Why sum the loss from multiple layers and sum it up for style transfer?

@davecg cool experiments! really like how you benchmark the impact of each layer. just to make sure i follow correctly, are these experiments on content loss variations ( single layer and everything but that specific single layer)?

@bckenstler did some experiments with block4_conv2, block3_conv2, block3conv4 and had some interesting results. I’d be curious to see your experiments with other convolution layers for different blocks.