[Feature] Add output_padding option to ConvTranspose2d

[zcbenz]

Passing the same parameters to nn.ConvTranspose2d does not revert nn.Conv2d in terms of dimension shape conservation, and an output_padding option can solve it.

Reference from PyTorch's docs:

The padding argument effectively adds dilation * (kernel_size - 1) - padding amount of zero padding to both sizes of the input. This is set so that when a Conv2d and a ConvTranspose2d are initialized with same parameters, they are inverses of each other in regard to the input and output shapes. However, when stride > 1, Conv2d maps multiple input shapes to the same output shape. output_padding is provided to resolve this ambiguity by effectively increasing the calculated output shape on one side. Note that output_padding is only used to find output shape, but does not actually add zero-padding to output.