add bias test doc for yolo ppyolo pafnet(#2675)

configs/ppyolo/README.md

@@ -132,7 +132,27 @@ CUDA_VISIBLE_DEVICES=0 python tools/eval.py -c configs/ppyolo/ppyolo_test.yml -o
 
 Evaluation results will be saved in `bbox.json`, compress it into a `zip` package and upload to [COCO dataset evaluation](https://competitions.codalab.org/competitions/20794#participate) to evaluate.
 
-**NOTE:** `configs/ppyolo/ppyolo_test.yml` is only used for evaluation on COCO test-dev2017 dataset, could not be used for training or COCO val2017 dataset evaluating.
+**NOTE 1:** `configs/ppyolo/ppyolo_test.yml` is only used for evaluation on COCO test-dev2017 dataset, could not be used for training or COCO val2017 dataset evaluating.
+
+**NOTE 2:** Due to the overall upgrade of the dynamic graph framework, the following weight models published by paddledetection need to be evaluated by adding the -- bias field, such as
+
+```bash
+# use weights released in PaddleDetection model zoo
+CUDA_VISIBLE_DEVICES=0 python tools/eval.py -c configs/ppyolo/ppyolo_r50vd_dcn_1x_coco.yml -o weights=https://paddledet.bj.bcebos.com/models/ppyolo_r50vd_dcn_1x_coco.pdparams --bias
+```
+These models are:
+
+1.ppyolo_r50vd_dcn_1x_coco
+
+2.ppyolo_r50vd_dcn_voc
+
+3.ppyolo_r18vd_coco
+
+4.ppyolo_mbv3_large_coco
+
+5.ppyolo_mbv3_small_coco
+
+6.ppyolo_tiny_650e_coco
 
 ### 3. Inference
 

configs/ppyolo/README_cn.md

@@ -116,7 +116,27 @@ CUDA_VISIBLE_DEVICES=0 python tools/eval.py -c configs/ppyolo/ppyolo_test.yml -o
 
 评估结果保存于`bbox.json`中，将其压缩为zip包后通过[COCO数据集评估页](https://competitions.codalab.org/competitions/20794#participate)提交评估。
 
-**注意:** `configs/ppyolo/ppyolo_test.yml`仅用于评估COCO test-dev数据集，不用于训练和评估COCO val2017数据集。
+**注意1:** `configs/ppyolo/ppyolo_test.yml`仅用于评估COCO test-dev数据集，不用于训练和评估COCO val2017数据集。
+
+**注意2:** 由于动态图框架整体升级，以下几个PaddleDetection发布的权重模型评估时需要添加--bias字段, 例如
+
+```bash
+# 使用PaddleDetection发布的权重
+CUDA_VISIBLE_DEVICES=0 python tools/eval.py -c configs/ppyolo/ppyolo_r50vd_dcn_1x_coco.yml -o weights=https://paddledet.bj.bcebos.com/models/ppyolo_r50vd_dcn_1x_coco.pdparams --bias
+```
+主要有:
+
+1.ppyolo_r50vd_dcn_1x_coco
+
+2.ppyolo_r50vd_dcn_voc
+
+3.ppyolo_r18vd_coco
+
+4.ppyolo_mbv3_large_coco
+
+5.ppyolo_mbv3_small_coco
+
+6.ppyolo_tiny_650e_coco
 
 ### 3. 推理
 

configs/ttfnet/README.md

@@ -40,7 +40,7 @@ PAFNet系列模型从如下方面优化TTFNet模型：
 
 | 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 |
 | :-------------- | :------------- | :-----: | :-----: | :------------: | :-----: | :-----------------------------------------------------: | :-----: |
-| ResNet50vd   | PAFNet           |    18    |   10x      |     ----     |  42.2  | [下载链接](https://paddledet.bj.bcebos.com/models/pafnet_10x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/ttfnet/pafnet_10x_coco.yml) |
+| ResNet50vd   | PAFNet           |    18    |   10x      |     ----     |  39.8  | [下载链接](https://paddledet.bj.bcebos.com/models/pafnet_10x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/ttfnet/pafnet_10x_coco.yml) |
 
 
 
@@ -50,7 +50,12 @@ PAFNet系列模型从如下方面优化TTFNet模型：
 | :-------------- | :------------- | :-----: | :-----: | :-----: | :------------: | :-----: | :-----------------------------------------------------: | :-----: |
 | MobileNetv3   |  PAFNet-Lite          |    12    |   20x     |     23.9    |  26.00   | 14 | [下载链接](https://paddledet.bj.bcebos.com/models/pafnet_lite_mobilenet_v3_20x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/ttfnet/pafnet_lite_mobilenet_v3_20x_coco.yml) |
 
+**注意：** 由于动态图框架整体升级，PAFNet的PaddleDetection发布的权重模型评估时需要添加--bias字段, 例如
 
+```bash
+# 使用PaddleDetection发布的权重
+CUDA_VISIBLE_DEVICES=0 python tools/eval.py -c configs/ppyolo/pafnet_10x_coco.yml -o weights=https://paddledet.bj.bcebos.com/models/pafnet_10x_coco.pdparams --bias
+```
 
 ## Citations
 ```

configs/yolov3/README.md

@@ -45,8 +45,17 @@
 | MobileNet-V3-SSLD | 416  |    8    |   270e  |      -        |  79.2  | [下载链接](https://paddledet.bj.bcebos.com/models/yolov3_mobilenet_v3_large_ssld_270e_voc.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/yolov3/yolov3_mobilenet_v3_large_ssld_270e_voc.yml) |
 | MobileNet-V3-SSLD | 320  |    8    |   270e  |      -        |  77.3  | [下载链接](https://paddledet.bj.bcebos.com/models/yolov3_mobilenet_v3_large_ssld_270e_voc.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/yolov3/yolov3_mobilenet_v3_large_ssld_270e_voc.yml) |
 
-**注意：** YOLOv3均使用8GPU训练，训练270个epoch
+**注意：** YOLOv3均使用8GPU训练，训练270个epoch。由于动态图框架整体升级，以下几个PaddleDetection发布的权重模型评估时需要添加--bias字段, 例如
 
+```bash
+# 使用PaddleDetection发布的权重
+CUDA_VISIBLE_DEVICES=0 python tools/eval.py -c configs/ppyolo/yolov3_darknet53_270e_coco.yml -o weights=https://paddledet.bj.bcebos.com/models/yolov3_darknet53_270e_coco.pdparams --bias
+```
+主要有:
+
+1.yolov3_darknet53_270e_coco
+
+2.yolov3_r50vd_dcn_270e_coco
 
 ## Citations
 ```