未验证 提交 1b7c04de 编写于 作者: Y YixinKristy 提交者: GitHub

Update Readme_cn and Add Readme_en on 2.4 (#5500)

* Update README_cn.md

* Update Readme

* Update README_cn.md

* Update README_cn.md
上级 7e1402e4
...@@ -2,12 +2,11 @@ ...@@ -2,12 +2,11 @@
<div align="center"> <div align="center">
<p align="center"> <p align="center">
<img src="https://user-images.githubusercontent.com/48054808/157664876-5162fa5e-bde1-40e4-9f4a-104438d11e7b.png" align="middle" width = "1000" /> <img src="https://user-images.githubusercontent.com/48054808/160532560-34cf7a1f-d950-435e-90d2-4b0a679e5119.png" align="middle" width = "800" />
</p> </p>
**飞桨目标检测开发套件,端到端地完成从训练到部署的全流程目标检测应用。** **飞桨目标检测开发套件,端到端地完成从训练到部署的全流程目标检测应用。**
[![License](https://img.shields.io/badge/license-Apache%202-blue.svg)](LICENSE) [![License](https://img.shields.io/badge/license-Apache%202-blue.svg)](LICENSE)
[![Version](https://img.shields.io/github/release/PaddlePaddle/PaddleDetection.svg)](https://github.com/PaddlePaddle/PaddleDetection/releases) [![Version](https://img.shields.io/github/release/PaddlePaddle/PaddleDetection.svg)](https://github.com/PaddlePaddle/PaddleDetection/releases)
![python version](https://img.shields.io/badge/python-3.6+-orange.svg) ![python version](https://img.shields.io/badge/python-3.6+-orange.svg)
...@@ -15,26 +14,21 @@ ...@@ -15,26 +14,21 @@
</div> </div>
## 产品动态 <img src="https://user-images.githubusercontent.com/48054808/157793354-6e7f381a-0aa6-4bb7-845c-9acf2ecc05c3.png" width="30"/> ## <img src="https://user-images.githubusercontent.com/48054808/157793354-6e7f381a-0aa6-4bb7-845c-9acf2ecc05c3.png" width="20"/> 产品动态
- 🔥 **2022.3.24:PaddleDetection发布[release/2.4版本](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.4)** - 🔥 **2022.3.24:PaddleDetection发布[release/2.4版本](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.4)**
- 发布高精度云边一体SOTA目标检测模型[PP-YOLOE](config/ppyoloe),全系列多尺度模型,满足不同硬件算力需求,可适配服务器、边缘端GPU及其他服务器端AI加速卡。 - 发布高精度云边一体SOTA目标检测模型[PP-YOLOE](configs/ppyoloe),COCO数据集精度51.4%,V100预测速度78.1 FPS,支持混合精度训练,训练较PP-YOLOv2加速33%,全系列多尺度模型,满足不同硬件算力需求,可适配服务器、边缘端GPU及其他服务器端AI加速卡。
- 发布边缘端和CPU端超轻量SOTA目标检测模型[PP-PicoDet增强版](configs/picodet),提供模型稀疏化和量化功能,便于模型加速,各类硬件无需单独开发后处理模块,降低部署门槛。 - 发布边缘端和CPU端超轻量SOTA目标检测模型[PP-PicoDet增强版](configs/picodet)精度提升2%左右,CPU预测速度提升63%,新增参数量0.7M的PicoDet-XS模型,提供模型稀疏化和量化功能,便于模型加速,各类硬件无需单独开发后处理模块,降低部署门槛。
- 发布实时行人分析工具[PP-Human](deploy/pphuman),支持行人跟踪、人流量统计、人体属性识别与摔倒检测四大能力,基于真实场景数据特殊优化,精准识别各类摔倒姿势,适应不同环境背景、光线及摄像角度。 - 发布实时行人分析工具[PP-Human](deploy/pphuman),支持行人跟踪、人流量统计、人体属性识别与摔倒检测四大能力,基于真实场景数据特殊优化,精准识别各类摔倒姿势,适应不同环境背景、光线及摄像角度。
- 2021.11.03: PaddleDetection发布[release/2.3版本](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.3) - 2021.11.03: PaddleDetection发布[release/2.3版本](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.3)
- 发布轻量级检测特色模型⚡[PP-PicoDet](configs/picodet),0.99m的参数量可实现精度30+mAP、速度150FPS。 - 发布轻量级检测特色模型⚡[PP-PicoDet](configs/picodet),0.99m的参数量可实现精度30+mAP、速度150FPS。
- 发布轻量级关键点特色模型⚡[PP-TinyPose](configs/keypoint/tiny_pose),单人场景FP16推理可达122FPS、51.8AP,具有精度高速度快、检测人数无限制、微小目标效果好的优势。 - 发布轻量级关键点特色模型⚡[PP-TinyPose](configs/keypoint/tiny_pose),单人场景FP16推理可达122FPS、51.8AP,具有精度高速度快、检测人数无限制、微小目标效果好的优势。
- 发布实时跟踪系统[PP-Tracking](deploy/pptracking),覆盖单、多镜头下行人、车辆、多类别跟踪,对小目标、密集型特殊优化,提供人、车流量技术解决方案。 - 发布实时跟踪系统[PP-Tracking](deploy/pptracking),覆盖单、多镜头下行人、车辆、多类别跟踪,对小目标、密集型特殊优化,提供人、车流量技术解决方案。
- 新增[Swin Transformer](configs/faster_rcnn)[TOOD](configs/tood)[GFL](configs/gfl)目标检测模型。 - 新增[Swin Transformer](configs/faster_rcnn)[TOOD](configs/tood)[GFL](configs/gfl)目标检测模型。
