diff --git a/README.md b/README.md index 5619db16009..8046fe0cba9 100644 --- a/README.md +++ b/README.md @@ -1,9 +1,7 @@ -# ⚡️FastDeploy +![⚡️FastDeploy](docs/logo/fastdeploy-opaque.png)

------------------------------------------------------------------------------------------- -

@@ -19,147 +17,196 @@ **⚡️FastDeploy**是一款**简单易用**的推理部署工具箱。覆盖业界主流**优质预训练模型**并提供**开箱即用**的开发体验，包括图像分类、目标检测、图像分割、人脸检测、人体关键点识别、文字识别等多任务，满足开发者**多场景**，**多硬件**、**多平台**的快速部署需求。 ## 发版历史 -- [v0.2.0] 2022.08.18 全面开源服务端部署代码，支持40+视觉模型在CPU/GPU，以及通过GPU TensorRT加速部署 - -## 服务端模型 - -| 任务场景 | 模型 | CPU | NVIDIA GPU | TensorRT | -| -------- | ------------------------------------------------------------ | ------- | ---------- | ------------------- | -| 图像分类 | [PaddleClas/ResNet50](./examples/vision/classification/paddleclas) | √ | √ | √ | -| | [PaddleClas/PPLCNet](./examples/vision/classification/paddleclas) | √ | √ | √ | -| | [PaddleClas/EfficientNet](./examples/vision/classification/paddleclas) | √ | √ | √ | -| | [PaddleClas/GhostNet](./examples/vision/classification/paddleclas) | √ | √ | √ | -| | [PaddleClas/MobileNetV1](./examples/vision/classification/paddleclas) | √ | √ | √ | -| | [PaddleClas/MobileNetV2](./examples/vision/classification/paddleclas) | √ | √ | √ | -| | [PaddleClas/ShuffleNetV2](./examples/vision/classification/paddleclas) | √ | √ | √ | -| 目标检测 | [PaddleDetection/PPYOLOE](./examples/vision/detection/paddledetection) | √ | √ | √ | -| | [PaddleDetection/PicoDet](./examples/vision/detection/paddledetection) | √ | √ | √ | -| | [PaddleDetection/YOLOX](./examples/vision/detection/paddledetection) | √ | √ | √ | -| | [PaddleDetection/YOLOv3](./examples/vision/detection/paddledetection) | √ | √ | √ | -| | [PaddleDetection/PPYOLO](./examples/vision/detection/paddledetection) | √ | √ | - | -| | [PaddleDetection/PPYOLOv2](./examples/vision/detection/paddledetection) | √ | √ | - | -| | [PaddleDetection/FasterRCNN](./examples/vision/detection/paddledetection) | √ | √ | - | -| | [WongKinYiu/YOLOv7](./examples/vision/detection/yolov7) | √ | √ | √ | - -## 快速开始 - -#### 安装FastDeploy Python - -用户根据开发环境选择安装版本，更多安装环境参考[安装文档](docs/quick_start/install.md). - -``` +- [v0.2.0] 2022.08.18 全面开源服务端部署代码，支持40+视觉模型在CPU/GPU，以及通过TensorRT加速部署 + +## 内容目录 +* [服务端模型列表](#fastdeploy-server-models) +* [服务端快速开始](#fastdeploy-quick-start) + * [快速安装](#fastdeploy-quick-start) + * [Python预测示例](#fastdeploy-quick-start-python) + * [C++预测示例](#fastdeploy-quick-start-cpp) +* [轻量化SDK快速实现端侧AI推理部署](#fastdeploy-edge-sdk) + * [边缘侧部署](#fastdeploy-edge-sdk-arm-linux) + * [移动端部署](#fastdeploy-edge-sdk-ios-android) + * [自定义模型部署](#fastdeploy-edge-sdk-custom) +* [社区交流](#fastdeploy-community) +* [Acknowledge](#fastdeploy-acknowledge) +* [License](#fastdeploy-license) +## 1. 服务端模型列表 🔥🔥🔥 + +

