xgmiao / FastDeploy

⚡️An Easy-to-use and Fast Deep Learning Model Deployment Toolkit for Cloud and Edge. Including Vision, Text, Audio and Video 20+ main stream scenarios and 150+ SOTA models with end-to-end optimization and multi-platform multi-framework support.

Home Page:https://www.paddlepaddle.org.cn/fastdeploy

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

English | 简体中文

⚡️FastDeploy

⚡️FastDeploy是一款易用高效的推理部署开发套件。覆盖业界🔥热门CV、NLP、Speech的AI模型并提供📦开箱即用的部署体验,包括图像分类、目标检测、图像分割、人脸检测、人脸识别、人体关键点识别、文字识别、语义理解等多任务,满足开发者多场景多硬件多平台的产业部署需求。

Image Classification Object Detection Semantic Segmentation Potrait Segmentation
Image Matting Real-Time Matting OCR Face Alignment
Pose Estimation Behavior Recognition NLP Speech

input :早上好今天是2020
/10/29,最低温度是-3°C。

output:

近期更新

  • 🔥 【直播分享】2022.11.09 20:30~21:30,《覆盖云边端全场景,150+热门模型快速部署》。微信扫码报名
  • 🔥 【直播分享】2022.11.10 20:30~21:30,《瑞芯微、晶晨、恩智浦等10+AI硬件部署,直达产业落地》。微信扫码报名
  • 🔥 【直播分享】2022.11.10 19:00~20:00,《10+热门模型在RK3588、RK3568部署实战》。微信扫码报名
  • 🔥 2022.10.31:Release FastDeploy release v0.5.0

    • 🖥️ 服务端部署:支持推理速度更快的后端,支持更多的模型
      • 集成 Paddle Inference TensorRT后端,并保证其使用与Paddle Inference、TensorRT、OpenVINO、ONNX Runtime、Paddle Lite等一致的开发体验;
      • 支持并测试 Graphcore IPU 通过 Paddle Inference后端;
      • 优化一键模型自动化压缩工具,支持YOLOv7、YOLOv6、YOLOv5等视觉模型,在CPU和GPU推理速度可提升1.5~2倍;
      • 新增 PP-TrackingRobustVideoMatting 等模型;
  • 🔥 2022.10.24:Release FastDeploy release v0.4.0

    • 🖥️ 服务端部署:推理速度大升级
      • 升级 GPU 端到端的优化,在YOLO系列上,模型推理速度从 43ms 提升到 25ms;
      • 新增 TinyPose and PicoDetji lianTinyPosePipeline部署能力;
    • 📲 移动端和端侧部署:移动端后端能力升级,支持更多的CV模型
      • 集成 Paddle Lite,并保证其使用与服务端常用推理引擎 Paddle Inference、TensorRT、OpenVINO、ONNX Runtime 等一致的开发体验;
      • 新增 轻量化目标检测模型分类模型的安卓端部署能力;
    • 🌐 Web和小程序部署:新增Web端部署能力
      • 集成 Paddle.js部署能力,新增 OCR、目标检测、人像分割背景替换、物体识别等Web端部署能力和Demo

目录

🖥️ 服务端部署

Python SDK快速开始(点击可收缩)

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
pip install numpy opencv-python fastdeploy-gpu-python -f https://www.paddlepaddle.org.cn/whl/fastdeploy.html
conda config --add channels conda-forge && conda install cudatoolkit=11.2 cudnn=8.2
安装CPU版本
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
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
# 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.copy())
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

C++ 推理示例

  • 准备模型和图片
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
// 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::Visualize::VisDetection(im, res, 0.5);
  cv::imwrite("vis_image.jpg", vis_im);
  return 0;
}

更多部署案例请参考视觉模型部署示例 .

