Cherry pick update dev doc (#2711)

* update doc on develop, test=document_fix

* update dependency of ppdet and paddle, test=document_fix

* update docs, test=document_fix

README_cn.md

@@ -219,7 +219,8 @@ PaddleDetection模块化地实现了多种主流目标检测算法，提供了
     - [PP-YOLO模型](configs/ppyolo/README_cn.md)
     - [676类目标检测](static/docs/featured_model/LARGE_SCALE_DET_MODEL.md)
     - [两阶段实用模型PSS-Det](configs/rcnn_enhance/README.md)
-    - [TTFNet](configs/ttfnet/README.md)
+    - [增强版Anchor Free模型TTFNet](configs/ttfnet/README.md)
+    - [半监督知识蒸馏预训练检测模型](docs/feature_models/SSLD_PRETRAINED_MODEL.md)
 - 通用实例分割
     - [SOLOv2](configs/solov2/README.md)
 - 旋转框检测

README_en.md

@@ -232,7 +232,8 @@ The relationship between COCO mAP and FPS on Tesla V100 of representative models
   - [PP-YOLO](configs/ppyolo/README.md)
   - [676 classes of object detection](static/docs/featured_model/LARGE_SCALE_DET_MODEL.md)
   - [Two-stage practical PSS-Det](configs/rcnn_enhance/README.md)
-  - [TTFNet](configs/ttfnet/README.md)
+  - [Enhanced Anchor Free model--TTFNet](configs/ttfnet/README.md)
+  - [SSLD pretrained models](docs/feature_models/SSLD_PRETRAINED_MODEL_en.md)
 - Universal instance segmentation
   - [SOLOv2](configs/solov2/README.md)
 - Rotation object detection

configs/fcos/README.md

@@ -10,11 +10,12 @@ FCOS (Fully Convolutional One-Stage Object Detection) is a fast anchor-free obje
 
 ## Model Zoo
 
-| 骨架网络        | 网络类型       | 每张GPU图片个数 | 学习率策略 |推理时间(fps) | Box AP |                           下载                          | 配置文件 |
+| Backbone        | Model      | images/GPU | lr schedule |FPS | Box AP |                           download                          | config |
 | :-------------- | :------------- | :-----: | :-----: | :------------: | :-----: | :-----------------------------------------------------: | :-----: |
-| ResNet50-FPN    | FCOS           |    2    |   1x      |     ----     |  39.6  | [下载链接](https://paddledet.bj.bcebos.com/models/fcos_r50_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.0/configs/fcos/fcos_r50_fpn_1x_coco.yml) |
-| ResNet50-FPN    | FCOS+DCN       |    2    |   1x      |     ----     |  44.3  | [下载链接](https://paddledet.bj.bcebos.com/models/fcos_dcn_r50_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.0/configs/fcos/fcos_dcn_r50_fpn_1x_coco.yml) |
-| ResNet50-FPN    | FCOS+multiscale_train    |    2    |   2x      |     ----     |  41.8  | [下载链接](https://paddledet.bj.bcebos.com/models/fcos_r50_fpn_multiscale_2x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.0/configs/fcos/fcos_r50_fpn_multiscale_2x_coco.yml) |
+| ResNet50-FPN    | FCOS           |    2    |   1x      |     ----     |  39.6  | [download](https://paddledet.bj.bcebos.com/models/fcos_r50_fpn_1x_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.0/configs/fcos/fcos_r50_fpn_1x_coco.yml) |
+| ResNet50-FPN    | FCOS+DCN       |    2    |   1x      |     ----     |  44.3  | [download](https://paddledet.bj.bcebos.com/models/fcos_dcn_r50_fpn_1x_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.0/configs/fcos/fcos_dcn_r50_fpn_1x_coco.yml) |
+| ResNet50-FPN    | FCOS+multiscale_train    |    2    |   2x      |     ----     |  41.8  | [download](https://paddledet.bj.bcebos.com/models/fcos_r50_fpn_multiscale_2x_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.0/configs/fcos/fcos_r50_fpn_multiscale_2x_coco.yml) |
+
 **Notes:**
 
 - FCOS is trained on COCO train2017 dataset and evaluated on val2017 results of `mAP(IoU=0.5:0.95)`.

docs/tutorials/INSTALL.md

@@ -17,6 +17,17 @@ For general information about PaddleDetection, please see [README.md](https://gi
 - cuDNN >= 7.6
 
 
+Dependency of PaddleDetection and PaddlePaddle:
+
+| PaddleDetection version | PaddlePaddle version  |    tips    |
+| :----------------: | :---------------: | :-------: |
+|    release/2.0       |       >= 2.0.1    |     Dygraph mode is set as default    |
+|    release/2.0-rc    |       >= 2.0.1    |     --    |
+|    release/0.5       |       >= 1.8.4    |  Cascade R-CNN and SOLOv2 depends on 2.0.0.rc |
+|    release/0.4       |       >= 1.8.4    |  PP-YOLO depends on 1.8.4 |
+|    release/0.3       |        >=1.7      |     --    |
+
+
 ## Instruction
 
 ### 1. Install PaddlePaddle

docs/tutorials/INSTALL_cn.md

@@ -16,6 +16,15 @@
 - CUDA >= 9.0
 - cuDNN >= 7.6
 
+PaddleDetection 依赖 PaddlePaddle 版本关系：
+
+|  PaddleDetection版本  | PaddlePaddle版本  |    备注    |
+| :------------------: | :---------------: | :-------: |
+|    release/2.0       |       >= 2.0.1    |     默认使用动态图模式    |
+|    release/2.0-rc    |       >= 2.0.1    |     --    |
+|    release/0.5       |       >= 1.8.4    |  大部分模型>=1.8.4即可运行，Cascade R-CNN系列模型与SOLOv2依赖2.0.0.rc版本 |
+|    release/0.4       |       >= 1.8.4    |  PP-YOLO依赖1.8.4 |
+|    release/0.3       |        >=1.7      |     --    |
 
 ## 安装说明
 

tools/infer.py

@@ -68,7 +68,7 @@ def parse_args():
         "--use_vdl",
         type=bool,
         default=False,
-        help="whether to record the data to VisualDL.")
+        help="Whether to record the data to VisualDL.")
     parser.add_argument(
         '--vdl_log_dir',
         type=str,
@@ -78,7 +78,7 @@ def parse_args():
         "--save_txt",
         type=bool,
         default=False,
-        help="whether to record the data to VisualDL.")
+        help="Whether to save inference result in txt.")
     args = parser.parse_args()
     return args