A question on how we calculate the style loss. I suspect the source of my confusion is my unfamiliarity with how tensorflow works.
The loss function just uses layer outputs,
loss = metrics.mse(layer, targ)
Loss function passes something different to gram_matrix.
loss=sum(style_loss(l1, l2) for l1,l2 in zip(layers, targs))
My question: why do we pass l1 and l2 to style loss instead of l1 and l2?
for l1,l2 in zip(layers, targs):
(397, 595, 64)
(198, 297, 128)
<tf.Tensor 'strided_slice_56:0' shape=(198, 297, 128) dtype=float32>
I did some reading on tensorflow and couldn't find anything about a "strided_slice" which provides any hints.