- 发布[Sniper](configs/sniper)小目标检测优化模型,发布针对EdgeBoard优化[PP-YOLO-EB](configs/ppyolo)模型。 - 发布[Sniper](configs/sniper)小目标检测优化模型,发布针对EdgeBoard优化[PP-YOLO-EB](configs/ppyolo)模型。
- 新增轻量化关键点模型[Lite HRNet](configs/keypoint)关键点模型并支持Paddle Lite部署。 - 新增轻量化关键点模型[Lite HRNet](configs/keypoint)关键点模型并支持Paddle Lite部署。
- 2021.08.10: PaddleDetection发布[release/2.2版本](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.2) - 2021.08.10: PaddleDetection发布[release/2.2版本](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.2)
...@@ -44,42 +38,46 @@ ...@@ -44,42 +38,46 @@
- 新增[人头](configs/mot/headtracking21)[车辆](configs/mot/vehicle)跟踪垂类模型。 - 新增[人头](configs/mot/headtracking21)[车辆](configs/mot/vehicle)跟踪垂类模型。
- 2021.05.20: PaddleDetection发布[release/2.1版本](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.1) - 2021.05.20: PaddleDetection发布[release/2.1版本](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.1)
- 新增[关键点检测](configs/keypoint),模型包括HigherHRNet,HRNet。 - 新增[关键点检测](configs/keypoint),模型包括HigherHRNet,HRNet。
- 新增[多目标跟踪](configs/mot)能力,模型包括DeepSORT,JDE,FairMOT。 - 新增[多目标跟踪](configs/mot)能力,模型包括DeepSORT,JDE,FairMOT。
- 发布PPYOLO系列模型压缩模型,新增[ONNX模型导出教程](deploy/EXPORT_ONNX_MODEL.md) - 发布PPYOLO系列模型压缩模型,新增[ONNX模型导出教程](deploy/EXPORT_ONNX_MODEL.md)
## 简介 <img title="" src="https://user-images.githubusercontent.com/48054808/157795569-9fc77c85-732f-4870-9be0-99a7fe2cff27.png" alt="" width="30"> ## <img title="" src="https://user-images.githubusercontent.com/48054808/157795569-9fc77c85-732f-4870-9be0-99a7fe2cff27.png" alt="" width="20"> 简介
**PaddleDetection**为基于飞桨PaddlePaddle的端到端目标检测套件,内置**190+主流目标检测、实例分割、跟踪、关键点检测**算法,其中包括**服务器端和移动端高精度、轻量级**产业级SOTA模型、冠军方案和学术前沿算法,并提供配置化的网络模块组件、十余种数据增强策略和损失函数等高阶优化支持和多种部署方案,在打通数据处理、模型开发、训练、压缩、部署全流程的基础上,提供丰富的案例及教程,加速算法产业落地应用。 **PaddleDetection**为基于飞桨PaddlePaddle的端到端目标检测套件,内置**30+模型算法****250+预训练模型**,覆盖**目标检测、实例分割、跟踪、关键点检测**等方向,其中包括**服务器端和移动端高精度、轻量级**产业级SOTA模型、冠军方案和学术前沿算法,并提供配置化的网络模块组件、十余种数据增强策略和损失函数等高阶优化支持和多种部署方案,在打通数据处理、模型开发、训练、压缩、部署全流程的基础上,提供丰富的案例及教程,加速算法产业落地应用。
#### 提供目标检测、实例分割、多目标跟踪、关键点检测等多种能力 #### 提供目标检测、实例分割、多目标跟踪、关键点检测等多种能力
<div width="1000" align="center"> <div align="center">
<img src="docs/images/ppdet.gif"/> <img src="docs/images/ppdet.gif" width="800"/>
</div> </div>
#### 应用场景覆盖工业、智慧城市、安防、交通、零售、医疗等十余种行业 #### 应用场景覆盖工业、智慧城市、安防、交通、零售、医疗等十余种行业
## 特性 <img src="https://user-images.githubusercontent.com/48054808/157799599-e6a66855-bac6-4e75-b9c0-96e13cb9612f.png" width="30"/> <div align="center">
<img src="https://user-images.githubusercontent.com/48054808/157826886-2e101a71-25a2-42f5-bf5e-30a97be28f46.gif" width="800"/>
</div>
## <img src="https://user-images.githubusercontent.com/48054808/157799599-e6a66855-bac6-4e75-b9c0-96e13cb9612f.png" width="20"/> 特性
- **模型丰富**: 包含**目标检测****实例分割****人脸检测****100+个预训练模型**,涵盖多种**全球竞赛冠军**方案。 - **模型丰富**: 包含**目标检测****实例分割****人脸检测******关键点检测******多目标跟踪****250+个预训练模型**,涵盖多种**全球竞赛冠军**方案。
- **使用简洁**:模块化设计,解耦各个网络组件,开发者轻松搭建、试用各种检测模型及优化策略,快速得到高性能、定制化的算法。 - **使用简洁**:模块化设计,解耦各个网络组件,开发者轻松搭建、试用各种检测模型及优化策略,快速得到高性能、定制化的算法。
- **端到端打通**: 从数据增强、组网、训练、压缩、部署端到端打通,并完备支持**云端**/**边缘端**多架构、多设备部署。 - **端到端打通**: 从数据增强、组网、训练、压缩、部署端到端打通,并完备支持**云端**/**边缘端**多架构、多设备部署。
- **高性能**: 基于飞桨的高性能内核,模型训练速度及显存占用优势明显。支持FP16训练, 支持多机训练。 - **高性能**: 基于飞桨的高性能内核,模型训练速度及显存占用优势明显。支持FP16训练, 支持多机训练。
## 技术交流 <img title="" src="https://user-images.githubusercontent.com/48054808/157800467-2a9946ad-30d1-49a9-b9db-ba33413d9c90.png" alt="" width="30"> ## <img title="" src="https://user-images.githubusercontent.com/48054808/157800467-2a9946ad-30d1-49a9-b9db-ba33413d9c90.png" alt="" width="20"> 技术交流
- 如果你发现任何PaddleDetection存在的问题或者是建议, 欢迎通过[GitHub Issues](https://github.com/PaddlePaddle/PaddleDetection/issues)给我们提issues。 - 如果你发现任何PaddleDetection存在的问题或者是建议, 欢迎通过[GitHub Issues](https://github.com/PaddlePaddle/PaddleDetection/issues)给我们提issues。