+ +符号说明: (1) ✅: 已经支持; (2) ❔: 计划未来支持; (3) ❌: 暂不支持; (4) contrib: 外部模型 +| 任务场景 | 模型 | API | Linux | Linux | Windows | Windows | MacOS | MacOS | Linux | +| :--------: | :--------: | :--------: | :--------: | :--------: | :--------: | :--------: | :--------: | :--------: | :--------: | +| --- | --- | --- | X86 CPU | NVIDIA GPU | Intel CPU | NVIDIA GPU | Intel CPU | Arm CPU | NVIDIA Jetson | +| Classification | [PaddleClas/ResNet50](./examples/vision/classification/paddleclas) | [Python](./examples/vision/classification/paddleclas/python)/[C++](./examples/vision/classification/paddleclas/cpp) | ✅ | ✅ | ✅ | ✅ | ✅ | ❔ | ❔ | +| Classification | [PaddleClas/PPLCNet](./examples/vision/classification/paddleclas) | [Python](./examples/vision/classification/paddleclas/python)/[C++](./examples/vision/classification/paddleclas/cpp) | ✅ | ✅ | ✅ | ✅ | ✅ | ❔ | ❔ | +| Classification | [PaddleClas/PPLCNetv2](./examples/vision/classification/paddleclas) | [Python](./examples/vision/classification/paddleclas/python)/[C++](./examples/vision/classification/paddleclas/cpp) | ✅ | ✅ | ✅ | ✅ | ✅ | ❔ | ❔ | +| Classification | [PaddleClas/EfficientNet](./examples/vision/classification/paddleclas) | [Python](./examples/vision/classification/paddleclas/python)/[C++](./examples/vision/classification/paddleclas/cpp) | ✅ | ✅ | ✅ | ✅ | ✅ | ❔ | ❔ | +| Classification | [PaddleClas/GhostNet](./examples/vision/classification/paddleclas) | [Python](./examples/vision/classification/paddleclas/python)/[C++](./examples/vision/classification/paddleclas/cpp) | ✅ | ✅ | ✅ | ✅ | ✅ | ❔ | ❔ | +| Classification | [PaddleClas/MobileNetV1](./examples/vision/classification/paddleclas) | [Python](./examples/vision/classification/paddleclas/python)/[C++](./examples/vision/classification/paddleclas/cpp) | ✅ | ✅ | ✅ | ✅ | ✅ | ❔ | ❔ | +| Classification | [PaddleClas/MobileNetV2](./examples/vision/classification/paddleclas) | [Python](./examples/vision/classification/paddleclas/python)/[C++](./examples/vision/classification/paddleclas/cpp) | ✅ | ✅ | ✅ | ✅ | ✅ | ❔ | ❔ | +| Classification | [PaddleClas/MobileNetV3](./examples/vision/classification/paddleclas) | [Python](./examples/vision/classification/paddleclas/python)/[C++](./examples/vision/classification/paddleclas/cpp) | ✅ | ✅ | ✅ | ✅ | ✅ | ❔ | ❔ | +| Classification | [PaddleClas/ShuffleNetV2](./examples/vision/classification/paddleclas) | [Python](./examples/vision/classification/paddleclas/python)/[C++](./examples/vision/classification/paddleclas/cpp) | ✅ | ✅ | ✅ | ✅ | ✅ | ❔ | ❔ | +| Classification | [PaddleClas/SqueeezeNetV1.1](./examples/vision/classification/paddleclas) | [Python](./examples/vision/classification/paddleclas/python)/[C++](./examples/vision/classification/paddleclas/cpp) | ✅ | ✅ | ✅ | ✅ | ✅ | ❔ | ❔ | +| Classification | [PaddleClas/Inceptionv3](./examples/vision/classification/paddleclas) | [Python](./examples/vision/classification/paddleclas/python)/[C++](./examples/vision/classification/paddleclas/cpp) | ✅ | ✅ | ✅ | ✅ | ✅ | ❔ | ❔ | +| Classification | [PaddleClas/PPHGNet](./examples/vision/classification/paddleclas) | [Python](./examples/vision/classification/paddleclas/python)/[C++](./examples/vision/classification/paddleclas/cpp) | ✅ | ✅ | ✅ | ✅ | ✅ | ❔ | ❔ | +| Classification | [PaddleClas/SwinTransformer](./examples/vision/classification/paddleclas) | [Python](./examples/vision/classification/paddleclas/python)/[C++](./examples/vision/classification/paddleclas/cpp) | ✅ | ✅ | ✅ | ✅ | ✅ | ❔ | ❔ | +| Detection | [PaddleDetection/PPYOLOE](./examples/vision/detection/paddledetection) | [Python](./examples/vision/detection/paddledetection/python)/[C++](./examples/vision/detection/paddledetection/cpp) | ✅ | ✅ | ✅ | ✅ | ✅ | ❔ | ❔ | +| Detection | [PaddleDetection/PicoDet](./examples/vision/detection/paddledetection) | [Python](./examples/vision/detection/paddledetection/python)/[C++](./examples/vision/detection/paddledetection/cpp) | ✅ | ✅ | ✅ | ✅ | ✅ | ❔ | ❔ | +| Detection | [PaddleDetection/YOLOX](./examples/vision/detection/paddledetection) | [Python](./examples/vision/detection/paddledetection/python)/[C++](./examples/vision/detection/paddledetection/cpp) | ✅ | ✅ | ✅ | ✅ | ✅ | ❔ | ❔ | +| Detection | [PaddleDetection/YOLOv3](./examples/vision/detection/paddledetection) | [Python](./examples/vision/detection/paddledetection/python)/[C++](./examples/vision/detection/paddledetection/cpp) | ✅ | ✅ | ✅ | ✅ | ✅ | ❔ | ❔ | +| Detection | [PaddleDetection/PPYOLO](./examples/vision/detection/paddledetection) | [Python](./examples/vision/detection/paddledetection/python)/[C++](./examples/vision/detection/paddledetection/cpp) | ✅ | ✅ | ✅ | ✅ | ✅ | ❔ | ❔ | +| Detection | [PaddleDetection/PPYOLOv2](./examples/vision/detection/paddledetection) | [Python](./examples/vision/detection/paddledetection/python)/[C++](./examples/vision/detection/paddledetection/cpp) | ✅ | ✅ | ✅ | ✅ | ✅ | ❔ | ❔ | +| Detection | [PaddleDetection/FasterRCNN](./examples/vision/detection/paddledetection) | [Python](./examples/vision/detection/paddledetection/python)/[C++](./examples/vision/detection/paddledetection/cpp) | ✅ | ✅ | ✅ | ✅ | ✅ | ❔ | ❔ | +| Detection | [Contrib/YOLOX](./examples/vision/detection/yolox) | [Python](./examples/vision/detection/yolox/python)/[C++](./examples/vision/detection/yolox/cpp) | ✅ | ✅ | ✅ | ✅ | ✅ | ❔ | ❔ | +| Detection | [Contrib/YOLOv7](./examples/vision/detection/yolov7) | [Python](./examples/vision/detection/yolov7/python)/[C++](./examples/vision/detection/yolov7/cpp) | ✅ | ✅ | ✅ | ✅ | ✅ | ❔ | ❔ | +| Detection | [Contrib/YOLOv6](./examples/vision/detection/yolov6) | [Python](./examples/vision/detection/yolov6/python)/[C++](./examples/vision/detection/yolov6/cpp) | ✅ | ✅ | ✅ | ✅ | ✅ | ❔ | ❔ | +| Detection | [Contrib/YOLOv5](./examples/vision/detection/yolov5) | [Python](./examples/vision/detection/yolov5/python)/[C++](./examples/vision/detection/yolov5/cpp) | ✅ | ✅ | ✅ | ✅ | ✅ | ❔ | ❔ | +| Detection | [Contrib/YOLOR](./examples/vision/detection/yolor) | [Python](./examples/vision/detection/yolor/python)/[C++](./examples/vision/detection/yolor/cpp) | ✅ | ✅ | ✅ | ✅ | ✅ | ❔ | ❔ | +| Detection | [Contrib/ScaledYOLOv4](./examples/vision/detection/scaledyolov4) | [Python](./examples/vision/detection/scaledyolov4/python)/[C++](./examples/vision/detection/scaledyolov4/cpp) | ✅ | ✅ | ✅ | ✅ | ✅ | ❔ | ❔ | +| Detection | [Contrib/YOLOv5Lite](./examples/vision/detection/yolov5lite) | [Python](./examples/vision/detection/yolov5lite/python)/[C++](./examples/vision/detection/yolov5lite/cpp) | ✅ | ✅ | ✅ | ✅ | ✅ | ❔ | ❔ | +| Detection | [Contrib/NanoDetPlus](./examples/vision/detection/nanodet_plus) | [Python](./examples/vision/detection/nanodet_plus/python)/[C++](./examples/vision/detection/nanodet_plus/cpp) | ✅ | ✅ | ✅ | ✅ | ✅ | ❔ | ❔ | +| Segmentation | [PaddleSeg/PPLiteSeg](./examples/vision/segmentation/paddleseg) | [Python](./examples/vision/segmentation/paddleseg/python)/[C++](./examples/vision/segmentation/paddleseg/cpp) | ✅ | ✅ | ✅ | ✅ | ✅ | ❔ | ❔ | +| Segmentation | [PaddleSeg/PPHumanSegLite](./examples/vision/segmentation/paddleseg) | [Python](./examples/vision/segmentation/paddleseg/python)/[C++](./examples/vision/segmentation/paddleseg/cpp) | ✅ | ✅ | ✅ | ✅ | ✅ | ❔ | ❔ | +| Segmentation | [PaddleSeg/HRNet](./examples/vision/segmentation/paddleseg) | [Python](./examples/vision/segmentation/paddleseg/python)/[C++](./examples/vision/segmentation/paddleseg/cpp) | ✅ | ✅ | ✅ | ✅ | ✅ | ❔ | ❔ | +| Segmentation | [PaddleSeg/PPHumanSegServer](./examples/vision/segmentation/paddleseg) | [Python](./examples/vision/segmentation/paddleseg/python)/[C++](./examples/vision/segmentation/paddleseg/cpp) | ✅ | ✅ | ✅ | ✅ | ✅ | ❔ | ❔ | +| Segmentation | [PaddleSeg/Unet](./examples/vision/segmentation/paddleseg) | [Python](./examples/vision/segmentation/paddleseg/python)/[C++](./examples/vision/segmentation/paddleseg/cpp) | ✅ | ✅ | ✅ | ✅ | ✅ | ❔ | ❔ | +| Segmentation | [PaddleSeg/Deeplabv3](./examples/vision/segmentation/paddleseg) | [Python](./examples/vision/segmentation/paddleseg/python)/[C++](./examples/vision/segmentation/paddleseg/cpp) | ✅ | ✅ | ✅ | ✅ | ✅ | ❔ | ❔ | +| FaceDetection | [Contrib/RetinaFace](./examples/vision/facedet/retinaface) | [Python](./examples/vision/facedet/retinaface/python)/[C++](./examples/vision/facedet/retinaface/cpp) | ✅ | ✅ | ✅ | ✅ | ✅ | ❔ | ❔ | +| FaceDetection | [Contrib/UltraFace](./examples/vision/facedet/utltraface) | [ Python](./examples/vision/facedet/utltraface/python)/[C++](./examples/vision/facedet/utltraface/cpp) | ✅ | ✅ | ✅ | ✅ | ✅ | ❔ | ❔ | +| FaceDetection | [Contrib/YOLOv5Face](./examples/vision/facedet/yolov5face) | [Python](./examples/vision/facedet/yolov5face/python)/[C++](./examples/vision/facedet/yolov5face/cpp) | ✅ | ✅ | ✅ | ✅ | ✅ | ❔ | ❔ | +| FaceDetection | [Contrib/SCRFD](./examples/vision/facedet/scrfd) | [Python](./examples/vision/facedet/scrfd/python)/[C++](./examples/vision/facedet/scrfd/cpp) | ✅ | ✅ | ✅ | ✅ | ✅ | ❔ | ❔ | +| FaceRecognition | [Contrib/ArcFace](./examples/vision/faceid/insightface) | [Python](./examples/vision/faceid/insightface/python)/[C++](./examples/vision/faceid/insightface/cpp) | ✅ | ✅ | ✅ | ✅ | ✅ | ❔ | ❔ | +| FaceRecognition | [Contrib/CosFace](./examples/vision/faceid/insightface) | [Python](./examples/vision/faceid/insightface/python)/[C++](./examples/vision/faceid/insightface/cpp) | ✅ | ✅ | ✅ | ✅ | ✅ | ❔ | ❔ | +| FaceRecognition | [Contrib/PartialFC](./examples/vision/faceid/insightface) | [Python](./examples/vision/faceid/insightface/python)/[C++](./examples/vision/faceid/insightface/cpp) | ✅ | ✅ | ✅ | ✅ | ✅ | ❔ | ❔ | +| FaceRecognition | [Contrib/VPL](./examples/vision/faceid/insightface) | [Python](./examples/vision/faceid/insightface/python)/[C++](./examples/vision/faceid/insightface/cpp) | ✅ | ✅ | ✅ | ✅ | ✅ | ❔ | ❔ | +| Matting | [Contrib/MODNet](./examples/vision/matting/modnet) | [Python](./examples/vision/matting/modnet/python)/[C++](./examples/vision/matting/modnet/cpp) | ✅ | ✅ | ✅ | ✅ | ✅ | ❔ | ❔ | + + +## 2. 服务端快速开始 +
+ +
+💡 快速安装 FastDeploy Python/C++ 库 + +用户根据自己的python版本选择安装对应的wheel包，详细的wheel目录请参考 [python安装文档](docs/compile/prebuilt_wheels.md) . + +```bash pip install https://bj.bcebos.com/paddlehub/fastdeploy/wheels/fastdeploy_python-0.2.0-cp38-cp38-manylinux1_x86_64.whl ``` - -准备目标检测模型和测试图片 +或获取C++预编译库，更多可用的预编译库请参考 [C++预编译库下载](docs/compile/prebuilt_libraries.md) +```bash +wget https://bj.bcebos.com/paddlehub/fastdeploy/cpp/fastdeploy-linux-x64-0.2.0.tgz ``` +准备目标检测模型和测试图片 +```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 ``` +
