+
+ 
+ 
+ 
+ 
+
+
+
+
+
产品动态
- 🔥 **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](configs/ppyoloe)，发布s/m/l/x版本，l版本COCO test2017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)，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。
- 新增[YOLOX](configs/yolox)目标检测模型，支持nano/tiny/s/m/l/x版本，x版本COCO val2017数据集精度51.8%。
- 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。
@@ -59,13 +35,13 @@
- 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)
-
+
- 发布Transformer检测系列模型，包括[DETR](configs/detr), [Deformable DETR](configs/deformable_detr), [Sparse RCNN](configs/sparse_rcnn)。
- 新增Dark HRNet关键点模型和MPII数据集[关键点模型](configs/keypoint)
- 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)
-
+
- 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。
- 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)。
@@ -97,8 +73,8 @@
- 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、微信用户群（添加并回复小助手“检测”）
+
@@ -300,16 +276,16 @@
### 进阶教程
- 参数配置
-
+
- [RCNN参数说明](docs/tutorials/config_annotation/faster_rcnn_r50_fpn_1x_coco_annotation.md)
- [PP-YOLO参数说明](docs/tutorials/config_annotation/ppyolo_r50vd_dcn_1x_coco_annotation.md)
- 模型压缩(基于[PaddleSlim](https://github.com/PaddlePaddle/PaddleSlim))
-
+
- [剪裁/量化/蒸馏教程](configs/slim)
- [推理部署](deploy/README.md)
-
+
- [模型导出教程](deploy/EXPORT_MODEL.md)
- [Paddle Inference部署](deploy/README.md)
- [Python端推理部署](deploy/python)
@@ -320,10 +296,28 @@
- [推理benchmark](deploy/BENCHMARK_INFER.md)
- 进阶开发
-
+
- [数据处理模块](docs/advanced_tutorials/READER.md)
- [新增检测模型](docs/advanced_tutorials/MODEL_TECHNICAL.md)
+### 课程专栏
+
+- **2022.4.19 [产业级目标检测技术与应用](https://aistudio.baidu.com/aistudio/education/group/info/23670)三日课：** 超强目标检测算法矩阵、实时行人分析系统PP-Human、目标检测产业应用全流程拆解与实践
+
+- **2022.3.26 [智慧城市行业](https://aistudio.baidu.com/aistudio/education/group/info/25620)七日课：** 城市规划、城市治理、智慧政务、交通管理、社区治理
+
+### 产业实践范例教程
+
+- [基于PP-PicoDet的通信塔识别及Android端部署](https://aistudio.baidu.com/aistudio/projectdetail/3561097)
+
+- [基于Faster-RCNN的瓷砖表面瑕疵检测](https://aistudio.baidu.com/aistudio/projectdetail/2571419)
+
+- [基于PaddleDetection的PCB瑕疵检测](https://aistudio.baidu.com/aistudio/projectdetail/2367089)
+
+- [基于FairMOT实现人流量统计](https://aistudio.baidu.com/aistudio/projectdetail/2421822)
+
+- [基于YOLOv3实现跌倒检测 ](https://aistudio.baidu.com/aistudio/projectdetail/2500639)
+
## 
模型库
- 通用目标检测:
@@ -346,7 +340,7 @@
- HRNet
- LiteHRNet
- [多目标跟踪](configs/mot/README.md)
- - [PP-Tracking](deploy/pptracking/README.md)
+ - [PP-Tracking](deploy/pptracking/README_cn.md)
- [DeepSORT](configs/mot/deepsort/README_cn.md)
- [JDE](configs/mot/jde/README_cn.md)
- [FairMOT](configs/mot/fairmot/README_cn.md)
@@ -355,7 +349,8 @@
- [行人检测](configs/pedestrian/README.md)
- [车辆检测](configs/vehicle/README.md)
- [人脸检测](configs/face_detection/README.md)
- - [实时行人分析](deploy/pphuman/README.md)
+- 场景化工具
+ - [实时行人分析工具PP-Human](deploy/pphuman/README.md)
- 比赛冠军方案
- [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)
diff --git a/README_en.md b/README_en.md
index b3b8c2baa26d19de2a5f6ff5ac738ed87cb373ff..f30cae8c9dc94d91ea6fed65726de5e8441cd237 100644
--- a/README_en.md
+++ b/README_en.md
@@ -7,17 +7,19 @@ English | [简体中文](README_cn.md)
****A High-Efficient Development Toolkit for Object Detection based on [PaddlePaddle](https://github.com/paddlepaddle/paddle).****
-[](LICENSE)
-[](https://github.com/PaddlePaddle/PaddleDetection/releases)
-
-
+
+
+
+
+
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), supporting s/m/l/x version, achieving mAP as 51.4% on COCO test dataset and 78.1 FPS on Nvidia V100 by PP-YOLOE-l, 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.
