# FastDeploy **Repository Path**: yongfudata/FastDeploy ## Basic Information - **Project Name**: FastDeploy - **Description**: โšก๏ธAn Easy-to-use and Fast Deep Learning Model Deployment Toolkit for โ˜๏ธCloud ๐Ÿ“ฑMobile and ๐Ÿ“นEdge. Including Image, Video, Text and Audio 20+ main stream scenarios and 150+ SOTA models. - **Primary Language**: Python - **License**: Apache-2.0 - **Default Branch**: develop - **Homepage**: https://www.paddlepaddle.org.cn/fastdeploy - **GVP Project**: No ## Statistics - **Stars**: 0 - **Forks**: 37 - **Created**: 2023-09-16 - **Last Updated**: 2023-09-16 ## Categories & Tags **Categories**: Uncategorized **Tags**: None ## README English | [็ฎ€ไฝ“ไธญๆ–‡](README_CN.md) | [เคนเคฟเคจเฅเคฆเฅ€](./docs/docs_i18n/README_เคนเคฟเคจเฅเคฆเฅ€.md) | [ๆ—ฅๆœฌ่ชž](./docs/docs_i18n/README_ๆ—ฅๆœฌ่ชž.md) | [ํ•œ๊ตญ์ธ](./docs/docs_i18n/README_ํ•œ๊ตญ์ธ.md) | [Pัƒฬััะบะธะน ัะทั‹ฬะบ](./docs/docs_i18n/README_Pัƒฬััะบะธะน_ัะทั‹ฬะบ.md) ![โšก๏ธFastDeploy](https://user-images.githubusercontent.com/31974251/185771818-5d4423cd-c94c-4a49-9894-bc7a8d1c29d0.png)

Installation | Documents | Quick Start | API Docs | Release Notes

[](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)
**โšก๏ธFastDeploy** is an **Easy-to-use** and **High Performance** AI model deployment toolkit for Cloud, Mobile and Edge with ๐Ÿ“ฆ**out-of-the-box and unified experience**, ๐Ÿ”š**end-to-end optimization** for over **๐Ÿ”ฅ160+ Text, Vision, Speech and Cross-modal AI models**. Including [image classification](examples/vision/classification), [object detection](examples/vision/detection), [OCR](./examples/vision/ocr), [face detection](./examples/vision/facedet), [matting](./examples/vision/matting), [pp-tracking](./examples/vision/tracking/pptracking), [NLP](./examples/text), [stable diffusion](./examples/multimodal/stable_diffusion), [TTS](./examples/audio/pp-tts) and other tasks to meet developers' industrial deployment needs for **multi-scenario**, **multi-hardware** and **multi-platform**.
## ๐ŸŒ  Recent updates - โœจโœจโœจ In **2023.01.17** we released [**YOLOv8**](./examples/vision/detection/paddledetection/) for deployment on FastDeploy series hardware, which includes [**Paddle YOLOv8**](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/yolov8) and [**ultralytics YOLOv8**](https://github.com/ultralytics/ultralytics) - You can deploy [**Paddle YOLOv8**](https://github.com/PaddlePaddle/PaddleYOLO/tree/release/2.5/configs/yolov8) on [**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), [**Phytium**](./examples/vision/detection/paddledetection/python/infer_yolov8.py), [**Kunlunxin**](./examples/vision/detection/paddledetection/python/infer_yolov8.py), [**HUAWEI Ascend**](./examples/vision/detection/paddledetection/python/infer_yolov8.py) ,[**ARM CPU**](./examples/vision/detection/paddledetection/cpp/infer_yolov8.cc) [**RK3588**](./examples/vision/detection/paddledetection/rknpu2) and [**Sophgo TPU**](./examples/vision/detection/paddledetection/sophgo). Both **Python** deployments and **C++** deployments are included. - You can deploy [**ultralytics YOLOv8**](https://github.com/ultralytics/ultralytics) on [**Intel CPU**](./examples/vision/detection/yolov8), [**NVIDIA GPU**](./examples/vision/detection/yolov8), [**Jetson**](./examples/vision/detection/yolov8). Both **Python** deployments and **C++** deployments are included - Fastdeploy supports quick deployment of multiple models, including **YOLOv8**, **PP-YOLOE+**, **YOLOv5** and other models - Serving deployment combined with VisualDL supports visual deployment. After the VDL service is started in the FastDeploy container, you can modify the model configuration, start/manage the model service, view performance data, and send requests on the VDL interface. For details, see related documents - [Serving deployment