-加载模型预测 -``` -import fastdeploy.vision as vis -import cv2 +### 2.1 Python预测示例 +
-model = vis.detection.PPYOLOE("ppyoloe_crn_l_300e_coco/model.pdmodel", - "ppyoloe_crn_l_300e_coco/model.pdiparams", - "ppyoloe_crn_l_300e_coco/infer_cfg.yml") +```python +import cv2 +import fastdeploy.vision as vision +model = vision.detection.PPYOLOE("model.pdmodel", "model.pdiparams", "infer_cfg.yml") im = cv2.imread("000000014439.jpg") result = model.predict(im.copy()) print(result) -vis_im = fd.vision.vis_detection(im, result, score_threshold=0.5) +vis_im = vision.vis_detection(im, result, score_threshold=0.5) cv2.imwrite("vis_image.jpg", vis_im) ``` +### 2.2 C++预测示例 +
-预测完成，可视化结果保存至`vis_image.jpg`，同时输出检测结果如下 -``` -DetectionResult: [xmin, ymin, xmax, ymax, score, label_id] -415.047363,89.311523, 506.009613, 283.863129, 0.950423, 0 -163.665710,81.914894, 198.585342, 166.760880, 0.896433, 0 -581.788635,113.027596, 612.623474, 198.521713, 0.842597, 0 -267.217224,89.777321, 298.796051, 169.361496, 0.837951, 0 -104.465599,45.482410, 127.688835, 93.533875, 0.773348, 0 -... -``` - -## 更多服务端部署示例 +```C++ +#include "fastdeploy/vision.h" -FastDeploy提供了大量部署示例供开发者参考，支持模型在CPU、GPU以及TensorRT的部署 +int main(int argc, char* argv[]) { + namespace vision = fastdeploy::vision; + auto model = vision::detection::PPYOLOE("model.pdmodel", "model.pdiparams", "infer_cfg.yml"); + auto im = cv::imread("000000014439.jpg"); -- [PaddleDetection模型部署](examples/vision/detection/paddledetection) -- [PaddleClas模型部署](examples/vision/classification/paddleclas) -- [PaddleSeg模型部署](examples/vision/segmentation/paddleseg) -- [YOLOv7部署](examples/vision/detection/yolov7) -- [YOLOv6部署](examples/vision/detection/yolov6) -- [YOLOv5部署](examples/vision/detection/yolov5) -- [人脸检测模型部署](examples/vision/facedet) -- [更多视觉模型部署示例...](examples/vision) + vision::DetectionResult res; + model.Predict(&im, &res) -### 📱轻量化SDK快速实现端侧AI推理部署 + auto vis_im = vision::Visualize::VisDetection(im, res, 0.5); + cv::imwrite("vis_image.jpg", vis_im); +} +``` +更多部署案例请参考[视觉模型部署示例](examples/vision) . +## 3. 轻量化SDK快速实现端侧AI推理部署 📱 +
