# FastDeploy **Repository Path**: seanpan2016/FastDeploy ## Basic Information - **Project Name**: FastDeploy - **Description**: 深度学习部署工具，多平台多模型 - **Primary Language**: Unknown - **License**: Apache-2.0 - **Default Branch**: develop - **Homepage**: None - **GVP Project**: No ## Statistics - **Stars**: 0 - **Forks**: 1 - **Created**: 2024-08-16 - **Last Updated**: 2024-08-16 ## Categories & Tags **Categories**: Uncategorized **Tags**: None ## README [English](README_EN.md) | 简体中文 | [हिन्दी](./docs/docs_i18n/README_हिन्दी.md) | [日本語](./docs/docs_i18n/README_日本語.md) | [한국인](./docs/docs_i18n/README_한국인.md) | [Pу́сский язы́к](./docs/docs_i18n/README_Pу́сский_язы́к.md) ![⚡️FastDeploy](https://user-images.githubusercontent.com/31974251/185771818-5d4423cd-c94c-4a49-9894-bc7a8d1c29d0.png)

安装 | 使用文档 | 快速开始 | API文档 | 更新日志

[](examples/vision/classification) [](examples/vision/detection) [](examples/vision/segmentation/paddleseg) [](examples/vision/segmentation/paddleseg) [](examples/vision/matting) [](examples/vision/matting) [](examples/vision/ocr)
[](examples/vision/facealign) [](examples/vision/keypointdetection) [](https://user-images.githubusercontent.com/54695910/200162475-f5d85d70-18fb-4930-8e7e-9ca065c1d618.gif) [](examples/text) [](https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/parakeet_espnet_fs2_pwg_demo/tn_g2p/parakeet/001.wav)
**⚡️FastDeploy**是一款**全场景**、**易用灵活**、**极致高效**的AI推理部署工具， 支持**云边端**部署。提供超过 🔥160+ **Text**，**Vision**， **Speech**和**跨模态**模型📦**开箱即用**的部署体验，并实现🔚**端到端**的推理性能优化。包括 [物体检测](./examples/vision/detection)、[字符识别（OCR）](./examples/vision/ocr)、[人脸](./examples/vision/facedet)、[人像扣图](./examples/vision/matting)、[多目标跟踪系统](./examples/vision/tracking/pptracking)、[NLP](./examples/text)、[Stable Diffusion文图生成](./examples/multimodal/stable_diffusion)、[TTS](./examples/audio/pp-tts) 等几十种任务场景，满足开发者**多场景、多硬件、多平台**的产业部署需求。
## 🌠 近期更新 - FastDeploy系列[**直播课程回放**](https://aistudio.baidu.com/aistudio/education/group/info/27800) - **2023.01.17** 发布 [**YOLOv8**](./examples/vision/detection/paddledetection/) 在FastDeploy系列硬件的部署支持。 其中包括 [**Paddle YOLOv8**](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/yolov8) 以及 [**社区 ultralytics YOLOv8**](https://github.com/ultralytics/ultralytics) - [**Paddle YOLOv8**](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/yolov8) 可以部署的硬件：[**Intel CPU**](./examples/vision/detection/paddledetection/python/infer_yolov8.py)、[**NVIDIA GPU**](./examples/vision/detection/paddledetection/python/infer_yolov8.py)、[**Jetson**](./examples/vision/detection/paddledetection/python/infer_yolov8.py)、[**飞腾**](./examples/vision/detection/paddledetection/python/infer_yolov8.py)、[**昆仑芯**](./examples/vision/detection/paddledetection/python/infer_yolov8.py)、[**昇腾**](./examples/vision/detection/paddledetection/python/infer_yolov8.py)、[**ARM CPU**](./examples/vision/detection/paddledetection/cpp/infer_yolov8.cc)、[**RK3588**](./examples/vision/detection/paddledetection/rknpu2) 