@@ -31,7 +33,7 @@ English | [简体中文](README_cn.md)
## 
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 design with configurable modules such as network components, data augmentations and losses. It releases many kinds SOTA industry practice models and integrates abilities of model compression and cross-platform high-performance deployment to help developers in the whole process with a faster and better way.
#### PaddleDetection provides image processing capabilities such as object detection, instance segmentation, multi-object tracking, keypoint detection and etc.
@@ -48,19 +50,19 @@ PaddleDetection is an end-to-end object detection development kit based on Paddl
## 
Features
- **Rich Models**
-
+
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.
- **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**.
- **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.
## 
Community
@@ -68,7 +70,7 @@ PaddleDetection is an end-to-end object detection development kit based on Paddl
- 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").
-
+
@@ -247,7 +249,9 @@ The relationship between COCO mAP and FPS on Tesla V100 of representative 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 v2` is optimized version of `PP-YOLO` which has mAP of 49.5% and 68.9FPS on Tesla V100
+
- `PP-YOLOE` is optimized version of `PP-YOLO v2` which has mAP of 51.4% and 78.1FPS on Tesla V100
+
- 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.
@@ -265,23 +269,23 @@ The relationship between COCO mAP and FPS on Qualcomm Snapdragon 865 of represen
### Get Started
-- [Installation guide](docs/tutorials/INSTALL.md)
-- [Prepare dataset](docs/tutorials/PrepareDataSet_en.md)
-- [Quick start on PaddleDetection](docs/tutorials/GETTING_STARTED.md)
+- [Installation Guide](docs/tutorials/INSTALL.md)
+- [Prepare Dataset](docs/tutorials/PrepareDataSet_en.md)
+- [Quick Start on PaddleDetection](docs/tutorials/GETTING_STARTED.md)
### 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 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))
-
+
- [Prune/Quant/Distill](configs/slim)
-- Inference and deployment
-
+- Inference and Deployment
+
- [Export model for inference](deploy/EXPORT_MODEL_en.md)
- [Paddle Inference](deploy/README_en.md)
- [Python inference](deploy/python)
@@ -292,14 +296,14 @@ The relationship between COCO mAP and FPS on Qualcomm Snapdragon 865 of represen
- [Inference benchmark](deploy/BENCHMARK_INFER_en.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.md)
## Model Zoo
-- Universal object detection
+- General Object Detection
- [Model library and baselines](docs/MODEL_ZOO_cn.md)
- [PP-YOLOE](configs/ppyoloe/README_cn.md)
- [PP-YOLO](configs/ppyolo/README.md)
@@ -309,27 +313,28 @@ The relationship between COCO mAP and FPS on Qualcomm Snapdragon 865 of represen
- [676 classes of object detection](static/docs/featured_model/LARGE_SCALE_DET_MODEL_en.md)
- [Two-stage practical PSS-Det](configs/rcnn_enhance/README_en.md)
- [SSLD pretrained models](docs/feature_models/SSLD_PRETRAINED_MODEL_en.md)
-- Universal instance segmentation
+- General Instance Segmentation
- [SOLOv2](configs/solov2/README.md)
-- Rotation object detection
+- Rotated Object Detection
- [S2ANet](configs/dota/README_en.md)
-- [Keypoint detection](configs/keypoint)
+- [Keypoint Detection](configs/keypoint)
- [PP-TinyPose](configs/keypoint/tiny_pose)
- HigherHRNet
- HRNet
- LiteHRNet
- [Multi-Object Tracking](configs/mot/README.md)
- - [PP-Tracking](deploy/pptracking/README.md)
+ - [PP-Tracking](deploy/pptracking/README_en.md)
- [DeepSORT](configs/mot/deepsort/README.md)
- [JDE](configs/mot/jde/README.md)
- [FairMOT](configs/mot/fairmot/README.md)
- [ByteTrack](configs/mot/bytetrack/README.md)
-- Vertical field
+- Practical Specific Models
- [Face detection](configs/face_detection/README_en.md)
- [Pedestrian detection](configs/pedestrian/README.md)
- [Vehicle detection](configs/vehicle/README.md)
+- Scienario Solution
- [Real-Time Human Analysis Tool PP-Human](deploy/pphuman)
-- Competition Plan
+- Competition Solution
- [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)