- 欢迎加入PaddleDetection QQ、微信(添加并回复小助手“检测”)用户群 - 欢迎加入PaddleDetection QQ、微信(添加并回复小助手“检测”)用户群
<div align="center"> <div align="center">
<img src="https://user-images.githubusercontent.com/48054808/157800129-2f9a0b72-6bb8-4b10-8310-93ab1639253f.jpg" width = "190" /> <img src="https://user-images.githubusercontent.com/48054808/157800129-2f9a0b72-6bb8-4b10-8310-93ab1639253f.jpg" width = "200" />
<img src="https://user-images.githubusercontent.com/48054808/157800287-a4fced21-2821-4e55-8fd6-6aae167122c2.png" width = "200" /> <img src="https://user-images.githubusercontent.com/48054808/160531099-9811bbe6-cfbb-47d5-8bdb-c2b40684d7dd.png" width = "200" />
</div> </div>
## 套件结构概览 <img src="https://user-images.githubusercontent.com/48054808/157827140-03ffaff7-7d14-48b4-9440-c38986ea378c.png" width="30"/> ## <img src="https://user-images.githubusercontent.com/48054808/157827140-03ffaff7-7d14-48b4-9440-c38986ea378c.png" width="20"/> 套件结构概览
<table align="center"> <table align="center">
<tbody> <tbody>
...@@ -232,7 +230,7 @@ ...@@ -232,7 +230,7 @@
</tbody> </tbody>
</table> </table>
## 模型性能概览 <img src="https://user-images.githubusercontent.com/48054808/157801371-9a9a8c65-1690-4123-985a-e0559a7f9494.png" width="30"/> ## <img src="https://user-images.githubusercontent.com/48054808/157801371-9a9a8c65-1690-4123-985a-e0559a7f9494.png" width="20"/> 模型性能概览
各模型结构和骨干网络的代表模型在COCO数据集上精度mAP和单卡Tesla V100上预测速度(FPS)对比图。 各模型结构和骨干网络的代表模型在COCO数据集上精度mAP和单卡Tesla V100上预测速度(FPS)对比图。
...@@ -259,7 +257,7 @@ ...@@ -259,7 +257,7 @@
- 测试数据均使用高通骁龙865(4\*A77 + 4\*A55)处理器batch size为1, 开启4线程测试,测试使用NCNN预测库,测试脚本见[MobileDetBenchmark](https://github.com/JiweiMaster/MobileDetBenchmark) - 测试数据均使用高通骁龙865(4\*A77 + 4\*A55)处理器batch size为1, 开启4线程测试,测试使用NCNN预测库,测试脚本见[MobileDetBenchmark](https://github.com/JiweiMaster/MobileDetBenchmark)
- [PP-PicoDet](configs/picodet)[PP-YOLO-Tiny](configs/ppyolo)为PaddleDetection自研模型,其余模型PaddleDetection暂未提供 - [PP-PicoDet](configs/picodet)[PP-YOLO-Tiny](configs/ppyolo)为PaddleDetection自研模型,其余模型PaddleDetection暂未提供
## 文档教程 <img src="https://user-images.githubusercontent.com/48054808/157828296-d5eb0ccb-23ea-40f5-9957-29853d7d13a9.png" width="30"/> ## <img src="https://user-images.githubusercontent.com/48054808/157828296-d5eb0ccb-23ea-40f5-9957-29853d7d13a9.png" width="20"/> 文档教程
### 入门教程 ### 入门教程
...@@ -295,7 +293,7 @@ ...@@ -295,7 +293,7 @@
- [数据处理模块](docs/advanced_tutorials/READER.md) - [数据处理模块](docs/advanced_tutorials/READER.md)
- [新增检测模型](docs/advanced_tutorials/MODEL_TECHNICAL.md) - [新增检测模型](docs/advanced_tutorials/MODEL_TECHNICAL.md)
## 模型库 <img src="https://user-images.githubusercontent.com/48054808/157829890-a535b8a6-631c-4c87-b861-64d4b32b2d6a.png" width="30"/> ## <img src="https://user-images.githubusercontent.com/48054808/157829890-a535b8a6-631c-4c87-b861-64d4b32b2d6a.png" width="20"/> 模型库
- 通用目标检测: - 通用目标检测:
- [模型库](docs/MODEL_ZOO_cn.md) - [模型库](docs/MODEL_ZOO_cn.md)
...@@ -330,12 +328,12 @@ ...@@ -330,12 +328,12 @@
- [Objects365 2019 Challenge夺冠模型](static/docs/featured_model/champion_model/CACascadeRCNN.md) - [Objects365 2019 Challenge夺冠模型](static/docs/featured_model/champion_model/CACascadeRCNN.md)
- [Open Images 2019-Object Detction比赛最佳单模型](static/docs/featured_model/champion_model/OIDV5_BASELINE_MODEL.md) - [Open Images 2019-Object Detction比赛最佳单模型](static/docs/featured_model/champion_model/OIDV5_BASELINE_MODEL.md)