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;
链接说明:「模型列」会跳转到模型推理Demo代码

任务场景 模型 API Linux Linux Win Win Mac Mac Linux Linux Linux Linux
--- --- --- X86 CPU NVIDIA GPU X86 CPU NVIDIA GPU X86 CPU Arm CPU AArch64 CPU NVIDIA Jetson Graphcore IPU Serving
Classification PaddleClas/ResNet50 Python/C++
Classification TorchVison/ResNet Python/C++
Classification ltralytics/YOLOv5Cls Python/C++
Classification PaddleClas/PP-LCNet Python/C++
Classification PaddleClas/PP-LCNetv2 Python/C++
Classification PaddleClas/EfficientNet Python/C++
Classification PaddleClas/GhostNet Python/C++
Classification PaddleClas/MobileNetV1 Python/C++
Classification PaddleClas/MobileNetV2 Python/C++
Classification PaddleClas/MobileNetV3 Python/C++
Classification PaddleClas/ShuffleNetV2 Python/C++
Classification PaddleClas/SqueeezeNetV1.1 Python/C++
Classification PaddleClas/Inceptionv3 Python/C++
Classification PaddleClas/PP-HGNet Python/C++
Classification PaddleClas/SwinTransformer Python/C++
Detection PaddleDetection/PP-YOLOE Python/C++
Detection PaddleDetection/PicoDet Python/C++
Detection PaddleDetection/YOLOX Python/C++
Detection PaddleDetection/YOLOv3 Python/C++
Detection PaddleDetection/PP-YOLO Python/C++
Detection PaddleDetection/PP-YOLOv2 Python/C++
Detection PaddleDetection/Faster-RCNN Python/C++
Detection PaddleDetection/Mask-RCNN Python/C++
Detection Megvii-BaseDetection/YOLOX Python/C++
Detection WongKinYiu/YOLOv7 Python/C++
Detection WongKinYiu/YOLOv7end2end_trt Python/C++
Detection WongKinYiu/YOLOv7end2end_ort_ Python/C++
Detection meituan/YOLOv6 Python/C++
Detection ultralytics/YOLOv5 Python/C++
Detection WongKinYiu/YOLOR Python/C++
Detection WongKinYiu/ScaledYOLOv4 Python/C++
Detection ppogg/YOLOv5Lite Python/C++
Detection RangiLyu/NanoDetPlus Python/C++
KeyPoint PaddleDetection/TinyPose Python/C++
KeyPoint PaddleDetection/PicoDet + TinyPose Python/C++
HeadPose omasaht/headpose Python/C++
Tracking PaddleDetection/PP-Tracking Python/C++
OCR PaddleOCR/PP-OCRv2 Python/C++
OCR PaddleOCR/PP-OCRv3 Python/C++
Segmentation PaddleSeg/PP-LiteSeg Python/C++
Segmentation PaddleSeg/PP-HumanSegLite Python/C++
Segmentation PaddleSeg/HRNet Python/C++
Segmentation PaddleSeg/PP-HumanSegServer Python/C++
Segmentation PaddleSeg/Unet Python/C++
Segmentation PaddleSeg/Deeplabv3 Python/C++
FaceDetection biubug6/RetinaFace Python/C++
FaceDetection Linzaer/UltraFace Python/C++
FaceDetection deepcam-cn/YOLOv5Face Python/C++
FaceDetection insightface/SCRFD Python/C++
FaceAlign Hsintao/PFLD Python/C++
FaceRecognition insightface/ArcFace Python/C++
FaceRecognition insightface/CosFace Python/C++
FaceRecognition insightface/PartialFC Python/C++
FaceRecognition insightface/VPL Python/C++
Matting ZHKKKe/MODNet Python/C++
Matting PeterL1n/RobustVideoMatting Python/C++
Matting PaddleSeg/PP-Matting Python/C++
Matting PaddleSeg/PP-HumanMatting Python/C++
Matting PaddleSeg/ModNet Python/C++
Information Extraction PaddleNLP/UIE Python/C++
NLP PaddleNLP/ERNIE-3.0 Python/C++
Speech PaddleSpeech/PP-TTS Python/C++ --

