[cherry pick] add changelog (#3934)

* add changelog

README_cn.md

@@ -263,6 +263,8 @@ PaddleDetection模块化地实现了多种主流目标检测算法，提供了
 
 ## 版本更新
 
+v2.2版本已经在`08/2021`发布，全新发布Transformer检测系列模型，新增关键点检测Dark HRNet模型，新增人头、车辆跟踪垂类模型，发布旋转框检测S2ANet优化模型，主流模型支持batch size > 1预测部署，详细内容请参考[版本更新文档](docs/CHANGELOG.md)
+
 v2.1版本已经在`05/2021`发布，全新发布关键点检测和多目标跟踪能力，支持无标注框检测，发布PPYOLO系列模型压缩模型，新增ONNX模型导出教程，详细内容请参考[版本更新文档](docs/CHANGELOG.md)。
 
 v2.0版本已经在`04/2021`发布，全面支持动态图版本，新增支持BlazeFace, PSSDet等系列模型和大量骨干网络，发布PP-YOLO v2, PP-YOLO tiny和旋转框检测S2ANet模型。支持模型蒸馏、VisualDL，新增动态图预测部署benchmark，详细内容请参考[版本更新文档](docs/CHANGELOG.md)。

README_en.md

@@ -269,6 +269,8 @@ The relationship between COCO mAP and FPS on Tesla V100 of representative models
 
 ## Updates
 
+v2.2 was released at `08/2021`, release Transformer detection models, release Dark HRNet keypoint detection model, release tracking models of head and vehicle, release optimized S2ANet model, inference with batch size > 1 supported for main architectures. Please refer to [change log](docs/CHANGELOG.md) for details.
+
 v2.1 was released at `05/2021`, Release Keypoint Detection and Multi-Object Tracking. Release model compression for PPYOLO series. Update documents such as export ONNX model. Please refer to [change log](docs/CHANGELOG.md) for details.
 
 v2.0 was released at `04/2021`, fully support dygraph version, which add BlazeFace, PSS-Det and plenty backbones, release `PP-YOLOv2`, `PP-YOLO tiny` and `S2ANet`, support model distillation and VisualDL, add inference benchmark, etc. Please refer to [change log](docs/CHANGELOG.md) for details.

docs/CHANGELOG.md

@@ -2,6 +2,32 @@
 
 ## 最新版本信息
 
+### 2.2(08.10/2021)
+
+- 模型丰富度：
+    - 发布Transformer检测模型：DETR、Deformable DETR、Sparse RCNN
+    - 关键点检测新增Dark模型，发布Dark HRNet模型
+    - 发布MPII数据集HRNet关键点检测模型
+    - 发布人头、车辆跟踪垂类模型
+
+- 模型优化：
+    - 旋转框检测模型S2ANet发布Align Conv优化模型，DOTA数据集mAP优化至74.0
+
+- 预测部署
+    - 主流模型支持batch size>1预测部署，包含YOLOv3，PP-YOLO，Faster RCNN，SSD，TTFNet，FCOS
+    - 新增多目标跟踪模型(JDE, FairMot, DeepSort) Python端预测部署支持，并支持TensorRT预测
+    - 新增多目标跟踪模型FairMot联合关键点检测模型部署Python端预测部署支持
+    - 新增关键点检测模型联合PP-YOLO预测部署支持
+
+- 文档：
+    - Windows预测部署文档新增TensorRT版本说明
+    - FAQ文档更新发布
+
+- 问题修复：
+    - 修复PP-YOLO系列模型训练收敛性问题
+    - 修复batch size>1时无标签数据训练问题
+
+
 ### 2.1(05.20/2021)
 - 模型丰富度提升：
     - 发布关键点模型HRNet，HigherHRNet

setup.py

@@ -19,10 +19,10 @@ import shutil
 import subprocess
 from setuptools import find_packages, setup
 
-
 # ==============  version definition  ==============
 
-PPDET_VERSION = "2.1.0"
+PPDET_VERSION = "2.2.0"
+
 
 def parse_version():
     return PPDET_VERSION.replace('-', '')
@@ -31,8 +31,9 @@ def parse_version():
 def git_commit():
     try:
         cmd = ['git', 'rev-parse', 'HEAD']
-        git_commit = subprocess.Popen(cmd, stdout = subprocess.PIPE,
-            ).communicate()[0].strip()
+        git_commit = subprocess.Popen(
+            cmd,
+            stdout=subprocess.PIPE, ).communicate()[0].strip()
         git_commit = git_commit.decode()
     except:
         git_commit = 'Unknown'
@@ -49,9 +50,8 @@ commit          = '%(commit)s'
 
     _git_commit = git_commit()
     with open(filename, 'w') as f:
-        f.write(ver_str % {
-            'version': PPDET_VERSION,
-            'commit': _git_commit})
+        f.write(ver_str % {'version': PPDET_VERSION, 'commit': _git_commit})
+
 
 write_version_py()