## 应用案例 <img title="" src="https://user-images.githubusercontent.com/48054808/157836473-1cf451fa-f01f-4148-ba68-b6d06d5da2f9.png" alt="" width="30"> ## <img title="" src="https://user-images.githubusercontent.com/48054808/157836473-1cf451fa-f01f-4148-ba68-b6d06d5da2f9.png" alt="" width="20"> 应用案例
- [人像圣诞特效自动生成工具](static/application/christmas) - [人像圣诞特效自动生成工具](static/application/christmas)
- [安卓健身APP](https://github.com/zhiboniu/pose_demo_android) - [安卓健身APP](https://github.com/zhiboniu/pose_demo_android)
## 第三方教程推荐 <img src="https://user-images.githubusercontent.com/48054808/157828296-d5eb0ccb-23ea-40f5-9957-29853d7d13a9.png" width="30"/> ## <img src="https://user-images.githubusercontent.com/48054808/160552806-496dc3ba-beb6-4623-8e26-44416b5848bf.png" width="25"/> 第三方教程推荐
- [PaddleDetection在Windows下的部署(一)](https://zhuanlan.zhihu.com/p/268657833) - [PaddleDetection在Windows下的部署(一)](https://zhuanlan.zhihu.com/p/268657833)
- [PaddleDetection在Windows下的部署(二)](https://zhuanlan.zhihu.com/p/280206376) - [PaddleDetection在Windows下的部署(二)](https://zhuanlan.zhihu.com/p/280206376)
...@@ -343,15 +341,15 @@ ...@@ -343,15 +341,15 @@
- [安全帽检测YOLOv3模型在树莓派上的部署](https://github.com/PaddleCV-FAQ/PaddleDetection-FAQ/blob/main/Lite%E9%83%A8%E7%BD%B2/yolov3_for_raspi.md) - [安全帽检测YOLOv3模型在树莓派上的部署](https://github.com/PaddleCV-FAQ/PaddleDetection-FAQ/blob/main/Lite%E9%83%A8%E7%BD%B2/yolov3_for_raspi.md)
- [使用SSD-MobileNetv1完成一个项目--准备数据集到完成树莓派部署](https://github.com/PaddleCV-FAQ/PaddleDetection-FAQ/blob/main/Lite%E9%83%A8%E7%BD%B2/ssd_mobilenet_v1_for_raspi.md) - [使用SSD-MobileNetv1完成一个项目--准备数据集到完成树莓派部署](https://github.com/PaddleCV-FAQ/PaddleDetection-FAQ/blob/main/Lite%E9%83%A8%E7%BD%B2/ssd_mobilenet_v1_for_raspi.md)
## 版本更新 <img src="https://user-images.githubusercontent.com/48054808/157835981-ef6057b4-6347-4768-8fcc-cd07fcc3d8b0.png" width="30"/> ## <img src="https://user-images.githubusercontent.com/48054808/157835981-ef6057b4-6347-4768-8fcc-cd07fcc3d8b0.png" width="20"/> 版本更新
版本更新内容请参考[版本更新文档](docs/CHANGELOG.md) 版本更新内容请参考[版本更新文档](docs/CHANGELOG.md)
## 许可证书 <img title="" src="https://user-images.githubusercontent.com/48054808/157835345-f5d24128-abaf-4813-b793-d2e5bdc70e5a.png" alt="" width="30"> ## <img title="" src="https://user-images.githubusercontent.com/48054808/157835345-f5d24128-abaf-4813-b793-d2e5bdc70e5a.png" alt="" width="20"> 许可证书
本项目的发布受[Apache 2.0 license](LICENSE)许可认证。 本项目的发布受[Apache 2.0 license](LICENSE)许可认证。
## 贡献代码 <img src="https://user-images.githubusercontent.com/48054808/157835796-08d4ffbc-87d9-4622-89d8-cf11a44260fc.png" width="30"/> ## <img src="https://user-images.githubusercontent.com/48054808/157835796-08d4ffbc-87d9-4622-89d8-cf11a44260fc.png" width="20"/> 贡献代码
我们非常欢迎你可以为PaddleDetection提供代码,也十分感谢你的反馈。 我们非常欢迎你可以为PaddleDetection提供代码,也十分感谢你的反馈。
...@@ -361,7 +359,7 @@ ...@@ -361,7 +359,7 @@
- 感谢[yangyudong](https://github.com/yangyudong2020), [hchhtc123](https://github.com/hchhtc123) 开发PP-Tracking GUI界面 - 感谢[yangyudong](https://github.com/yangyudong2020), [hchhtc123](https://github.com/hchhtc123) 开发PP-Tracking GUI界面
- 感谢[Shigure19](https://github.com/Shigure19) 开发PP-TinyPose健身APP - 感谢[Shigure19](https://github.com/Shigure19) 开发PP-TinyPose健身APP
## 引用 <img src="https://user-images.githubusercontent.com/48054808/157835276-9aab9d1c-1c46-446b-bdd4-5ab75c5cfa48.png" width="30"/> ## <img src="https://user-images.githubusercontent.com/48054808/157835276-9aab9d1c-1c46-446b-bdd4-5ab75c5cfa48.png" width="20"/> 引用
``` ```
@misc{ppdet2019, @misc{ppdet2019,
......
