flotsam and jetsam from the neural driftnets

UPDATE: both the Twitter and Mastodon versions now take advantage of the extra headroom to post longer versions of the text with line-breaks, much closer to the original NaNoGenMo version.

@neuralgae uses a neural net to generate an image from a set of random categories, classifies the result using a neural net (not necessarily the same one) and repeats, giving sequences of surreal objects which are kind of related to one another. The categories are used to generate the accompanying text using a basic Markov generator.

It's based on my entry for National Novel Generation Month (NaNoGenMo) in 2015. Source code and heaps of technical notes are available in the GitHub repository.