[cherry-pick] fix ppyoloe amp bug, add reduce_mean to custom_black_list (#6797)

configs/ppyoloe/README.md

@@ -78,12 +78,12 @@ The PaddleDetection team provides configs and weights of various feature detecti
 Training PP-YOLOE+ on 8 GPUs with following command
 
 ```bash
-python -m paddle.distributed.launch --gpus 0,1,2,3,4,5,6,7 tools/train.py -c configs/ppyoloe/ppyoloe_plus_crn_l_80e_coco.yml
+python -m paddle.distributed.launch --gpus 0,1,2,3,4,5,6,7 tools/train.py -c configs/ppyoloe/ppyoloe_plus_crn_l_80e_coco.yml --eval --amp
 ```
 
 **Notes:**
-- use `--amp` to train with default config to avoid out of memeory.
 - If you need to evaluate while training, please add `--eval`.
+- PP-YOLOE+ supports mixed precision training, please add `--amp`.
 - PaddleDetection supports multi-machine distribued training, you can refer to [DistributedTraining tutorial](../../docs/DistributedTraining_en.md).
 
 

configs/ppyoloe/README_cn.md

@@ -78,10 +78,11 @@ PaddleDetection团队提供了基于PP-YOLOE的各种垂类检测模型的配置
 请执行以下指令训练PP-YOLOE+
 
 ```bash
-python -m paddle.distributed.launch --gpus 0,1,2,3,4,5,6,7 tools/train.py -c configs/ppyoloe/ppyoloe_plus_crn_l_80e_coco.yml
+python -m paddle.distributed.launch --gpus 0,1,2,3,4,5,6,7 tools/train.py -c configs/ppyoloe/ppyoloe_plus_crn_l_80e_coco.yml --eval --amp
 ```
 **注意:**
 - 如果需要边训练边评估，请添加`--eval`.
+- PP-YOLOE+支持混合精度训练，请添加`--amp`.
 - PaddleDetection支持多机训练，可以参考[多机训练教程](../../docs/DistributedTraining_cn.md).
 
 ### 评估

configs/ppyoloe/_base_/ppyoloe_crn.yml

@@ -2,6 +2,7 @@ architecture: YOLOv3
 norm_type: sync_bn
 use_ema: true
 ema_decay: 0.9998
+custom_black_list: ['reduce_mean']
 
 YOLOv3:
   backbone: CSPResNet

configs/ppyoloe/_base_/ppyoloe_plus_crn.yml

@@ -2,6 +2,7 @@ architecture: YOLOv3
 norm_type: sync_bn
 use_ema: true
 ema_decay: 0.9998
+custom_black_list: ['reduce_mean']
 
 YOLOv3:
   backbone: CSPResNet