Support of padding, dilation and stride in compute_grad1 function

[oljike]

Propose to substitute the following line:

autograd-hacks/autograd_hacks.py

Line 165 in 1fa974a

A = torch.nn.functional.unfold(A, layer.kernel_size)

with:
A = torch.nn.functional.unfold(A, layer.kernel_size, dilation=layer.dilation, padding=layer.padding, stride=layer.stride)