English | [简体中文](README_cn.md) English | [简体中文](README_cn.md)
<div align="center">
<p align="center">
<img src="https://user-images.githubusercontent.com/48054808/160532560-34cf7a1f-d950-435e-90d2-4b0a679e5119.png" align="middle" width = "800" />
</p>
****A High-Efficient Development Toolkit for Object Detection based on [PaddlePaddle](https://github.com/paddlepaddle/paddle).****
[![License](https://img.shields.io/badge/license-Apache%202-blue.svg)](LICENSE)
[![Version](https://img.shields.io/github/release/PaddlePaddle/PaddleDetection.svg)](https://github.com/PaddlePaddle/PaddleDetection/releases)
![python version](https://img.shields.io/badge/python-3.6+-orange.svg)
![support os](https://img.shields.io/badge/os-linux%2C%20win%2C%20mac-yellow.svg)
</div>
# Product news ## <img src="https://user-images.githubusercontent.com/48054808/157793354-6e7f381a-0aa6-4bb7-845c-9acf2ecc05c3.png" width="20"/> Latest News
- 🔥 **2022.3.24:PaddleDetection [release 2.4 version](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.4)**
- Release GPU SOTA object detection series models (s/m/l/x) [PP-YOLOE](configs/ppyoloe), achieving mAP as 51.4% on COCO test dataset and 78.1 FPS on Nvidia V100, supporting AMP training and its training speed is 33% faster than PP-YOLOv2.
- Release enhanced models of [PP-PicoDet](configs/picodet), including PP-PicoDet-XS model with 0.7M parameters, its mAP promoted ~2% on COCO, inference speed accelerated 63% on CPU, and post-processing integrated into the network to optimize deployment pipeline.
- Release real-time human analysis tool [PP-Human](deploy/pphuman), which is based on data from real-life situations, supporting pedestrian detection, attribute recognition, human tracking, multi-camera tracking, human statistics and action recognition.
- 2021.11.03: Release [release/2.3](https://github.com/PaddlePaddle/Paddleetection/tree/release/2.3) version. Release mobile object detection model ⚡[PP-PicoDet](configs/picodet), mobile keypoint detection model ⚡[PP-TinyPose](configs/keypoint/tiny_pose),Real-time tracking system [PP-Tracking](deploy/pptracking). Release object detection models, including [Swin-Transformer](configs/faster_rcnn), [TOOD](configs/tood), [GFL](configs/gfl), release [Sniper](configs/sniper) tiny object detection models and optimized [PP-YOLO-EB](configs/ppyolo) model for EdgeBoard. Release mobile keypoint detection model [Lite HRNet](configs/keypoint). - 2021.11.03: Release [release/2.3](https://github.com/PaddlePaddle/Paddleetection/tree/release/2.3) version. Release mobile object detection model ⚡[PP-PicoDet](configs/picodet), mobile keypoint detection model ⚡[PP-TinyPose](configs/keypoint/tiny_pose),Real-time tracking system [PP-Tracking](deploy/pptracking). Release object detection models, including [Swin-Transformer](configs/faster_rcnn), [TOOD](configs/tood), [GFL](configs/gfl), release [Sniper](configs/sniper) tiny object detection models and optimized [PP-YOLO-EB](configs/ppyolo) model for EdgeBoard. Release mobile keypoint detection model [Lite HRNet](configs/keypoint).
- 2021.08.10: Release [release/2.2](https://github.com/PaddlePaddle/Paddleetection/tree/release/2.2) version. Release Transformer object detection models, including [DETR](configs/detr), [Deformable DETR](configs/deformable_detr), [Sparse RCNN](configs/sparse_rcnn). Release [keypoint detection](configs/keypoint) models, including DarkHRNet and model trained on MPII dataset. Release [head-tracking](configs/mot/headtracking21) and [vehicle-tracking](configs/mot/vehicle) multi-object tracking models. - 2021.08.10: Release [release/2.2](https://github.com/PaddlePaddle/Paddleetection/tree/release/2.2) version. Release Transformer object detection models, including [DETR](configs/detr), [Deformable DETR](configs/deformable_detr), [Sparse RCNN](configs/sparse_rcnn). Release [keypoint detection](configs/keypoint) models, including DarkHRNet and model trained on MPII dataset. Release [head-tracking](configs/mot/headtracking21) and [vehicle-tracking](configs/mot/vehicle) multi-object tracking models.
- 2021.05.20: Release [release/2.1](https://github.com/PaddlePaddle/Paddleetection/tree/release/2.1) version. Release [Keypoint Detection](configs/keypoint), including HigherHRNet and HRNet, [Multi-Object Tracking](configs/mot), including DeepSORT,JDE and FairMOT. Release model compression for PPYOLO series models.Update documents such as [EXPORT ONNX MODEL](deploy/EXPORT_ONNX_MODEL.md).
- 2021.05.20: Release [release/2.1](https://github.com/PaddlePaddle/Paddleetection/tree/release/2.1) version. Release [Keypoint Detection](configs/keypoint), including HigherHRNet and HRNet, [Multi-Object Tracking](configs/mot), including DeepSORT,JDE and FairMOT. Release model compression for PPYOLO series models.Update documents such as [EXPORT ONNX MODEL](deploy/EXPORT_ONNX_MODEL.md).
