contrib/cv/detection/Faster_R-CNN_ResNet50/README.md b/ACL_PyTorch/contrib/cv/detection/Faster_R-CNN_ResNet50/README.md index 4eef86588e5987a4aa138b58a0ea67a383b07a09..9b45475739bdada93e0a7dca2846600e38b4a7f5 100644 --- a/ACL_PyTorch/contrib/cv/detection/Faster_R-CNN_ResNet50/README.md +++ b/ACL_PyTorch/contrib/cv/detection/Faster_R-CNN_ResNet50/README.md @@ -3,8 +3,6 @@ - [概述](#ZH-CN_TOPIC_0000001172161501) -- [推理环境准备](#ZH-CN_TOPIC_0000001126281702) - - [快速上手](#ZH-CN_TOPIC_0000001126281700) - [获取源码](#section4622531142816) @@ -13,9 +11,7 @@ - [模型推理性能](#ZH-CN_TOPIC_0000001172201573) -- [配套环境](#ZH-CN_TOPIC_0000001126121892) - - ****** +****** @@ -53,18 +49,6 @@ Faster-R-CNN 在Fast RCNN的基础上使用RPN层代替Selective Search提取候 | labels | 100 | INT64 | ND | -# 推理环境准备 - -- 该模型需要以下插件与驱动 - -| 配套 | 版本 | 环境准备指导 | -| ------------------------------------------------------------ | ------- | ------------------------------------------------------------ | -| 固件与驱动 | 22.0.3 | [Pytorch框架推理环境准备](https://www.hiascend.com/document/detail/zh/ModelZoo/pytorchframework/pies) | -| CANN | 6.0.RC1 | - | -| Python | 3.7.5 | - | -| PyTorch | 1.8.1 | - | -| 说明：Atlas 300I Duo 推理卡请以CANN版本选择实际固件与驱动版本。 | \ | \ | - # 快速上手 ## 获取源码 diff --git a/ACL_PyTorch/contrib/cv/detection/ch_PP-OCRv2_det/README.md b/ACL_PyTorch/contrib/cv/detection/ch_PP-OCRv2_det/README.md index b8a4ac3bb512a261f0780ababa47251033117846..73b07e25706fbc0585e3b76d409a9aaa1f754a5e 100644 --- a/ACL_PyTorch/contrib/cv/detection/ch_PP-OCRv2_det/README.md +++ b/ACL_PyTorch/contrib/cv/detection/ch_PP-OCRv2_det/README.md @@ -3,8 +3,6 @@ - [概述](#ZH-CN_TOPIC_0000001172161501) -- [推理环境准备](#ZH-CN_TOPIC_0000001126281702) - - [快速上手](#ZH-CN_TOPIC_0000001126281700) - [获取源码](#section4622531142816) @@ -13,7 +11,6 @@ - [模型推理性能](#ZH-CN_TOPIC_0000001172201573) -- [配套环境](#ZH-CN_TOPIC_0000001126121892) # 概述 @@ -46,20 +43,6 @@ ch_PP-OCRv2_det是基于PP-OCRv2的中文文本检测模型，PP-OCRv2在PP-OCR | output1 | FLOAT32 | batchsize x 1 x imgH x imgW | NCHW | -# 推理环境准备\[所有版本\] - -- 该模型需要以下插件与驱动 - - **表 1** 版本配套表 - -| 配套 | 版本 | 环境准备指导 | -| ------------------------------------------------------------ | ------- | ------------------------------------------------------------ | -| 固件与驱动 | 22.0.2 | [Pytorch框架推理环境准备](https://www.hiascend.com/document/detail/zh/ModelZoo/pytorchframework/pies) | -| CANN | 5.1.RC2 | - | -| Python | 3.7.5 | - | -| paddlepaddle | 2.3.2 |仅支持x86服务器安装 | -| 说明：Atlas 300I Duo 推理卡请以CANN版本选择实际固件与驱动版本。 | \ | \ | - # 快速上手 ## 获取源码 diff --git a/ACL_PyTorch/contrib/cv/detection/ch_PP-OCRv3_det/README.md b/ACL_PyTorch/contrib/cv/detection/ch_PP-OCRv3_det/README.md index 280efa56f364b0568f31534b0bba25c726234760..dbdd061808f1aa1a11339b2d1d812a28609db54c 100644 --- a/ACL_PyTorch/contrib/cv/detection/ch_PP-OCRv3_det/README.md +++ b/ACL_PyTorch/contrib/cv/detection/ch_PP-OCRv3_det/README.md @@ -2,7 +2,6 @@ - [概述](#ZH-CN_TOPIC_0000001172161501) -- [推理环境准备](#ZH-CN_TOPIC_0000001126281702) - [快速上手](#ZH-CN_TOPIC_0000001126281700) - [获取源码](#section4622531142816) @@ -42,20 +41,6 @@ ch_PP-OCRv3_det是基于PP-OCRv3的中文文本检测模型，PP-OCRv3在PP-OCR2 | output1 | FLOAT32 | batchsize x 1 x imgH x imgW | NCHW | -# 推理环境准备\[所有版本\] - -- 该模型需要以下插件与驱动 - - **表 1** 版本配套表 - -| 配套 | 版本 | 环境准备指导 | -| ------------------------------------------------------------ | ------- | ------------------------------------------------------------ | -| 固件与驱动 | 1.0.17 | [Pytorch框架推理环境准备](https://www.hiascend.com/document/detail/zh/ModelZoo/pytorchframework/pies) | -| CANN | 6.0.RC1 | - | -| Python | 3.7.5 | - | -| paddlepaddle | 2.3.1 | 仅支持x86服务器安装 | -| 说明：Atlas 300I Duo 推理卡请以CANN版本选择实际固件与驱动版本。 | \ | \ | - # 快速上手 ## 获取源码 diff --git a/ACL_PyTorch/contrib/cv/detection/ch_ppocr_server_v2.0_det/README.md b/ACL_PyTorch/contrib/cv/detection/ch_ppocr_server_v2.0_det/README.md index 031a72e643956dde19d8d5cffdcc70df1a77d160..54bd818850429f8bc4f779fcfa8d96a9a1a12886 100644 --- a/ACL_PyTorch/contrib/cv/detection/ch_ppocr_server_v2.0_det/README.md +++ b/ACL_PyTorch/contrib/cv/detection/ch_ppocr_server_v2.0_det/README.md @@ -5,8 +5,6 @@ - [输入输出数据](#section540883920406) -- [推理环境准备](#ZH-CN_TOPIC_0000001126281702) - - [快速上手](#ZH-CN_TOPIC_0000001126281700) - [获取源码](#section4622531142816) @@ -47,20 +45,6 @@ ch_PP-OCRv2_det是基于PP-OCRv2的中文文本检测模型，PP-OCRv2在PP-OCR | output1 | FLOAT32 | batchsize x 1 x imgH x imgW | NCHW | -# 推理环境准备\[所有版本\] - -- 该模型需要以下插件与驱动 - - **表 1** 版本配套表 - - | 配套 | 版本 | 环境准备指导 | - | ------------------------------------------------------------ | ------- | ------------------------------------------------------------ | - | 固件与驱动 | 22.0.2 | [Pytorch框架推理环境准备](https://www.hiascend.com/document/detail/zh/ModelZoo/pytorchframework/pies) | - | CANN | 5.1.RC2 | - | - | Python | 3.7.5 | - | - | paddlepaddle | 2.3.2 | 仅支持x86服务器安装 | - | 说明：Atlas 300I Duo 推理卡请以CANN版本选择实际固件与驱动版本。 | \ | \ | - # 快速上手 ## 获取源码 diff --git a/ACL_PyTorch/contrib/cv/detection/en_PP-OCRv3_det/README.md b/ACL_PyTorch/contrib/cv/detection/en_PP-OCRv3_det/README.md index d0405bbc474d377088beb88965a04a7c5a2f4574..0cb793c6ffc89faebb5fbd7db9803bc3e1442b37 100644 --- a/ACL_PyTorch/contrib/cv/detection/en_PP-OCRv3_det/README.md +++ b/ACL_PyTorch/contrib/cv/detection/en_PP-OCRv3_det/README.md @@ -3,8 +3,6 @@ - [概述](#ZH-CN_TOPIC_0000001172161501) -- [推理环境准备](#ZH-CN_TOPIC_0000001126281702) - - [快速上手](#ZH-CN_TOPIC_0000001126281700) - [获取源码](#section4622531142816) @@ -13,7 +11,6 @@ - [模型推理性能](#ZH-CN_TOPIC_0000001172201573) -- [配套环境](#ZH-CN_TOPIC_0000001126121892) # 概述 @@ -46,20 +43,6 @@ en_PP-OCRv3_det是基于[[PP-OCRv3](https://github.com/PaddlePaddle/PaddleOCR/bl | output1 | FLOAT32 | batchsize x 1 x imgH x imgW | NCHW | -# 推理环境准备\[所有版本\] - -- 该模型需要以下插件与驱动 - - **表 1** 版本配套表 - -| 配套 | 版本 | 环境准备指导 | -| ------------------------------------------------------------ | ------- | ------------------------------------------------------------ | -| 固件与驱动 | 22.0.2 | [Pytorch框架推理环境准备](https://www.hiascend.com/document/detail/zh/ModelZoo/pytorchframework/pies) | -| CANN | 5.1.RC2 | - | -| Python | 3.7.5 | - | -| PaddlePaddle | 2.3.2 | 仅支持x86服务器安装 | -| 说明：Atlas 300I Duo 推理卡请以CANN版本选择实际固件与驱动版本。 | \ | \ | - # 快速上手 ## 获取源码