visualization](https://github.com/PaddlePaddle/FastDeploy/blob/develop/serving/docs/EN/vdl_management-en.md) - [Serving request visualization](https://github.com/PaddlePaddle/FastDeploy/blob/develop/serving/docs/EN/client-en.md#use-visualdl-as-fastdeploy-client-for-request-visualization) - **โœจ๐Ÿ‘ฅโœจ Community** - **Slack**๏ผšJoin our [Slack community](https://join.slack.com/t/fastdeployworkspace/shared_invite/zt-1m88mytoi-mBdMYcnTF~9LCKSOKXd6Tg) and chat with other community members about ideas - **Wechat**๏ผšScan the QR code below using WeChat, follow the PaddlePaddle official account and fill out the questionnaire to join the WeChat group, and share the deployment industry implementation pain points with the community developers
## ๐ŸŒŒ Inference Backend and Abilities | | | || | | | | |:----------|:----------:|:----------:|:----------:|:----------:|:----------:|:----------:|:----------:| | X86_64 CPU | |       | |

|

| |

| | NVDIA GPU | | |
|

|

| | | |Phytium CPU | | | |
| | | | | KunlunXin XPU | | | | | | | | | Huawei Ascend NPU | | |
| | | | | |Graphcore IPU | | | | | | | | | Sophgo | | | | | | | | |Intel graphics card | | | | | | | | | Jetson | | |
|

|

| | | |ARM CPU | | |
|
| | | | |RK3588 etc. | | | | | | | | |RV1126 etc. | | | | | | | | | Amlogic | | | | | | | | | NXP | | | | | | | | ## ๐Ÿ”ฎ Contents - [โœด๏ธ A Quick Start for Python SDK](#fastdeploy-quick-start-python) - [โœด๏ธ A Quick Start for C++ SDK](#fastdeploy-quick-start-cpp) - **Installation** - [How to Install Prebuilt Library](docs/en/build_and_install/download_prebuilt_libraries.md) - [How to Build GPU Deployment Environment](docs/en/build_and_install/gpu.md) - [How to Build CPU Deployment Environment](docs/en/build_and_install/cpu.md) - [How to Build IPU Deployment Environment](docs/en/build_and_install/ipu.md) - [How to Build KunlunXin XPU Deployment Environment](docs/en/build_and_install/kunlunxin.md) - [How to Build RV1126 Deployment Environment](docs/en/build_and_install/rv1126.md) - [How to Build RKNPU2 Deployment Environment](docs/en/build_and_install/rknpu2.md) - [How to Build A311D Deployment Environment](docs/en/build_and_install/a311d.md) - [How to build Huawei Ascend Deployment Environment](docs/en/build_and_install/huawei_ascend.md) - [How to Build FastDeploy Library on Nvidia Jetson Platform](docs/en/build_and_install/jetson.md) - [How to Build FastDeploy Android C++ SDK](docs/en/build_and_install/android.md) - **Quick Start** - [PP-YOLOE Python Deployment Example](docs/en/quick_start/models/python.md) - [PP-YOLOE C++ Deployment Example](docs/en/quick_start/models/cpp.md) - **Demos on Different Backends** - [Runtime Python Inference](docs/en/quick_start/runtime/python.md) - [Runtime C++ Inference](docs/en/quick_start/runtime/cpp.md) - [How to Change Model Inference Backend](docs/en/faq/how_to_change_backend.md) - **Serving Deployment** - [FastDeploy Serving Deployment Image Compilation](serving/docs/EN/compile-en.md) - [Serving Deployment](serving) - **API Documents** - [Python API](https://www.paddlepaddle.org.cn/fastdeploy-api-doc/python/html/) - [C++ API](https://www.paddlepaddle.org.cn/fastdeploy-api-doc/cpp/html/) - [Android Java API](java/android) - **Performance Tune-up** - [Quantization Acceleration](docs/en/quantize.md) - [Multi thread](/tutorials/multi_thread) - **FAQ** - [1. Using the FastDeploy C++ SDK on Windows Platform](docs/en/faq/use_sdk_on_windows.md) - [2. FastDeploy to deploy on Android Platform](docs/en/faq/use_cpp_sdk_on_android.md) - [3. TensorRT Q&As](docs/en/faq/tensorrt_tricks.md) - **More FastDeploy Deploy Modules** - [Benchmark Testing](benchmark) - **Model list** - [๐Ÿ–ฅ๏ธ Supported Server-side and Cloud Model List](#fastdeploy-server-models) - [๐Ÿ“ณ Supported Mobile and Edge Model List](#fastdeploy-edge-models) - [โš›๏ธ Supported Web and Mini Program Model List](#fastdeploy-web-models) - **๐Ÿ’• Developer Contributions** - [Develop a new model](docs/en/faq/develop_a_new_model.md) ## Quick Start๐Ÿ’จ
