Received an invalid combination of arguments

1

return _ssim(img1, img2, window, self.window_size, channel, self.size_average)

File “C:\Users\anoud\anaconda3\envs\env1\lib\site-packages\pytorch_ssim_init_.py”, line 18, in _ssim
mu1 = F.conv2d(img1, window, padding = window_size/2, groups = channel)

TypeError: conv2d() received an invalid combination of arguments - got (Tensor, Tensor, padding=float, groups=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)
  • (Tensor input, Tensor weight, Tensor bias, tuple of ints stride, str padding, tuple of ints dilation, int groups)
2

Base in the error message you are passing a float value as the padding argument, which is not supported.
Transform window_size/2 to an int and it should work.