未验证 提交 0ecc2c98 编写于 作者: K Kaipeng Deng 提交者: GitHub

Update changlog and version for release 2.4 (#5486)

* update version and changelog for release/2.4
上级 cd08a245
README_en.md
\ No newline at end of file
README_cn.md
\ No newline at end of file
......@@ -4,6 +4,34 @@
## 最新版本信息
### 2.4(03.24/2022)
- PP-YOLOE:
- 发布PP-YOLOE特色模型,COCO数据集精度51.4%,V100预测速度78.1 FPS,精度速度服务器端SOTA
- 发布s/m/l/x系列模型,打通TensorRT、ONNX部署能力
- 支持混合精度训练,训练较PP-YOLOv2加速33%
- PP-PicoDet:
- 发布PP-PicoDet优化模型,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
- 后处理集成到网络中,优化端到端部署成本
- 行人分析Pipeline:
- 发布PP-Human行人分析Pipeline,覆盖行人检测、属性识别、行人跟踪、跨镜跟踪、人流量统计、动作识别多种功能,打通TensorRT部署
- 属性识别支持StrongBaseline模型
- ReID支持Centroid模型
- 动作识别支持ST-GCN摔倒检测
- 框架功能优化:
- 支持混合精度训练,通过`–amp`开启
- EMA训练速度优化20%,优化EMA训练模型保存方式
- 支持infer预测结果保存为COCO格式
- 部署优化:
- RCNN全系列模型支持Paddle2ONNX导出ONNX模型
- SSD模型支持导出时融合解码OP,优化边缘端部署速度
- 支持NMS导出TensorRT,TensorRT部署端到端速度提升
### 2.3(11.03/2021)
- 特色模型:
......
......@@ -4,6 +4,34 @@ English | [简体中文](./CHANGELOG.md)
## Last Version Information
### 2.4(03.24/2022)
- PP-YOLOE:
- Release PP-YOLOE object detection models, achieve mAP as 51.4% on COCO test dataset and 78.1 FPS on Nvidia V100, reach SOTA performance for object detection on GPU``
- Release series models: s/m/l/x, and support deployment base on TensorRT & ONNX
- Spport AMP training and training speed is 33% faster than PP-YOLOv2
- PP-PicoDet:
- Release enhanced models of PP-PicoDet, mAP promoted ~2% on COCO and inference speed accelerated 63% on CPU
- Release PP-PicoDet-XS model with 0.7M parameters
- Post-processing integrated into the network to optimize deployment pipeline
- PP-Human:
- Release PP-Human human analysis pipeline,including pedestrian detection, attribute recognition, human tracking, multi-camera tracking, human statistics, action recognition. Supporting deployment with TensorRT
- Release StrongBaseline model for attribute recognition
- Release Centroid model for ReID
- Release ST-GCN model for falldown action recognition
- Function Optimize:
- Support AMP training, enable with `--amp`
- Optimize 20% training speed when training with EMA, improve saving method of EMA weights
- Support saving inference results in COCO format
- Deployment Optimize:
- Support export ONNX model by Paddle2ONNX for all RCNN models
- Supoort export model with fused decode OP for SSD models to enhance inference speed in edge side
- Support export NMS to TensorRT model, optmize inference speed on TensorRT
### 2.3(11.03/2021)
- Feature models:
......
......@@ -21,7 +21,7 @@ from setuptools import find_packages, setup
# ============== version definition ==============
PPDET_VERSION = "2.3.0"
PPDET_VERSION = "2.4.0"
def parse_version():
......
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