fishfsr的模型结构问题
Closed this issue · 6 comments
lalagui commented
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!
wcy-cs commented
您好,代码已经更新,应该不会再有这个问题了。
lalagui commented
好的,非常感谢
lalagui commented
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?
wcy-cs commented
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。
wcy-cs commented
您好,刚找了一下原来的代码,大概是跑了50个epoch。
lalagui commented
好的好的,非常感谢