和 [**Sophgo TPU**](./examples/vision/detection/paddledetection/sophgo), 部分硬件包含 **Python** 部署和 **C++** 部署； - [**社区 ultralytics YOLOv8**](https://github.com/ultralytics/ultralytics) 可以部署的硬件：[**Intel CPU**](./examples/vision/detection/yolov8)、[**NVIDIA GPU**](./examples/vision/detection/yolov8)、[**Jetson**](./examples/vision/detection/yolov8)，均包含 **Python** 部署和 **C++** 部署； - FastDeploy 一行模型API切换，可以实现**YOLOv8**、 **PP-YOLOE+**、**YOLOv5** 等模型性能对比。 - 服务化部署结合VisualDL新增支持可视化部署。在FastDeploy容器中启动VDL服务后，即可在VDL界面修改模型配置、启动/管理模型服务、查看性能数据、发送请求等，详细操作可参考相关文档 - [Serving可视化部署](https://github.com/PaddlePaddle/FastDeploy/blob/develop/serving/docs/zh_CN/vdl_management.md) - [Serving可视化请求](https://github.com/PaddlePaddle/FastDeploy/blob/develop/serving/docs/zh_CN/client.md#%E4%BD%BF%E7%94%A8fastdeploy-client%E8%BF%9B%E8%A1%8C%E5%8F%AF%E8%A7%86%E5%8C%96%E8%AF%B7%E6%B1%82) - **✨👥✨ 社区交流** - **Slack**：Join our [Slack community](https://join.slack.com/t/fastdeployworkspace/shared_invite/zt-1o50e4voz-zbiIneCNRf_eH99eS2NVLg) and chat with other community members about ideas - **微信**：扫描二维码，填写问卷加入技术社区，与社区开发者交流部署产业落地痛点问题
## 🌌 推理后端及能力 | | | || | | | | |:----------|:----------:|:----------:|:----------:|:----------:|:----------:|:----------:|:----------:| | X86_64 CPU | |       | |

|

| |

| | NVDIA GPU | | |
|

|

| | | |飞腾 CPU | | | |
| | | | | 昆仑芯 XPU | | | | | | | | | 华为昇腾 NPU | | |
| | | | | |Graphcore IPU | | | | | | | | | 算能 | | | | | | | | |Intel 显卡 | | | | | | | | |Jetson | | |
|

|

| | | |ARM CPU | | |
|
| | | | |RK3588等 | | | | | | | | |RV1126等 | | | | | | | | | 晶晨 | | | | | | | | | 恩智浦 | | | | | | | | ## 🔮 文档教程 - [✴️ Python SDK快速开始](#fastdeploy-quick-start-python) - [✴️ C++ SDK快速开始](#fastdeploy-quick-start-cpp) - **安装文档** - [预编译库下载安装](docs/cn/build_and_install/download_prebuilt_libraries.md) - [GPU部署环境编译安装](docs/cn/build_and_install/gpu.md) - [CPU部署环境编译安装](docs/cn/build_and_install/cpu.md) - [IPU部署环境编译安装](docs/cn/build_and_install/ipu.md) - [昆仑芯XPU部署环境编译安装](docs/cn/build_and_install/kunlunxin.md) - [瑞芯微RV1126部署环境编译安装](docs/cn/build_and_install/rv1126.md) - [瑞芯微RK3588部署环境编译安装](docs/cn/build_and_install/rknpu2.md) - [晶晨A311D部署环境编译安装](docs/cn/build_and_install/a311d.md) - [华为昇腾部署环境编译安装](docs/cn/build_and_install/huawei_ascend.md) - [Jetson部署环境编译安装](docs/cn/build_and_install/jetson.md) - [Android平台部署环境编译安装](docs/cn/build_and_install/android.md) - **快速使用** - [PP-YOLOE Python部署示例](docs/cn/quick_start/models/python.md) - [PP-YOLOE C++部署示例](docs/cn/quick_start/models/cpp.md) - **不同后端使用** - [Runtime Python使用示例](docs/cn/quick_start/runtime/python.md) - [Runtime C++使用示例](docs/cn/quick_start/runtime/cpp.md) - [如何配置模型部署的推理后端](docs/cn/faq/how_to_change_backend.md) - **服务化部署** - [服务化部署镜像编译安装](serving/docs/zh_CN/compile.md) - [服务化部署](serving) - **API文档** - [Python API文档](https://www.paddlepaddle.org.cn/fastdeploy-api-doc/python/html/) - [C++ API文档](https://www.paddlepaddle.org.cn/fastdeploy-api-doc/cpp/html/) - [Android Java API文档](java/android) - **性能调优** - [量化加速](docs/cn/quantize.md) - [多线程多进程使用](/tutorials/multi_thread) - **常见问题** - [1. Windows上C++ SDK如何使用](docs/cn/faq/use_sdk_on_windows.md) - [2. Android上如何使用FastDeploy C++ SDK](docs/cn/faq/use_cpp_sdk_on_android.md) - [3. TensorRT使用中的一些技巧](docs/cn/faq/tensorrt_tricks.md) - **更多FastDeploy部署模块** - [Benchmark测试](benchmark) - **模型支持列表** - [🖥️ 服务端 模型支持列表](#fastdeploy-server-models) - [📳 移动端和端侧 模型支持列表](#fastdeploy-edge-models) - [⚛️ Web和小程序 模型支持列表](#fastdeploy-web-models) - **💕开发者贡献** - [增加新模型](docs/cn/faq/develop_a_new_model.md)
## 快速开始💨
Python SDK快速开始（点开收缩）
### 🎆 快速安装 #### 🔸 前置依赖 - CUDA >= 11.2、cuDNN >= 8.0、Python >= 3.6 - OS: Linux x86_64/macOS/Windows 10 #### 🔸 安装GPU版本 ```bash pip install numpy opencv-python fastdeploy-gpu-python -f https://www.paddlepaddle.org.cn/whl/fastdeploy.html ``` #### [🔸 Conda安装(推荐✨)](docs/cn/build_and_install/download_prebuilt_libraries.md) ```bash conda config --add channels conda-forge && conda install cudatoolkit=11.2 cudnn=8.2 ``` #### 🔸 安装CPU版本 ```bash pip install numpy opencv-python fastdeploy-python -f https://www.paddlepaddle.org.cn/whl/fastdeploy.html ``` ### 🎇 Python 推理示例 * 准备模型和图片 ```bash wget https://bj.bcebos.com/paddlehub/fastdeploy/ppyoloe_crn_l_300e_coco.tgz tar xvf ppyoloe_crn_l_300e_coco.tgz wget https://gitee.com/paddlepaddle/PaddleDetection/raw/release/2.4/demo/000000014439.jpg ``` * 测试推理结果 ```python # GPU/TensorRT部署参考 examples/vision/detection/paddledetection/python import cv2 import fastdeploy.vision as vision model = vision.detection.PPYOLOE("ppyoloe_crn_l_300e_coco/model.pdmodel", "ppyoloe_crn_l_300e_coco/model.pdiparams", "ppyoloe_crn_l_300e_coco/infer_cfg.yml") im = cv2.imread("000000014439.jpg") result = model.predict(im) print(result) vis_im = vision.vis_detection(im, result, score_threshold=0.5) cv2.imwrite("vis_image.jpg", vis_im) ```
C++ SDK快速开始（点开查看详情）
### 🎆 安装 - 参考[C++预编译库下载](docs/cn/build_and_install/download_prebuilt_libraries.md)文档 #### 🎇 C++ 推理示例 * 准备模型和图片 ```bash wget https://bj.bcebos.com/paddlehub/fastdeploy/ppyoloe_crn_l_300e_coco.tgz tar xvf ppyoloe_crn_l_300e_coco.tgz wget https://gitee.com/paddlepaddle/PaddleDetection/raw/release/2.4/demo/000000014439.jpg ``` * 测试推理结果 ```C++ // GPU/TensorRT部署参考 examples/vision/detection/paddledetection/cpp #include "fastdeploy/vision.h" int main(int argc, char* argv[]) { namespace vision = fastdeploy::vision; auto model = vision::detection::PPYOLOE("ppyoloe_crn_l_300e_coco/model.pdmodel", "ppyoloe_crn_l_300e_coco/model.pdiparams", "ppyoloe_crn_l_300e_coco/infer_cfg.yml"); auto im = cv::imread("000000014439.jpg"); vision::DetectionResult res; model.Predict(im, &res); auto vis_im = vision::VisDetection(im, res, 0.5); cv::imwrite("vis_image.jpg", vis_im); return 0; } ```
更多部署案例请参考[模型部署示例](examples) .
