I was impressed with your efficient padding method. So I used your method in my code.
But I have a problem.
error :
raw_out = super(PartialConv2d, self).forward(torch.mul(input, mask)
TypeError: mul() received an invalid combination of arguments - got (Tensor, NoneType), but expected one of:
(Tensor input, Tensor other, Tensor out)
(Tensor input, float other, Tensor out)
The first iteration does not produce an error, but at the second iteration this error occurs.
I think the error is due to the mask value being none.
That's why I
I used self.last_size = (None, None) on line 44 or I used the mask by replacing it with the self variable.
If you have any other way to fix this error, can you recommend it?
I was impressed with your efficient padding method. So I used your method in my code. But I have a problem.
error : raw_out = super(PartialConv2d, self).forward(torch.mul(input, mask) TypeError: mul() received an invalid combination of arguments - got (Tensor, NoneType), but expected one of:
(Tensor input, float other, Tensor out)
The first iteration does not produce an error, but at the second iteration this error occurs. I think the error is due to the mask value being none. That's why I I used self.last_size = (None, None) on line 44 or I used the mask by replacing it with the self variable.
If you have any other way to fix this error, can you recommend it?
Thank you for opening the code.