📲 移动端和端侧部署 🔥🔥🔥🔥

Paddle Lite NPU部署

📲 端侧模型支持列表

任务场景 模型 大小(MB) Linux Android iOS Linux Linux Linux Linux 更新中...
--- --- --- ARM CPU ARM CPU ARM CPU 瑞芯微NPU
RK3568/RK3588
瑞芯微NPU
RV1109/RV1126/RK1808
晶晨NPU
A311D/S905D/C308X
恩智浦NPU
i.MX 8M Plus
更新中...|
Classification PaddleClas/PP-LCNet 11.9 -- -- -- --
Classification PaddleClas/PP-LCNetv2 26.6 -- -- -- --
Classification PaddleClas/EfficientNet 31.4 -- -- -- --
Classification PaddleClas/GhostNet 20.8 -- -- -- --
Classification PaddleClas/MobileNetV1 17 -- -- -- --
Classification PaddleClas/MobileNetV2 14.2 -- -- -- --
Classification PaddleClas/MobileNetV3 22 --
Classification PaddleClas/ShuffleNetV2 9.2 -- -- -- --
Classification PaddleClas/SqueezeNetV1.1 5 -- -- -- --
Classification PaddleClas/Inceptionv3 95.5 -- -- -- --
Classification PaddleClas/PP-HGNet 59 -- -- -- --
Classification PaddleClas/SwinTransformer_224_win7 352.7 -- -- -- --
Detection PaddleDetection/PP-PicoDet_s_320_coco 4.1 -- -- -- --
Detection PaddleDetection/PP-PicoDet_s_320_lcnet 4.9 --
Detection PaddleDetection/CenterNet 4.8 -- -- -- --
Detection PaddleDetection/YOLOv3_MobileNetV3 94.6 -- -- -- --
Detection PaddleDetection/PP-YOLO_tiny_650e_coco 4.4 -- -- -- --
Detection PaddleDetection/SSD_MobileNetV1_300_120e_voc 23.3 -- -- -- --
Detection PaddleDetection/PP-YOLO_ResNet50vd 188.5 -- -- -- --
Detection PaddleDetection/PP-YOLOv2_ResNet50vd 218.7 -- -- -- --
Detection PaddleDetection/PP-YOLO_crn_l_300e_coco 209.1 -- -- -- --
Detection YOLOv5s 29.3 -- -- -- --
Face Detection BlazeFace 1.5 -- -- -- --
Face Detection RetinaFace 1.7 -- -- -- --
Keypoint Detection PaddleDetection/PP-TinyPose 5.5 --
Segmentation PaddleSeg/PP-LiteSeg(STDC1) 32.2 -- -- -- --
Segmentation PaddleSeg/PP-HumanSeg-Lite 0.556 -- -- -- --
Segmentation PaddleSeg/HRNet-w18 38.7 -- -- -- --
Segmentation PaddleSeg/PP-HumanSeg 107.2 -- -- -- --
Segmentation PaddleSeg/Unet 53.7 -- -- -- --
Segmentation PaddleSeg/Deeplabv3 150
OCR PaddleOCR/PP-OCRv1 2.3+4.4 -- -- -- --
OCR PaddleOCR/PP-OCRv2 2.3+4.4 -- -- -- --
OCR PaddleOCR/PP-OCRv3 2.4+10.6 --
OCR PaddleOCR/PP-OCRv3-tiny 2.4+10.7 -- -- -- --

🌐 Web和小程序部署

任务场景 模型 web_demo
--- --- Paddle.js
Detection FaceDetection
Detection ScrewDetection
Segmentation PaddleSeg/HumanSeg
Object Recognition GestureRecognition
Object Recognition ItemIdentification
OCR PaddleOCR/PP-OCRv3

社区交流

  • 加入社区👬: 微信扫描二维码,进入FastDeploy技术交流群

Acknowledge

本项目中SDK生成和下载使用了EasyEdge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

About

⚡️An Easy-to-use and Fast Deep Learning Model Deployment Toolkit for Cloud and Edge. Including Vision, Text, Audio and Video 20+ main stream scenarios and 150+ SOTA models with end-to-end optimization and multi-platform multi-framework support.

https://www.paddlepaddle.org.cn/fastdeploy

License:Apache License 2.0


Languages

Language:C++ 69.9%Language:Python 16.4%Language:CMake 5.6%Language:Java 5.3%Language:Shell 1.4%Language:Batchfile 0.7%Language:C 0.3%Language:Cuda 0.3%Language:Dockerfile 0.1%