## ✴️ ✴️ 服务端模型支持列表 ✴️ ✴️ 符号说明: (1) ✅ : 已经支持; (2) ❔: 正在进行中; (3) N/A : 暂不支持.
服务端模型支持列表（点击可收缩）
| 任务场景 | 模型 | Linux | Linux | Win | Win | Mac | Mac | Linux | Linux | Linux | Linux | Linux | Linux | Linux | |:----------------------:|:--------------------------------------------------------------------------------------------:|:------------------------------------------------:|:----------:|:-------:|:----------:|:-------:|:-------:|:-----------:|:---------------:|:-------------:|:-------------:|:-------:|:-------:|:-------:| | --- | --- | X86 CPU | NVIDIA GPU | X86 CPU | NVIDIA GPU | X86 CPU | Arm CPU | AArch64 CPU | 飞腾D2000 aarch64 | [NVIDIA Jetson](./docs/cn/build_and_install/jetson.md) | [Graphcore IPU](./docs/cn/build_and_install/ipu.md) | [昆仑芯 XPU](./docs/cn/build_and_install/kunlunxin.md) |[华为 昇腾](./docs/cn/build_and_install/huawei_ascend.md) | [Serving](./serving) | | Classification | [PaddleClas/ResNet50](./examples/vision/classification/paddleclas) | [✅](./examples/vision/classification/paddleclas) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |✅ | | Classification | [TorchVison/ResNet](examples/vision/classification/resnet) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ❔ | ✅ |✅ | ❔ | | Classification | [ultralytics/YOLOv5Cls](examples/vision/classification/yolov5cls) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ❔ | ✅ | ❔ |❔ | | Classification | [PaddleClas/PP-LCNet](./examples/vision/classification/paddleclas) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |✅ | ✅ | | Classification | [PaddleClas/PP-LCNetv2](./examples/vision/classification/paddleclas) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |✅ | ✅ | | Classification | [PaddleClas/EfficientNet](./examples/vision/classification/paddleclas) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |✅ | ✅ | | Classification | [PaddleClas/GhostNet](./examples/vision/classification/paddleclas) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |✅ | ✅ | | Classification | [PaddleClas/MobileNetV1](./examples/vision/classification/paddleclas) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |✅ | ✅ | | Classification | [PaddleClas/MobileNetV2](./examples/vision/classification/paddleclas) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |✅ | ✅ | | Classification | [PaddleClas/MobileNetV3](./examples/vision/classification/paddleclas) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |✅ | ✅ | | Classification | [PaddleClas/ShuffleNetV2](./examples/vision/classification/paddleclas) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |✅ | ✅ | | Classification | [PaddleClas/SqueeezeNetV1.1](./examples/vision/classification/paddleclas) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |✅ | ✅ | | Classification | [PaddleClas/Inceptionv3](./examples/vision/classification/paddleclas) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ❔ | ✅ |✅ | ✅ | | Classification | [PaddleClas/PP-HGNet](./examples/vision/classification/paddleclas) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |✅ | ✅ | | Detection | 🔥🔥[PaddleDetection/PP-YOLOE+](./examples/vision/detection/paddledetection) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ❔ | ✅ |✅ | ✅ | | Detection | [🔥PaddleDetection/YOLOv8](./examples/vision/detection/paddledetection) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ❔ | ✅ |✅ | ❔ | | Detection | [🔥ultralytics/YOLOv8](./examples/vision/detection/yolov8) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ❔ | ✅ | ❔ | ❔ |❔ | ❔ | | Detection | [PaddleDetection/PicoDet](./examples/vision/detection/paddledetection) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ❔ | ✅ | ❔ | ✅ | | Detection | [PaddleDetection/YOLOX](./examples/vision/detection/paddledetection) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ❔ | ✅ | ✅ | ✅ | | Detection | [PaddleDetection/YOLOv3](./examples/vision/detection/paddledetection) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ❔ | ✅ | ✅ | ✅ | | Detection | [PaddleDetection/PP-YOLO](./examples/vision/detection/paddledetection) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ❔ | ✅ | ✅ | ✅ | | Detection | [PaddleDetection/PP-YOLOv2](./examples/vision/detection/paddledetection) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ❔ | ✅ | ✅ | ✅ | | Detection | [PaddleDetection/Faster-RCNN](./examples/vision/detection/paddledetection) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ❔ | ✅ |❔ | ✅ | | Detection | [PaddleDetection/Mask-RCNN](./examples/vision/detection/paddledetection) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ❔ | ✅ |❔ | ✅ | | Detection | [Megvii-BaseDetection/YOLOX](./examples/vision/detection/yolox) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ❔ | ✅ |✅ | ❔ | | Detection | [WongKinYiu/YOLOv7](./examples/vision/detection/yolov7) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ❔ | ✅ |✅ | ❔ | | Detection | [WongKinYiu/YOLOv7end2end_trt](./examples/vision/detection/yolov7end2end_trt) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ❔ | ✅ | ❔ | ❔ |❔ | ❔ | | Detection | [WongKinYiu/YOLOv7end2end_ort](./examples/vision/detection/yolov7end2end_ort) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ❔ | ❔ |❔ | ❔ | | Detection | [meituan/YOLOv6](./examples/vision/detection/yolov6) | ✅ | ✅ | ✅ |✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ❔ | ✅ | ❔ | | Detection | [ultralytics/YOLOv5](./examples/vision/detection/yolov5) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ❔ | ✅ | ✅ |✅ | | Detection | [WongKinYiu/YOLOR](./examples/vision/detection/yolor) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ❔ | ✅ | ❔ | ❔ | ✅ | ❔ | | Detection | [WongKinYiu/ScaledYOLOv4](./examples/vision/detection/scaledyolov4) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ❔ | ❔ |❔ | ❔ | | Detection | [ppogg/YOLOv5Lite](./examples/vision/detection/yolov5lite) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ? | ❔ |❔ |❔ | | Detection | [RangiLyu/NanoDetPlus](./examples/vision/detection/nanodet_plus) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ❔ | ❔ |❔ | ❔ | | Perception | [Paddle3D/Smoke](./examples/vision/perception/paddle3d/smoke) | ❔ | ✅ | ❔ | ✅ | ❔ | ❔ | ❔ | ❔ | ❔ | ❔ | ❔ |❔ | ✅ | | KeyPoint | [PaddleDetection/TinyPose](./examples/vision/keypointdetection/tiny_pose) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ❔ | ✅ |❔ | ❔ | | KeyPoint | [PaddleDetection/PicoDet + TinyPose](./examples/vision/keypointdetection/det_keypoint_unite) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ❔ | ✅ | ❔ |❔ | | HeadPose | [omasaht/headpose](examples/vision/headpose) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ❔ | ✅ | ❔ | ❔ | ❔ |❔ | | Tracking | [PaddleDetection/PP-Tracking](examples/vision/tracking/pptracking) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ❔ | ❔ | ❔ |❔ | | OCR | [PaddleOCR/PP-OCRv2](./examples/vision/ocr) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ❔ | ✅ | ❔ | ✅ |✅ | ❔ | | OCR | [PaddleOCR/PP-OCRv3](./examples/vision/ocr) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ❔ | ✅ |✅ | ✅ | | Segmentation | [PaddleSeg/PP-LiteSeg](./examples/vision/segmentation/paddleseg) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ❔ | ✅ | ❔ | ✅ |❔ | ❔ | | Segmentation | [PaddleSeg/PP-HumanSegLite](./examples/vision/segmentation/paddleseg) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ❔ | ✅ | ❔ | ✅ |✅ | ❔ | | Segmentation | [PaddleSeg/HRNet](./examples/vision/segmentation/paddleseg) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ❔ | ✅ | ❔ | ✅ | ✅ |❔ | | Segmentation | [PaddleSeg/PP-HumanSegServer](./examples/vision/segmentation/paddleseg) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ❔ | ✅ | ❔ | ✅ | ✅ |❔ | | Segmentation | [PaddleSeg/Unet](./examples/vision/segmentation/paddleseg) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ❔ | ✅ | ✅ | ✅ | ✅ |❔ | | Segmentation | [PaddleSeg/Deeplabv3](./examples/vision/segmentation/paddleseg) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ❔ | ✅ | ❔ | ✅ | ✅ |❔ | | FaceDetection | [biubug6/RetinaFace](./examples/vision/facedet/retinaface) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ❔ | ❔ | ❔ | ❔ | | FaceDetection | [Linzaer/UltraFace](./examples/vision/facedet/ultraface) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ❔ | ❔ | ❔ |❔ | | FaceDetection | [deepcam-cn/YOLOv5Face](./examples/vision/facedet/yolov5face) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ❔ | ❔ | ❔ |❔ | | FaceDetection | [insightface/SCRFD](./examples/vision/facedet/scrfd) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ❔ | ❔ | ❔ |❔ | | FaceAlign | [Hsintao/PFLD](examples/vision/facealign/pfld) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ❔ | ❔ | ❔ |❔ | | FaceAlign | [Single430/FaceLandmark1000](./examples/vision/facealign/face_landmark_1000) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ❔ | ✅ | ❔ | ❔ | ❔ | ❔ | | FaceAlign | [jhb86253817/PIPNet](./examples/vision/facealign) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ❔ | ✅ | ❔ | ❔ | ❔ |❔ | | FaceRecognition | [insightface/ArcFace](./examples/vision/faceid/insightface) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ❔ | ❔ | ❔ |❔ | | FaceRecognition | [insightface/CosFace](./examples/vision/faceid/insightface) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ❔ | ❔ | ❔ |❔ | | FaceRecognition | [insightface/PartialFC](./examples/vision/faceid/insightface) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ❔ | ❔ | ❔ | ❔ | | FaceRecognition | [insightface/VPL](./examples/vision/faceid/insightface) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ❔ | ❔ | ❔ | ❔ | | Matting | [ZHKKKe/MODNet](./examples/vision/matting/modnet) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ❔ | ✅ | ❔ | ❔ | ❔ |❔ | | Matting | [PeterL1n/RobustVideoMatting]() | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ❔ | ✅ | ❔ | ❔ | ❔ | ❔ | | Matting | [PaddleSeg/PP-Matting](./examples/vision/matting/ppmatting) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ❔ | ✅ |✅ | ❔ | | Matting | [PaddleSeg/PP-HumanMatting](./examples/vision/matting/modnet) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ❔ | ✅ |✅ |❔ | | Matting | [PaddleSeg/ModNet](./examples/vision/matting/modnet) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ❔ | ❔ |❔ | ❔ | | Video Super-Resolution | [PaddleGAN/BasicVSR](./) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ❔ | ✅ | ❔ | ❔ | ❔ |❔ | | Video Super-Resolution | [PaddleGAN/EDVR](./examples/vision/sr/edvr) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ❔ | ✅ | ❔ | ❔ |❔ | ❔ | | Video Super-Resolution | [PaddleGAN/PP-MSVSR](./examples/vision/sr/ppmsvsr) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ❔ | ✅ | ❔ | ❔ |❔ | ❔ | | Information Extraction | [PaddleNLP/UIE](./examples/text/uie) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ❔ | ✅ | ❔ | ❔ |❔ | | | NLP | [PaddleNLP/ERNIE-3.0](./examples/text/ernie-3.0) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ❔ | ❔ | ❔ | ✅ |❔ | ✅ | | Speech | [PaddleSpeech/PP-TTS](./examples/audio/pp-tts) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ❔ | ❔ | -- |❔ |❔ | ✅ |
## 📳 移动端和端侧 模型支持列表
端侧模型支持列表（点击可收缩）
| 任务场景 | 模型 | 大小(MB) | Linux | Android | Linux | Linux | Linux | Linux | Linux | 更新中... | |:------------------:|:-----------------------------------------------------------------------------------------:|:--------:|:-------:|:-------:|:-------:|:-----------------------:|:------------------------------:|:---------------------------:|:--------------------------------:|:-------:| | --- | --- | --- | ARM CPU | [ARM CPU](./java/android) | [瑞芯微NPU
RK3588/RK3568/RK3566](./docs/cn/build_and_install/rknpu2.md) | [瑞芯微NPU
RV1109/RV1126/RK1808](./docs/cn/build_and_install/rv1126.md) | [晶晨NPU
A311D/S905D/C308X](./docs/cn/build_and_install/a311d.md) | 恩智浦NPU
i.MX 8M Plus | 更新中... | | Classification | [PaddleClas/ResNet50](examples/vision/classification/paddleclas) | 98 | ✅ | ✅ | [✅](./examples/vision/classification/paddleclas/rknpu2) | ✅ | | | | | Classification | [PaddleClas/PP-LCNet](examples/vision/classification/paddleclas) | 11.9 | ✅ | ✅ | ❔ | ✅ | -- | -- | -- | | Classification | [PaddleClas/PP-LCNetv2](examples/vision/classification/paddleclas) | 26.6 | ✅ | ✅ | ❔ | ✅ | -- | -- | -- | | Classification | [PaddleClas/EfficientNet](examples/vision/classification/paddleclas) | 31.4 | ✅ | ✅ | ❔ | ✅ | -- | -- | -- | | Classification | [PaddleClas/GhostNet](examples/vision/classification/paddleclas) | 20.8 | ✅ | ✅ | ❔ | ✅ | -- | -- | -- | | Classification | [PaddleClas/MobileNetV1](examples/vision/classification/paddleclas) | 17 | ✅ | ✅ | ❔ | ✅ | -- | -- | -- | | Classification | [PaddleClas/MobileNetV2](examples/vision/classification/paddleclas) | 14.2 | ✅ | ✅ | ❔ | ✅ | -- | -- | -- | | Classification | [PaddleClas/MobileNetV3](examples/vision/classification/paddleclas) | 22 | ✅ | ✅ | ❔ | ✅ | ❔ | ❔ | -- | | Classification | [PaddleClas/ShuffleNetV2](examples/vision/classification/paddleclas) | 9.2 | ✅ | ✅ | ❔ | ✅ | -- | -- | -- | | Classification | [PaddleClas/SqueezeNetV1.1](examples/vision/classification/paddleclas) | 5 | ✅ | ✅ | ❔ | ✅ | -- | -- | -- | | Classification | [PaddleClas/Inceptionv3](examples/vision/classification/paddleclas) | 95.5 | ✅ | ✅ | ❔ | ✅ | -- | -- | -- | | Classification | [PaddleClas/PP-HGNet](examples/vision/classification/paddleclas) | 59 | ✅ | ✅ | ❔ | ✅ | -- | -- | -- | | Detection | [PaddleDetection/PicoDet_s](examples/vision/detection/paddledetection) | 4.9 | ✅ | ✅ | [✅](./examples/vision/detection/paddledetection/rknpu2) | ✅ | ✅ | ✅ | -- | | Detection | [YOLOv5](./examples/vision/detection/rkyolo) | | ❔ | ❔ | [✅](./examples/vision/detection/rkyolo) | ❔ | ❔ | ❔ | -- | | Face Detection | [deepinsight/SCRFD](./examples/vision/facedet/scrfd) | 2.5 | ✅ | ✅ | [✅](./examples/vision/facedet/scrfd/rknpu2) | -- | -- | -- | -- | | Keypoint Detection | [PaddleDetection/PP-TinyPose](examples/vision/keypointdetection/tiny_pose) | 5.5 | ✅ | ✅ | ❔ | ❔ | ❔ | ❔ | -- | | Segmentation | [PaddleSeg/PP-LiteSeg(STDC1)](examples/vision/segmentation/paddleseg) | 32.2 | ✅ | ✅ | [✅](./examples/vision/segmentation/paddleseg/rknpu2) | -- | -- | -- | -- | | Segmentation | [PaddleSeg/PP-HumanSeg-Lite](examples/vision/segmentation/paddleseg) | 0.556 | ✅ | ✅ | [✅](./examples/vision/segmentation/paddleseg/rknpu2) | -- | -- | -- | -- | | Segmentation | [PaddleSeg/HRNet-w18](examples/vision/segmentation/paddleseg) | 38.7 | ✅ | ✅ | [✅](./examples/vision/segmentation/paddleseg/rknpu2) | -- | -- | -- | -- | | Segmentation | [PaddleSeg/PP-HumanSeg](examples/vision/segmentation/paddleseg) | 107.2 | ✅ | ✅ | [✅](./examples/vision/segmentation/paddleseg/rknpu2) | -- | -- | -- | -- | | Segmentation | [PaddleSeg/Unet](examples/vision/segmentation/paddleseg) | 53.7 | ✅ | ✅ | [✅](./examples/vision/segmentation/paddleseg/rknpu2) | -- | -- | -- | -- | | Segmentation | [PaddleSeg/Deeplabv3](examples/vision/segmentation/paddleseg) | 150 | ❔ | ✅ | [✅](./examples/vision/segmentation/paddleseg/rknpu2) | | | | | | OCR | [PaddleOCR/PP-OCRv2](examples/vision/ocr/PP-OCRv2) | 2.3+4.4 | ✅ | ✅ | ❔ | -- | -- | -- | -- | | OCR | [PaddleOCR/PP-OCRv3](examples/vision/ocr/PP-OCRv3) | 2.4+10.6 | ✅ | ❔ | ❔ | ❔ | ❔ | ❔ | -- |
## ⚛️ Web和小程序 模型支持列表
Web和小程序部署支持列表（点击可收缩）
| 任务场景 | 模型 | [web_demo](examples/application/js/web_demo) | |:------------------:|:-------------------------------------------------------------------------------------------:|:--------------------------------------------:| | --- | --- | [Paddle.js](examples/application/js) | | Detection | [FaceDetection](examples/application/js/web_demo/src/pages/cv/detection) | ✅ | | Detection | [ScrewDetection](examples/application/js/web_demo/src/pages/cv/detection) | ✅ | | Segmentation | [PaddleSeg/HumanSeg](./examples/application/js/web_demo/src/pages/cv/segmentation/HumanSeg) | ✅ | | Object Recognition | [GestureRecognition](examples/application/js/web_demo/src/pages/cv/recognition) | ✅ | | Object Recognition | [ItemIdentification](examples/application/js/web_demo/src/pages/cv/recognition) | ✅ | | OCR | [PaddleOCR/PP-OCRv3](./examples/application/js/web_demo/src/pages/cv/ocr) | ✅ |
## 💐 Acknowledge 本项目中SDK生成和下载使用了[EasyEdge](https://ai.baidu.com/easyedge/app/openSource)中的免费开放能力，在此表示感谢。 ## ©️ License
FastDeploy遵循[Apache-2.0开源协议](./LICENSE)。