# Introduction ## <img title="" src="https://user-images.githubusercontent.com/48054808/157795569-9fc77c85-732f-4870-9be0-99a7fe2cff27.png" alt="" width="20"> Introduction
PaddleDetection is an end-to-end object detection development kit based on PaddlePaddle, which implements varied mainstream object detection, instance segmentation, tracking and keypoint detection algorithms in modular designwhich with configurable modules such as network components, data augmentations and losses, and release many kinds SOTA industry practice models, integrates abilities of model compression and cross-platform high-performance deployment, aims to help developers in the whole end-to-end development in a faster and better way. PaddleDetection is an end-to-end object detection development kit based on PaddlePaddle, which implements varied mainstream object detection, instance segmentation, tracking and keypoint detection algorithms in modular designwhich with configurable modules such as network components, data augmentations and losses, and release many kinds SOTA industry practice models, integrates abilities of model compression and cross-platform high-performance deployment, aims to help developers in the whole end-to-end development in a faster and better way.
### PaddleDetection provides image processing capabilities such as object detection, instance segmentation, multi-object tracking, keypoint detection and etc. #### PaddleDetection provides image processing capabilities such as object detection, instance segmentation, multi-object tracking, keypoint detection and etc.
<div width="1000" align="center"> <div align="center">
<img src="docs/images/ppdet.gif"/> <img src="docs/images/ppdet.gif" width="800"/>
</div> </div>
#### PaddleDetection covers industrialization, smart city, security & protection, retail, medicare industry and etc.
<div align="center">
<img src="https://user-images.githubusercontent.com/48054808/157826886-2e101a71-25a2-42f5-bf5e-30a97be28f46.gif" width="800"/>
</div>
### Features ## <img src="https://user-images.githubusercontent.com/48054808/157799599-e6a66855-bac6-4e75-b9c0-96e13cb9612f.png" width="20"/> Features
- **Rich Models** - **Rich Models**
PaddleDetection provides rich of models, including **100+ pre-trained models** such as **object detection**, **instance segmentation**, **face detection** etc. It covers a variety of **global competition champion** schemes.
- **Highly Flexible:** PaddleDetection provides rich of models, including **250+ pre-trained models** such as **object detection**, **instance segmentation**, **face detection**, **keypoint detection**, **multi-object tracking** and etc, covering a variety of **global competition champion** schemes.
Components are designed to be modular. Model architectures, as well as data preprocess pipelines and optimization strategies, can be easily customized with simple configuration changes.
- **Highly Flexible**
Components are designed to be modular. Model architectures, as well as data preprocess pipelines and optimization strategies, can be easily customized with simple configuration changes.
- **Production Ready**
From data augmentation, constructing models, training, compression, depolyment, get through end to end, and complete support for multi-architecture, multi-device deployment for **cloud and edge device**.
- **Production Ready:** - **High Performance**
From data augmentation, constructing models, training, compression, depolyment, get through end to end, and complete support for multi-architecture, multi-device deployment for **cloud and edge device**.
- **High Performance:** Based on the high performance core of PaddlePaddle, advantages of training speed and memory occupation are obvious. FP16 training and multi-machine training are supported as well.
Based on the high performance core of PaddlePaddle, advantages of training speed and memory occupation are obvious. FP16 training and multi-machine training are supported as well.
#### Overview of Kit Structures ## <img title="" src="https://user-images.githubusercontent.com/48054808/157800467-2a9946ad-30d1-49a9-b9db-ba33413d9c90.png" alt="" width="20"> Community
- If you have any problem or suggestion on PaddleDetection, please send us issues through [GitHub Issues](https://github.com/PaddlePaddle/PaddleDetection/issues).
- Welcome to Join PaddleDetection QQ Group and Wechat Group (reply "Det").
<div align="center">
<img src="https://user-images.githubusercontent.com/48054808/157800129-2f9a0b72-6bb8-4b10-8310-93ab1639253f.jpg" width = "200" />
<img src="https://user-images.githubusercontent.com/48054808/160531099-9811bbe6-cfbb-47d5-8bdb-c2b40684d7dd.png" width = "200" />
</div>
## <img src="https://user-images.githubusercontent.com/48054808/157827140-03ffaff7-7d14-48b4-9440-c38986ea378c.png" width="20"/> Overview of Kit Structures
<table align="center"> <table align="center">
<tbody> <tbody>
...@@ -181,44 +221,43 @@ Based on the high performance core of PaddlePaddle, advantages of training speed ...@@ -181,44 +221,43 @@ Based on the high performance core of PaddlePaddle, advantages of training speed
</td> </td>
</tr> </tr>
</td> </td>
</tr> </tr>
</tbody> </tbody>
</table> </table>
#### Overview of Model Performance ## <img src="https://user-images.githubusercontent.com/48054808/157801371-9a9a8c65-1690-4123-985a-e0559a7f9494.png" width="20"/> Overview of Model Performance
The relationship between COCO mAP and FPS on Tesla V100 of representative models of each server side architectures and backbones. The relationship between COCO mAP and FPS on Tesla V100 of representative models of each server side architectures and backbones.