A Quick Start for Python SDK(click to fold)
#### ๐ŸŽ† Installation ##### ๐Ÿ”ธ Prerequisites - CUDA >= 11.2 ใ€cuDNN >= 8.0 ใ€ Python >= 3.6 - OS: Linux x86_64/macOS/Windows 10 ##### ๐Ÿ”ธ Install FastDeploy SDK with both CPU and GPU support ```bash pip install fastdeploy-gpu-python -f https://www.paddlepaddle.org.cn/whl/fastdeploy.html ``` ##### [๐Ÿ”ธ Conda Installation (Recommendedโœจ)](docs/en/build_and_install/download_prebuilt_libraries.md) ```bash conda config --add channels conda-forge && conda install cudatoolkit=11.2 cudnn=8.2 ``` ##### ๐Ÿ”ธ Install FastDeploy SDK with only CPU support ```bash pip install fastdeploy-python -f https://www.paddlepaddle.org.cn/whl/fastdeploy.html ``` #### ๐ŸŽ‡ Python Inference Example * Prepare model and picture ```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 ``` * Test inference results ```python # For deployment of GPU/TensorRT, please refer to examples/vision/detection/paddledetection/python import cv2 import fastdeploy.vision as vision im = cv2.imread("000000014439.jpg") 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") result = model.predict(im) print(result) vis_im = vision.vis_detection(im, result, score_threshold=0.5) cv2.imwrite("vis_image.jpg", vis_im) ```
A Quick Start for C++ SDK(click to expand)
#### ๐ŸŽ† Installation - Please refer to [C++ Prebuilt Libraries Download](docs/en/build_and_install/download_prebuilt_libraries.md) #### ๐ŸŽ‡ C++ Inference Example * Prepare models and pictures ```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 ``` * Test inference results ```C++ // For GPU/TensorRT deployment, please refer to examples/vision/detection/paddledetection/cpp #include "fastdeploy/vision.h" int main(int argc, char* argv[]) { namespace vision = fastdeploy::vision; auto im = cv::imread("000000014439.jpg"); 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"); 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; } ```
For more deployment models, please refer to [Vision Model Deployment Examples](examples/vision) .
## โœด๏ธ โœด๏ธ Server-side and Cloud Model List โœด๏ธ โœด๏ธ Notes: โœ…: already supported; โ”: to be supported in the future; N/A: Not Available;
Server-side and cloud model list(click to fold)
| Task | Model | 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 | Phytium D2000 aarch64 | [NVIDIA Jetson](./docs/en/build_and_install/jetson.md) | [Graphcore IPU](./docs/en/build_and_install/ipu.md) | [kunlunxin XPU](./docs/en/build_and_install/kunlunxin.md) |[Huawei Ascend](./docs/en/build_and_install/huawei_ascend.md) | [Serving](./serving) | | Classification | [PaddleClas/ResNet50](./examples/vision/classification/paddleclas) | [โœ…](./examples/vision/classification/paddleclas) | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… |โœ… | | Classification | [TorchVison/ResNet](examples/vision/classification/resnet) | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โ” | โœ… |โœ… | โ” | | Classification | [ltralytics/YOLOv5Cls](examples/vision/classification/yolov5cls) | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โ” | โœ… | โ” |โ” | | Classification | [PaddleClas/PP-LCNet](./examples/vision/classification/paddleclas) | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… |โœ… | โœ… | | Classification | [PaddleClas/PP-LCNetv2](./examples/vision/classification/paddleclas) | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… |โœ… | โœ… | | Classification | [PaddleClas/EfficientNet](./examples/vision/classification/paddleclas) | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… |โœ… | โœ… | | Classification | [PaddleClas/GhostNet](./examples/vision/classification/paddleclas) | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… |โœ… | โœ… | | Classification | [PaddleClas/MobileNetV1](./examples/vision/classification/paddleclas) | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… |โœ… | โœ… | | Classification | [PaddleClas/MobileNetV2](./examples/vision/classification/paddleclas) | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… |โœ… | โœ… | | Classification | [PaddleClas/MobileNetV3](./examples/vision/classification/paddleclas) | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… |โœ… | โœ… | | Classification | [PaddleClas/ShuffleNetV2](./examples/vision/classification/paddleclas) | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… |โœ… | โœ… | | Classification | [PaddleClas/SqueeezeNetV1.1](./examples/vision/classification/paddleclas) | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… |โœ… | โœ… | | Classification | [PaddleClas/Inceptionv3](./examples/vision/classification/paddleclas) | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โ” | โœ… |โœ… | โœ… | | Classification | [PaddleClas/PP-HGNet](./examples/vision/classification/paddleclas) | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… |โœ… | โœ… | | Detection | ๐Ÿ”ฅ๐Ÿ”ฅ[PaddleDetection/PP-YOLOE+](./examples/vision/detection/paddledetection) | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โ” | โœ… |โœ… | โœ… | | Detection | [๐Ÿ”ฅPaddleDetection/YOLOv8](./examples/vision/detection/paddledetection) | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โ” | โœ… |โœ… | โ” | | Detection | [๐Ÿ”ฅultralytics/YOLOv8](./examples/vision/detection/yolov8) | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โ” | โœ… | โ” | โ” |โ” | โ” | | Detection | [PaddleDetection/PicoDet](./examples/vision/detection/paddledetection) | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โ” | โœ… | โ” | โœ… | | Detection | [PaddleDetection/YOLOX](./examples/vision/detection/paddledetection) | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โ” | โœ… | โœ… | โœ… | | Detection | [PaddleDetection/YOLOv3](./examples/vision/detection/paddledetection) | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โ” | โœ… | โœ… | โœ… | | Detection | [PaddleDetection/PP-YOLO](./examples/vision/detection/paddledetection) | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โ” | โœ… | โœ… | โœ… | | Detection | [PaddleDetection/PP-YOLOv2](./examples/vision/detection/paddledetection) | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โ” | โœ… | โœ… | โœ… | | Detection | [PaddleDetection/Faster-RCNN](./examples/vision/detection/paddledetection) | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โ” | โœ… |โ” | โœ… | | Detection | [PaddleDetection/Mask-RCNN](./examples/vision/detection/paddledetection) | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โ” | โœ… |โ” | โœ… | | Detection | [Megvii-BaseDetection/YOLOX](./examples/vision/detection/yolox) | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โ” | โœ… |โœ… | โ” | | Detection | [WongKinYiu/YOLOv7](./examples/vision/detection/yolov7) | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โ” | โœ… |โœ… | โ” | | Detection | [WongKinYiu/YOLOv7end2end_trt](./examples/vision/detection/yolov7end2end_trt) | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โ” | โœ… | โ” | โ” |โ” | โ” | | Detection | [WongKinYiu/YOLOv7end2end_ort](./examples/vision/detection/yolov7end2end_ort) | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โ” | โ” |โ” | โ” | | Detection | [meituan/YOLOv6](./examples/vision/detection/yolov6) | โœ… | โœ… | โœ… |โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โ” | โœ… | โ” | | Detection | [ultralytics/YOLOv5](./examples/vision/detection/yolov5) | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โ” | โœ… | โœ… |โœ… | | Detection | [WongKinYiu/YOLOR](./examples/vision/detection/yolor) | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โ” | โœ… | โ” | โ” | โœ… | โ” | | Detection | [WongKinYiu/ScaledYOLOv4](./examples/vision/detection/scaledyolov4) | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โ” | โ” |โ” | โ” | | Detection | [ppogg/YOLOv5Lite](./examples/vision/detection/yolov5lite) | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | ? | โ” |โ” |โ” | | Detection | [RangiLyu/NanoDetPlus](./examples/vision/detection/nanodet_plus) | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โ” | โ” |โ” | โ” | | Perception | [Paddle3D/Smoke](./examples/vision/perception/paddle3d/smoke) | โ” | โœ… | โ” | โœ… | โ” | โ” | โ” | โ” | โ” | โ” | โ” |โ” | โœ… | | KeyPoint | [PaddleDetection/TinyPose](./examples/vision/keypointdetection/tiny_pose) | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โ” | โœ… |โ” | โ” | | KeyPoint | [PaddleDetection/PicoDet + TinyPose](./examples/vision/keypointdetection/det_keypoint_unite) | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โ” | โœ… | โ” |โ” | | HeadPose | [omasaht/headpose](examples/vision/headpose) | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โ” | โœ… | โ” | โ” | โ” |โ” | | Tracking | [PaddleDetection/PP-Tracking](examples/vision/tracking/pptracking) | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โ” | โ” | โ” |โ” | | OCR | [PaddleOCR/PP-OCRv2](./examples/vision/ocr) | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โ” | โœ… | โ” | โœ… |โœ… | โ” | | OCR | [PaddleOCR/PP-OCRv3](./examples/vision/ocr) | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โ” | โœ… |โœ… | โœ… | | Segmentation | [PaddleSeg/PP-LiteSeg](./examples/vision/segmentation/paddleseg) | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โ” | โœ… | โ” | โœ… |โ” | โ” | | Segmentation | [PaddleSeg/PP-HumanSegLite](./examples/vision/segmentation/paddleseg) | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โ” | โœ… | โ” | โœ… |โœ… | โ” | | Segmentation | [PaddleSeg/HRNet](./examples/vision/segmentation/paddleseg) | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โ” | โœ… | โ” | โœ… | โœ… |โ” | | Segmentation | [PaddleSeg/PP-HumanSegServer](./examples/vision/segmentation/paddleseg) | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โ” | โœ… | โ” | โœ… | โœ… |โ” | | Segmentation | [PaddleSeg/Unet](./examples/vision/segmentation/paddleseg) | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โ” | โœ… | โœ… | โœ… | โœ… |โ” | | Segmentation | [PaddleSeg/Deeplabv3](./examples/vision/segmentation/paddleseg) | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โ” | โœ… | โ” | โœ… | โœ… |โ” | | FaceDetection | [biubug6/RetinaFace](./examples/vision/facedet/retinaface) | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โ” | โ” | โ” | โ” | | FaceDetection | [Linzaer/UltraFace](./examples/vision/facedet/ultraface) | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โ” | โ” | โ” |โ” | | FaceDetection | [deepcam-cn/YOLOv5Face](./examples/vision/facedet/yolov5face) | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โ” | โ” | โ” |โ” | | FaceDetection | [insightface/SCRFD](./examples/vision/facedet/scrfd) | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โ” | โ” | โ” |โ” | | FaceAlign | [Hsintao/PFLD](examples/vision/facealign/pfld) | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โ” | โ” | โ” |โ” | | FaceAlign | [Single430/FaceLandmark1000](./examples/vision/facealign/face_landmark_1000) | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โ” | โœ… | โ” | โ” | โ” | โ” | | FaceAlign | [jhb86253817/PIPNet](./examples/vision/facealign) | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โ” | โœ… | โ” | โ” | โ” |โ” | | FaceRecognition | [insightface/ArcFace](./examples/vision/faceid/insightface) | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โ” | โ” | โ” |โ” | | FaceRecognition | [insightface/CosFace](./examples/vision/faceid/insightface) | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โ” | โ” | โ” |โ” | | FaceRecognition | [insightface/PartialFC](./examples/vision/faceid/insightface) | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โ” | โ” | โ” | โ” | | FaceRecognition | [insightface/VPL](./examples/vision/faceid/insightface) | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โ” | โ” | โ” | โ” | | Matting | [ZHKKKe/MODNet](./examples/vision/matting/modnet) | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โ” | โœ… | โ” | โ” | โ” |โ” | | Matting | [PeterL1n/RobustVideoMatting]() | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โ” | โœ… | โ” | โ” | โ” | โ” | | Matting | [PaddleSeg/PP-Matting](./examples/vision/matting/ppmatting) | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โ” | โœ… |โœ… | โ” | | Matting | [PaddleSeg/PP-HumanMatting](./examples/vision/matting/modnet) | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โ” | โœ… |โœ… |โ” | | Matting | [PaddleSeg/ModNet](./examples/vision/matting/modnet) | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โ” | โ” |โ” | โ” | | Video Super-Resolution | [PaddleGAN/BasicVSR](./) | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โ” | โœ… | โ” | โ” | โ” |โ” | | Video Super-Resolution | [PaddleGAN/EDVR](./examples/vision/sr/edvr) | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โ” | โœ… | โ” | โ” |โ” | โ” | | Video Super-Resolution | [PaddleGAN/PP-MSVSR](./examples/vision/sr/ppmsvsr) | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โ” | โœ… | โ” | โ” |โ” | โ” | | Information Extraction | [PaddleNLP/UIE](./examples/text/uie) | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โ” | โœ… | โ” | โ” |โ” | | | NLP | [PaddleNLP/ERNIE-3.0](./examples/text/ernie-3.0) | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โ” | โ” | โ” | โœ… |โ” | โœ… | | Speech | [PaddleSpeech/PP-TTS](./examples/audio/pp-tts) | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โœ… | โ” | โ” | -- |โ” |โ” | โœ… |
## ๐Ÿ“ณ Mobile and Edge Device Deployment
Mobile and Edge Model List๏ผˆclick to fold๏ผ‰
| Task | Model | Size(MB) | Linux | Android | Linux | Linux | Linux | Linux | Linux | TBD ... | |:------------------:|:-----------------------------------------------------------------------------------------:|:--------:|:-------:|:-------:|:-------:|:-----------------------:|:------------------------------:|:---------------------------:|:--------------------------------:|:-------:| | --- | --- | --- | ARM CPU | [ARM CPU](./java/android) | [Rockchip NPU
RK3588/RK3568/RK3566](./docs/en/build_and_install/rknpu2.md) | [Rockchip NPU
RV1109/RV1126/RK1808](./docs/en/build_and_install/rv1126.md) | [Amlogic NPU
A311D/S905D/C308X](./docs/en/build_and_install/a311d.md) | NXP NPU
i.MX 8M Plus | TBD... | | Classification | [PaddleClas/ResNet50](examples/vision/classification/paddleclas) | 98 | โœ… | โœ… | [โœ…](./examples/vision/classification/paddleclas/rknpu2) | โœ… | | | | | Classification | [PaddleClas/PP-LCNet](examples/vision/classification/paddleclas) | 11.9 | โœ… | โœ… | โ” | โœ… | -- | -- | -- | | Classification | [PaddleClas/PP-LCNetv2](examples/vision/classification/paddleclas) | 26.6 | โœ… | โœ… | โ” | โœ… | -- | -- | -- | | Classification | [PaddleClas/EfficientNet](examples/vision/classification/paddleclas) | 31.4 | โœ… | โœ… | โ” | โœ… | -- | -- | -- | | Classification | [PaddleClas/GhostNet](examples/vision/classification/paddleclas) | 20.8 | โœ… | โœ… | โ” | โœ… | -- | -- | -- | | Classification | [PaddleClas/MobileNetV1](examples/vision/classification/paddleclas) | 17 | โœ… | โœ… | โ” | โœ… | -- | -- | -- | | Classification | [PaddleClas/MobileNetV2](examples/vision/classification/paddleclas) | 14.2 | โœ… | โœ… | โ” | โœ… | -- | -- | -- | | Classification | [PaddleClas/MobileNetV3](examples/vision/classification/paddleclas) | 22 | โœ… | โœ… | โ” | โœ… | โ” | โ” | -- | | Classification | [PaddleClas/ShuffleNetV2](examples/vision/classification/paddleclas) | 9.2 | โœ… | โœ… | โ” | โœ… | -- | -- | -- | | Classification | [PaddleClas/SqueezeNetV1.1](examples/vision/classification/paddleclas) | 5 | โœ… | โœ… | โ” | โœ… | -- | -- | -- | | Classification | [PaddleClas/Inceptionv3](examples/vision/classification/paddleclas) | 95.5 | โœ… | โœ… | โ” | โœ… | -- | -- | -- | | Classification | [PaddleClas/PP-HGNet](examples/vision/classification/paddleclas) | 59 | โœ… | โœ… | โ” | โœ… | -- | -- | -- | | Detection | [PaddleDetection/PicoDet_s](examples/vision/detection/paddledetection) | 4.9 | โœ… | โœ… | [โœ…](./examples/vision/detection/paddledetection/rknpu2) | โœ… | โœ… | โœ… | -- | | Detection | [YOLOv5](./examples/vision/detection/rkyolo) | | โ” | โ” | [โœ…](./examples/vision/detection/rkyolo) | โ” | โ” | โ” | -- | | Face Detection | [deepinsight/SCRFD](./examples/vision/facedet/scrfd) | 2.5 | โœ… | โœ… | [โœ…](./examples/vision/facedet/scrfd/rknpu2) | -- | -- | -- | -- | | Keypoint Detection | [PaddleDetection/PP-TinyPose](examples/vision/keypointdetection/tiny_pose) | 5.5 | โœ… | โœ… | โ” | โ” | โ” | โ” | -- | | Segmentation | [PaddleSeg/PP-LiteSeg(STDC1)](examples/vision/segmentation/paddleseg) | 32.2 | โœ… | โœ… | [โœ…](./examples/vision/segmentation/paddleseg/rknpu2) | -- | -- | -- | -- | | Segmentation | [PaddleSeg/PP-HumanSeg-Lite](examples/vision/segmentation/paddleseg) | 0.556 | โœ… | โœ… | [โœ…](./examples/vision/segmentation/paddleseg/rknpu2) | -- | -- | -- | -- | | Segmentation | [PaddleSeg/HRNet-w18](examples/vision/segmentation/paddleseg) | 38.7 | โœ… | โœ… | [โœ…](./examples/vision/segmentation/paddleseg/rknpu2) | -- | -- | -- | -- | | Segmentation | [PaddleSeg/PP-HumanSeg](examples/vision/segmentation/paddleseg) | 107.2 | โœ… | โœ… | [โœ…](./examples/vision/segmentation/paddleseg/rknpu2) | -- | -- | -- | -- | | Segmentation | [PaddleSeg/Unet](examples/vision/segmentation/paddleseg) | 53.7 | โœ… | โœ… | [โœ…](./examples/vision/segmentation/paddleseg/rknpu2) | -- | -- | -- | -- | | Segmentation | [PaddleSeg/Deeplabv3](examples/vision/segmentation/paddleseg) | 150 | โ” | โœ… | [โœ…](./examples/vision/segmentation/paddleseg/rknpu2) | | | | | | OCR | [PaddleOCR/PP-OCRv2](examples/vision/ocr/PP-OCRv2) | 2.3+4.4 | โœ… | โœ… | โ” | -- | -- | -- | -- | | OCR | [PaddleOCR/PP-OCRv3](examples/vision/ocr/PP-OCRv3) | 2.4+10.6 | โœ… | โ” | โ” | โ” | โ” | โ” | -- |
## โš›๏ธ Web and Mini Program Model List
Web and mini program model list(click to fold)
| Task | Model | [web_demo](examples/application/js/web_demo) | |:------------------:|:-------------------------------------------------------------------------------------------:|:--------------------------------------------:| | --- | --- | [Paddle.js](examples/application/js) | | Detection | [FaceDetection](examples/application/js/web_demo/src/pages/cv/detection) | โœ… | | Detection | [ScrewDetection](examples/application/js/web_demo/src/pages/cv/detection) | โœ… | | Segmentation | [PaddleSeg/HumanSeg](./examples/application/js/web_demo/src/pages/cv/segmentation/HumanSeg) | โœ… | | Object Recognition | [GestureRecognition](examples/application/js/web_demo/src/pages/cv/recognition) | โœ… | | Object Recognition | [ItemIdentification](examples/application/js/web_demo/src/pages/cv/recognition) | โœ… | | OCR | [PaddleOCR/PP-OCRv3](./examples/application/js/web_demo/src/pages/cv/ocr) | โœ… |
## ๐Ÿ’ Acknowledge
We sincerely appreciate the open-sourced capabilities in [EasyEdge](https://ai.baidu.com/easyedge/app/openSource) as we adopt it for the SDK generation and download in this project. ## ยฉ๏ธ License
FastDeploy is provided under the [Apache-2.0](./LICENSE).