MPR_Net Deblurring 训练模型报错

[monkeycc]

https://github.com/PaddlePaddle/PaddleGAN/blob/develop/docs/zh_CN/tutorials/mpr_net.md#21-%E6%95%B0%E6%8D%AE%E5%87%86%E5%A4%87

python -u tools/main.py --config-file configs/mprnet_deblurring.yaml

GoPro
├── train
│   ├── input
│   └── target
└── test
    ├── input
    └── target

W1003 16:21:28.178328 16476 gpu_resources.cc:119] Please NOTE: device: 0, GPU Compute Capability: 8.6, Driver API Version: 12.2, Runtime API Version: 11.7
W1003 16:21:28.181943 16476 gpu_resources.cc:149] device: 0, cuDNN Version: 8.4.
Traceback (most recent call last):
  File "e:\2023_code_web\paddlegan-develop\ppgan\engine\trainer.py", line 52, in __next__
    data = next(self.iter_loader)
  File "E:\anaconda3\envs\PaddleGan\lib\site-packages\paddle\io\dataloader\dataloader_iter.py", line 291, in __next__
    self._reader.read_next_list()[0]
StopIteration

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "tools/main.py", line 56, in <module>
    main(args, cfg)
  File "tools/main.py", line 46, in main
    trainer.train()
  File "e:\2023_code_web\paddlegan-develop\ppgan\engine\trainer.py", line 224, in train
    data = next(iter_loader)
  File "e:\2023_code_web\paddlegan-develop\ppgan\engine\trainer.py", line 56, in __next__
    data = next(self.iter_loader)
  File "E:\anaconda3\envs\PaddleGan\lib\site-packages\paddle\io\dataloader\dataloader_iter.py", line 291, in __next__
    self._reader.read_next_list()[0]
StopIteration

[JunnYu]

你好，发现你的系统是windows（windows下数据读取的num_workers不能>0）。建议在linux系统下进行上述内容，或者前往aistudio上进行训练。https://github.com/PaddlePaddle/PaddleGAN/blob/21ee373c2a9481231f50b32e0753d3f543a86396/configs/mprnet_deblurring.yaml#L22C5-L22C16