<div align="center"> <div align="center">
<img src="docs/images/fps_map.png" /> <img src="docs/images/fps_map.png" />
</div> </div>
**NOTE:** **NOTE:**
- `CBResNet stands` for `Cascade-Faster-RCNN-CBResNet200vd-FPN`, which has highest mAP on COCO as 53.3% - `CBResNet stands` for `Cascade-Faster-RCNN-CBResNet200vd-FPN`, which has highest mAP on COCO as 53.3%
- `Cascade-Faster-RCNN` stands for `Cascade-Faster-RCNN-ResNet50vd-DCN`, which has been optimized to 20 FPS inference speed when COCO mAP as 47.8% in PaddleDetection models - `Cascade-Faster-RCNN` stands for `Cascade-Faster-RCNN-ResNet50vd-DCN`, which has been optimized to 20 FPS inference speed when COCO mAP as 47.8% in PaddleDetection models
- `PP-YOLO` achieves mAP of 45.9% on COCO and 72.9FPS on Tesla V100. Both precision and speed surpass [YOLOv4](https://arxiv.org/abs/2004.10934) - `PP-YOLO` achieves mAP of 45.9% on COCO and 72.9FPS on Tesla V100. Both precision and speed surpass [YOLOv4](https://arxiv.org/abs/2004.10934)
- `PP-YOLO v2` is optimized version of `PP-YOLO` which has mAP of 49.5% and 68.9FPS on Tesla V100 - `PP-YOLO v2` is optimized version of `PP-YOLO` which has mAP of 49.5% and 68.9FPS on Tesla V100
- All these models can be get in [Model Zoo](#ModelZoo) - All these models can be get in [Model Zoo](#ModelZoo)
The relationship between COCO mAP and FPS on Qualcomm Snapdragon 865 of representative mobile side models. The relationship between COCO mAP and FPS on Qualcomm Snapdragon 865 of representative mobile side models.
<div align="center"> <div align="center">
<img src="docs/images/mobile_fps_map.png" width=600 /> <img src="docs/images/mobile_fps_map.png" width=600/>
</div> </div>
**NOTE:** **NOTE:**
- All data tested on Qualcomm Snapdragon 865(4\*A77 + 4\*A55) processor with batch size of 1 and CPU threads of 4, and use NCNN library in testing, benchmark scripts is publiced at [MobileDetBenchmark](https://github.com/JiweiMaster/MobileDetBenchmark) - All data tested on Qualcomm Snapdragon 865(4*A77 + 4*A55) processor with batch size of 1 and CPU threads of 4, and use NCNN library in testing, benchmark scripts is publiced at [MobileDetBenchmark](https://github.com/JiweiMaster/MobileDetBenchmark)
- [PP-PicoDet](configs/picodet) and [PP-YOLO-Tiny](configs/ppyolo) are developed and released by PaddleDetection, other models are not provided in PaddleDetection. - [PP-PicoDet](configs/picodet) and [PP-YOLO-Tiny](configs/ppyolo) are developed and released by PaddleDetection, other models are not provided in PaddleDetection.
## Tutorials ## <img src="https://user-images.githubusercontent.com/48054808/157828296-d5eb0ccb-23ea-40f5-9957-29853d7d13a9.png" width="20"/> Tutorials
### Get Started ### Get Started
...@@ -226,17 +265,19 @@ The relationship between COCO mAP and FPS on Qualcomm Snapdragon 865 of represen ...@@ -226,17 +265,19 @@ The relationship between COCO mAP and FPS on Qualcomm Snapdragon 865 of represen
- [Prepare dataset](docs/tutorials/PrepareDataSet_en.md) - [Prepare dataset](docs/tutorials/PrepareDataSet_en.md)
- [Quick start on PaddleDetection](docs/tutorials/GETTING_STARTED.md) - [Quick start on PaddleDetection](docs/tutorials/GETTING_STARTED.md)
### Advanced Tutorials ### Advanced Tutorials
- Parameter configuration - Parameter configuration
- [Parameter configuration for RCNN model](docs/tutorials/config_annotation/faster_rcnn_r50_fpn_1x_coco_annotation_en.md) - [Parameter configuration for RCNN model](docs/tutorials/config_annotation/faster_rcnn_r50_fpn_1x_coco_annotation_en.md)
- [Parameter configuration for PP-YOLO model](docs/tutorials/config_annotation/ppyolo_r50vd_dcn_1x_coco_annotation_en.md) - [Parameter configuration for PP-YOLO model](docs/tutorials/config_annotation/ppyolo_r50vd_dcn_1x_coco_annotation_en.md)
- Model Compression(Based on [PaddleSlim](https://github.com/PaddlePaddle/PaddleSlim)) - Model Compression(Based on [PaddleSlim](https://github.com/PaddlePaddle/PaddleSlim))
- [Prune/Quant/Distill](configs/slim) - [Prune/Quant/Distill](configs/slim)
- Inference and deployment - Inference and deployment
- [Export model for inference](deploy/EXPORT_MODEL_en.md) - [Export model for inference](deploy/EXPORT_MODEL_en.md)
- [Paddle Inference](deploy/README_en.md) - [Paddle Inference](deploy/README_en.md)
- [Python inference](deploy/python) - [Python inference](deploy/python)
...@@ -248,14 +289,15 @@ The relationship between COCO mAP and FPS on Qualcomm Snapdragon 865 of represen ...@@ -248,14 +289,15 @@ The relationship between COCO mAP and FPS on Qualcomm Snapdragon 865 of represen
- [Exporting to ONNX and using OpenVINO for inference](docs/advanced_tutorials/openvino_inference/README.md) - [Exporting to ONNX and using OpenVINO for inference](docs/advanced_tutorials/openvino_inference/README.md)
- Advanced development - Advanced development
