Closed noshaba closed 8 years ago
Hi Leon!
I wanted to try your other Loss Function, so I changed
for l,layer in enumerate(tex_layers): constraints[layer] = constraint([LossFunctions.gram_mse_loss], [{'target_gram_matrix': gram_matrix(net.blobs[layer].data), 'weight': tex_weights[l]}])
to
for l,layer in enumerate(tex_layers): constraints[layer] = constraint([LossFunctions.meanfm_mse_loss], [{'target_activations': net.blobs[layer].data, 'weight': tex_weights[l]}])
but then I get as a loss in my first Iteration 0 and the activations are always equal to the target activations.
Oh found the problem... I had to use net.blobs[layer].data.copy() instead of net.blobs[layer].data... :)
Hi Leon!
I wanted to try your other Loss Function, so I changed
to
but then I get as a loss in my first Iteration 0 and the activations are always equal to the target activations.