Created by: trollhe

版本信息:

python3.7
PaddlePaddle 1.8.0
gpu环境

在aistudio中，运行如下命令训练

# 准备数据集
!python dataset/fruit/download_fruit.py

# 训练模型
!python -u tools/train.py -c configs/yolov3_mobilenet_v1_fruit.yml

报错信息如下:

2020-08-11 11:38:03,638-WARNING: paddle.fluid.layers.matrix_nms OP not found, maybe a newer version of paddle is required.
Traceback (most recent call last):
  File "tools/train.py", line 368, in <module>
    main()
  File "tools/train.py", line 114, in main
    train_fetches = model.train(feed_vars)
  File "/home/aistudio/work/det/ppdet/modeling/architectures/yolo.py", line 159, in train
    return self.build(feed_vars, mode='train')
  File "/home/aistudio/work/det/ppdet/modeling/architectures/yolo.py", line 85, in build
    gt_score, targets)
  File "/home/aistudio/work/det/ppdet/modeling/anchor_heads/yolo_head.py", line 401, in get_loss
    self.prefix_name)
  File "/home/aistudio/work/det/ppdet/modeling/losses/yolo_loss.py", line 88, in __call__
    name=prefix_name + "yolo_loss" + str(i))
TypeError: yolov3_loss() got an unexpected keyword argument 'scale_x_y'

看了没有关于这方面的报错解决方法，烦请帮忙处理下。