Switch to PyTorch API (computational graph is broken!)

[Nikronic]

Deep-Halftoning/utils/losses.py

Lines 136 to 138 in f968d28

	patch_loss = np.sum(
	[self.MSE_loss(self.gram_matrix(self.get_patch(ly)), self.gram_matrix(self.get_patch(lp)))
	for ly, lp in zip(y_vgg, details_outputs_vgg)])

Why on earth there is a numpy function during the forward pass of computing loss? Switch to pytorch and get rid of for-loop.