Randomizing neural style transfer

I have noticed that I prefer the original neural-style over the faster variants like texture-nets and fast-neural-style. One reason is that neural-style allows more control and more immediate feedback when working on images; this applies when one is not interested in developing reusable filters but working a individual images and developing …

Continue reading

Seeing beoynd the edges of the image

mar05-0091

In an earlier post, http://liipetti.net/erratic/2016/11/25/imaginary-landscapes-using-pix2pix/, I experimented with pix2pix, a versatile new package for training a model, using a conditional GAN architecture, to do various image transforms. In that earlier post, I also ventured beyond an image transform in which the content of the image is kept spatially similar, namely adding what is …

Continue reading

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