fishfsr的模型结构问题

Question

fishfsr的模型结构问题

Closed this issue 7 months ago · 6 comments

您好，在运行fsr文件夹中main_parsing.py文件时，遇到下列问题：
TypeError: conv2d() received an invalid combination of arguments - got (Tensor, Parameter, Parameter, tuple, tuple, tuple, int), but expected one of:

(Tensor input, Tensor weight, Tensor bias, tuple of ints stride, tuple of ints padding, tuple of ints dilation, int groups)
didn't match because some of the arguments have invalid types: (Tensor, Parameter, Parameter, tuple, tuple, tuple, int)
(Tensor input, Tensor weight, Tensor bias, tuple of ints stride, str padding, tuple of ints dilation, int groups)
didn't match because some of the arguments have invalid types: (Tensor, Parameter, Parameter, tuple, tuple, tuple, int)
请问是net结构的问题吗？应该怎么解决？期盼您的回复，感谢！

Answer 1 · 2024-01-22T11:51:20.000Z

您好，代码已经更新，应该不会再有这个问题了。

Answer 2 · 2024-01-23T01:03:56.000Z

好的，非常感谢

Answer 3 · 2024-01-23T08:23:51.000Z

您好，对于fishfsrnet，我在训练时速度很慢，请问一下你们在celeba数据集上训练多少个epoch呀？

Answer 4 · 2024-03-06T02:52:56.000Z

不好意思，刚看到您的问题，具体训练多少个epoch有点记不太清了。

Answer 5 · 2024-03-06T07:16:12.000Z

您好，刚找了一下原来的代码，大概是跑了50个epoch。

Answer 6 · 2024-03-06T07:17:43.000Z

好的好的，非常感谢