- [New data augmentations](docs/advanced_tutorials/READER_en.md)
- [New detection algorithms](docs/advanced_tutorials/MODEL_TECHNICAL_en.md)
- [New data augmentations](docs/advanced_tutorials/READER_en.md)
- [New detection algorithms](docs/advanced_tutorials/MODEL_TECHNICAL.md)
## Model Zoo ## <img src="https://user-images.githubusercontent.com/48054808/157829890-a535b8a6-631c-4c87-b861-64d4b32b2d6a.png" width="20"/> Model Zoo
- Universal object detection - Universal object detection
- [Model library and baselines](docs/MODEL_ZOO_cn.md) - [Model library and baselines](docs/MODEL_ZOO_cn.md)
- [PP-YOLOE](configs/ppyoloe/README_cn.md)
- [PP-YOLO](configs/ppyolo/README.md) - [PP-YOLO](configs/ppyolo/README.md)
- [PP-PicoDet](configs/picodet/README.md) - [PP-PicoDet](configs/picodet/README.md)
- [Enhanced Anchor Free model--TTFNet](configs/ttfnet/README_en.md) - [Enhanced Anchor Free model--TTFNet](configs/ttfnet/README_en.md)
...@@ -281,35 +323,35 @@ The relationship between COCO mAP and FPS on Qualcomm Snapdragon 865 of represen ...@@ -281,35 +323,35 @@ The relationship between COCO mAP and FPS on Qualcomm Snapdragon 865 of represen
- [Face detection](configs/face_detection/README_en.md) - [Face detection](configs/face_detection/README_en.md)
- [Pedestrian detection](configs/pedestrian/README.md) - [Pedestrian detection](configs/pedestrian/README.md)
- [Vehicle detection](configs/vehicle/README.md) - [Vehicle detection](configs/vehicle/README.md)
- [Real-Time Human Analysis Tool PP-Human](deploy/pphuman)
- Competition Plan - Competition Plan
- [Objects365 2019 Challenge champion model](static/docs/featured_model/champion_model/CACascadeRCNN_en.md) - [Objects365 2019 Challenge champion model](static/docs/featured_model/champion_model/CACascadeRCNN_en.md)
- [Best single model of Open Images 2019-Object Detection](static/docs/featured_model/champion_model/OIDV5_BASELINE_MODEL_en.md) - [Best single model of Open Images 2019-Object Detection](static/docs/featured_model/champion_model/OIDV5_BASELINE_MODEL_en.md)
## Applications ## <img title="" src="https://user-images.githubusercontent.com/48054808/157836473-1cf451fa-f01f-4148-ba68-b6d06d5da2f9.png" alt="" width="20"> Applications
- [Christmas portrait automatic generation tool](static/application/christmas) - [Christmas portrait automatic generation tool](static/application/christmas)
- [Android Fitness Demo](https://github.com/zhiboniu/pose_demo_android) - [Android Fitness Demo](https://github.com/zhiboniu/pose_demo_android)
## Updates ## <img src="https://user-images.githubusercontent.com/48054808/157835981-ef6057b4-6347-4768-8fcc-cd07fcc3d8b0.png" width="20"/> Updates
Updates please refer to [change log](docs/CHANGELOG_en.md) for details.
For the details of version update, please refer to [Version Update Doc](docs/CHANGELOG.md).
## License ## <img title="" src="https://user-images.githubusercontent.com/48054808/157835345-f5d24128-abaf-4813-b793-d2e5bdc70e5a.png" alt="" width="20"> License
PaddleDetection is released under the [Apache 2.0 license](LICENSE). PaddleDetection is released under the [Apache 2.0 license](LICENSE).
## <img src="https://user-images.githubusercontent.com/48054808/157835796-08d4ffbc-87d9-4622-89d8-cf11a44260fc.png" width="20"/> Contribution
## Contributing
Contributions are highly welcomed and we would really appreciate your feedback!! Contributions are highly welcomed and we would really appreciate your feedback!!
- Thanks [Mandroide](https://github.com/Mandroide) for cleaning the code and unifying some function interface. - Thanks [Mandroide](https://github.com/Mandroide) for cleaning the code and unifying some function interface.
- Thanks [FL77N](https://github.com/FL77N/) for contributing the code of `Sparse-RCNN` model. - Thanks [FL77N](https://github.com/FL77N/) for contributing the code of `Sparse-RCNN` model.
- Thanks [Chen-Song](https://github.com/Chen-Song) for contributing the code of `Swin Faster-RCNN` model. - Thanks [Chen-Song](https://github.com/Chen-Song) for contributing the code of `Swin Faster-RCNN` model.
- Thanks [yangyudong](https://github.com/yangyudong2020), [hchhtc123](https://github.com/hchhtc123) for contributing PP-Tracking GUI interface. - Thanks [yangyudong](https://github.com/yangyudong2020), [hchhtc123](https://github.com/hchhtc123) for contributing PP-Tracking GUI interface.
- Thanks [Shigure19](https://github.com/Shigure19) for contributing PP-TinyPose fitness APP. - Thanks [Shigure19](https://github.com/Shigure19) for contributing PP-TinyPose fitness APP.
## Citation ## <img src="https://user-images.githubusercontent.com/48054808/157835276-9aab9d1c-1c46-446b-bdd4-5ab75c5cfa48.png" width="20"/> Citation
``` ```
@misc{ppdet2019, @misc{ppdet2019,
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册