Some very specific image resolutions lead to errors

[slashedstar]

For instance, with a 850x756 content image:

  File "X:\Avirtual\NeuralNeighborStyleTransfer-main\styleTransfer.py", line 70, in <module>
    output = produce_stylization(content_im_orig, style_im_orig, phi,
  File "X:\Avirtual\NeuralNeighborStyleTransfer-main\utils\stylize.py", line 122, in produce_stylization
    s_pyr = optimize_output_im(s_pyr, c_pyr, content_im, style_im_tmp,
  File "X:\Avirtual\NeuralNeighborStyleTransfer-main\utils\stylize.py", line 311, in optimize_output_im
    s_col_samp = cs_tmp.contiguous().view(1, chans, -1)
RuntimeError: shape '[1, 512, -1]' is invalid for input of size 3673856

With 850x272:

File "X:\Avirtual\NeuralNeighborStyleTransfer-main\utils\imagePyramid.py", line 20, in dec_lap_pyr
    x_small = F.interpolate(cur, (h // 2, w // 2), mode='bilinear')
  File "X:\avirtual\.main\lib\site-packages\torch\nn\functional.py", line 3919, in interpolate
    return torch._C._nn.upsample_bilinear2d(input, output_size, align_corners, scale_factors)
RuntimeError: Input and output sizes should be greater than 0, but got input (H: 1, W: 3) output (H: 0, W: 1)