【论文复现】clear_gradients() 报错 TypeError: 'NoneType' object is not iterable

[Ryan906k9]

Traceback (most recent call last):
  File "main.py", line 94, in <module>
    main()
  File "main.py", line 86, in main
    gan.train()
  File "/home/aistudio/UGATIT.py", line 338, in train
    self.D_optim.clear_gradients()
  File "</opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/decorator.py:decorator-gen-59>", line 2, in clear_gradients
  File "/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/fluid/wrapped_decorator.py", line 25, in __impl__
    return wrapped_func(*args, **kwargs)
  File "/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/fluid/framework.py", line 216, in __impl__
    return func(*args, **kwargs)
  File "/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/fluid/optimizer.py", line 791, in clear_gradients
    for p in self._parameter_list:
TypeError: 'NoneType' object is not iterable

请问这个报错可能是什么导致的？

[wangchaochaohu]

如果调用clear_gradients只能在动态图下进行调用 这边把代码贴出来吗

[Ryan906k9]

可能是缩进问题，已经修复