How neural-style works?

convnet2

I have, in many of my posts, described my experiments using and mis-using neural-style. Some of my experiments can be rather hard to understand in detail unless the reader has a basic understanding how neural-style works. So this post will try to bridge that gap, without going into the mathematical …

Continue reading

Getting the space back

paris_2840k-sw20fw50cw10_110

In my two previous posts, I experimented with neural-style by taking the fully connected layers into use. This resulted in something quite different, which I have provisionally called neural-mirage. Neural-mirage looks at the uppermost fc layer, the most abstract classification of what the network thinks it sees in the image, and …

Continue reading

I have seen a neural mirage

xpl4vgg16-helsinki03-fc8-cw1e3sw10000-800_350

In my previous post, Controlling image content with FC layers, I described how I had modified neural-style to optimize content based on the classifications obtained from the top-most, fully connected layers (which neural-style does not use).  I had found that the modified program produced visually quite interesting results, but I …

Continue reading

Beyond imitating style

The big thing about neural-style is being able to separate style and content of an image, and to synthesize new images mixing content and style from different sources. The original paper describing this new technology demonstrated how it is possible to apply the style of famous paintings from Van Gogh, Kandinsky …

Continue reading