| 任务场景 | 模型 | 大小(MB) | 边缘端 | 移动端 | 移动端 | -| ------------------ | ---------------------------- | --------------------- | --------------------- | ---------------------- | --------------------- | -| ---- | --- | --- | Linux | Android | iOS | -| ----- | ---- | --- | ARM CPU | ARM CPU | ARM CPU | -| Classfication | PP-LCNet | 11.9 | ✅ | ✅ | ✅ | -| | PP-LCNetv2 | 26.6 | ✅ | ✅ | ✅ | -| | EfficientNet | 31.4 | ✅ | ✅ | ✅ | -| | GhostNet | 20.8 | ✅ | ✅ | ✅ | -| | MobileNetV1 | 17 | ✅ | ✅ | ✅ | -| | MobileNetV2 | 14.2 | ✅ | ✅ | ✅ | -| | MobileNetV3 | 22 | ✅ | ✅ | ✅ | -| | ShuffleNetV2 | 9.2 | ✅ | ✅ | ✅ | -| | SqueezeNetV1.1 | 5 | ✅ | ✅ | ✅ | -| | Inceptionv3 | 95.5 | ✅ | ✅ | ✅ | -| | PP-HGNet | 59 | ✅ | ✅ | ✅ | -| | SwinTransformer_224_win7 | 352.7 | ✅ | ✅ | ✅ | -| Detection | PP-PicoDet_s_320_coco | 4.1 | ✅ | ✅ | ✅ | -| | PP-PicoDet_s_320_lcnet | 4.9 | ✅ | ✅ | ✅ | -| | CenterNet | 4.8 | ✅ | ✅ | ✅ | -| | YOLOv3_MobileNetV3 | 94.6 | ✅ | ✅ | ✅ | -| | PP-YOLO_tiny_650e_coco | 4.4 | ✅ | ✅ | ✅ | -| | SSD_MobileNetV1_300_120e_voc | 23.3 | ✅ | ✅ | ✅ | -| | PP-YOLO_ResNet50vd | 188.5 | ✅ | ✅ | ✅ | -| | PP-YOLOv2_ResNet50vd | 218.7 | ✅ | ✅ | ✅ | -| | PP-YOLO_crn_l_300e_coco | 209.1 | ✅ | ✅ | ✅ | -| | YOLOv5s | 29.3 | ✅ | ✅ | ✅ | -| Face Detection | BlazeFace | 1.5 | ✅ | ✅ | ✅ | -| Face Localisation | RetinaFace | 1.7 | ✅ | ❌ | ❌ | -| Keypoint Detection | PP-TinyPose | 5.5 | ✅ | ✅ | ✅ | -| Segmentation | PP-LiteSeg(STDC1) | 32.2 | ✅ | ✅ | ✅ | -| | PP-HumanSeg-Lite | 0.556 | ✅ | ✅ | ✅ | -| | HRNet-w18 | 38.7 | ✅ | ✅ | ✅ | -| | PP-HumanSeg-Server | 107.2 | ✅ | ✅ | ✅ | -| | Unet | 53.7 | ❌ | ✅ | ❌ | -| OCR | PP-OCRv1 | 2.3+4.4 | ✅ | ✅ | ✅ | -| | PP-OCRv2 | 2.3+4.4 | ✅ | ✅ | ✅ | -| | PP-OCRv3 | 2.4+10.6 | ✅ | ✅ | ✅ | -| | PP-OCRv3-tiny | 2.4+10.7 | ✅ | ✅ | ✅ | - - -#### 边缘侧部署 - -- ARM Linux 系统 +| :--------: | :--------: | :--------: | :--------: | :--------: | :--------: | +| --- | --- | --- | Linux | Android | iOS | +| --- | --- | --- | ARM CPU | ARM CPU | ARM CPU | +| Classification | PP-LCNet | 11.9 | ✅ | ✅ | ✅ | +| Classification | PP-LCNetv2 | 26.6 | ✅ | ✅ | ✅ | +| Classification | EfficientNet | 31.4 | ✅ | ✅ | ✅ | +| Classification | GhostNet | 20.8 | ✅ | ✅ | ✅ | +| Classification | MobileNetV1 | 17 | ✅ | ✅ | ✅ | +| Classification | MobileNetV2 | 14.2 | ✅ | ✅ | ✅ | +| Classification | MobileNetV3 | 22 | ✅ | ✅ | ✅ | +| Classification | ShuffleNetV2 | 9.2 | ✅ | ✅ | ✅ | +| Classification | SqueezeNetV1.1 | 5 | ✅ | ✅ | ✅ | +| Classification | Inceptionv3 | 95.5 | ✅ | ✅ | ✅ | +| Classification | PP-HGNet | 59 | ✅ | ✅ | ✅ | +| Classification | SwinTransformer_224_win7 | 352.7 | ✅ | ✅ | ✅ | +| Detection | PP-PicoDet_s_320_coco | 4.1 | ✅ | ✅ | ✅ | +| Detection | PP-PicoDet_s_320_lcnet | 4.9 | ✅ | ✅ | ✅ | +| Detection | CenterNet | 4.8 | ✅ | ✅ | ✅ | +| Detection | YOLOv3_MobileNetV3 | 94.6 | ✅ | ✅ | ✅ | +| Detection | PP-YOLO_tiny_650e_coco | 4.4 | ✅ | ✅ | ✅ | +| Detection | SSD_MobileNetV1_300_120e_voc | 23.3 | ✅ | ✅ | ✅ | +| Detection | PP-YOLO_ResNet50vd | 188.5 | ✅ | ✅ | ✅ | +| Detection | PP-YOLOv2_ResNet50vd | 218.7 | ✅ | ✅ | ✅ | +| Detection | PP-YOLO_crn_l_300e_coco | 209.1 | ✅ | ✅ | ✅ | +| Detection | YOLOv5s | 29.3 | ✅ | ✅ | ✅ | +| FaceDetection | BlazeFace | 1.5 | ✅ | ✅ | ✅ | +| FaceDetection | RetinaFace | 1.7 | ✅ | ❌ | ❌ | +| KeypointsDetection | PP-TinyPose | 5.5 | ✅ | ✅ | ✅ | +| Segmentation | PP-LiteSeg(STDC1) | 32.2 | ✅ | ✅ | ✅ | +| Segmentation | PP-HumanSeg-Lite | 0.556 | ✅ | ✅ | ✅ | +| Segmentation | HRNet-w18 | 38.7 | ✅ | ✅ | ✅ | +| Segmentation | PP-HumanSeg-Server | 107.2 | ✅ | ✅ | ✅ | +| Segmentation | Unet | 53.7 | ❌ | ✅ | ❌ | +| OCR | PP-OCRv1 | 2.3+4.4 | ✅ | ✅ | ✅ | +| OCR | PP-OCRv2 | 2.3+4.4 | ✅ | ✅ | ✅ | +| OCR | PP-OCRv3 | 2.4+10.6 | ✅ | ✅ | ✅ | +| OCR | PP-OCRv3-tiny | 2.4+10.7 | ✅ | ✅ | ✅ | + +### 3.1 边缘侧部署 +
+ +- ARM Linux 系统 - [C++ Inference部署（含视频流）](./docs/ARM-Linux-CPP-SDK-Inference.md) - [C++ 服务化部署](./docs/ARM-Linux-CPP-SDK-Serving.md) - [Python Inference部署](./docs/ARM-Linux-Python-SDK-Inference.md) - [Python 服务化部署](./docs/ARM-Linux-Python-SDK-Serving.md) -#### 移动端部署 +### 3.2 移动端部署 +
- [iOS 系统部署](./docs/iOS-SDK.md) - [Android 系统部署](./docs/Android-SDK.md) -#### 自定义模型部署 +### 3.3 自定义模型部署 +
- [快速实现个性化模型替换](./docs/Replace-Model-With-Anther-One.md) -## 社区交流 +## 4. 社区交流 +
- **加入社区👬：** 微信扫描二维码后，填写问卷加入交流群，与开发者共同讨论推理部署痛点问题 @@ -167,11 +214,13 @@ FastDeploy提供了大量部署示例供开发者参考，支持模型在CPU、G -## Acknowledge +## 5. 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，再次表示感谢。 -## License +## 6. License +
FastDeploy遵循[Apache-2.0开源协议](./LICENSE)。 diff --git a/docs/api/vision_results/face_detection_result.md b/docs/api/vision_results/face_detection_result.md index 2e1a13143d8..30029a7f0fa 100644 --- a/docs/api/vision_results/face_detection_result.md +++ b/docs/api/vision_results/face_detection_result.md @@ -32,3 +32,4 @@ struct FaceDetectionResult { - **scores**(list of float): 成员变量，表示单张图片检测出来的所有目标置信度 - **landmarks**(list of list(float)): 成员变量，表示单张图片检测出来的所有人脸的关键点 - **landmarks_per_face**(int): 成员变量，表示每个人脸框中的关键点的数量。 + diff --git a/docs/compile/prebuilt_libraries.md b/docs/compile/prebuilt_libraries.md index bd58fc4b0b8..905eb6d5295 100644 --- a/docs/compile/prebuilt_libraries.md +++ b/docs/compile/prebuilt_libraries.md @@ -1,4 +1,4 @@ -# FastDeploy 预编编译Python Wheel包 +# FastDeploy 预编译 C++ 库 FastDeploy提供了在Windows/Linux/Mac上的预先编译CPP部署库，开发者可以直接下载后使用，也可以自行编译代码。 diff --git a/docs/logo/fastdeploy-opaque.png b/docs/logo/fastdeploy-opaque.png new file mode 100644 index 00000000000..16289dcf555 Binary files /dev/null and b/docs/logo/fastdeploy-opaque.png differ