znah / deepdream_c

This is an artistic experiment trying to implement Convolutional Neural Network inference and back-propagation using a minimal subset of C89 language and standard library features. As of now this program can:

Generate adversarial examples (versions of the input image with almost imperceivable modifications that nevertheless cause neural network to incorrectly classify them)

Apply DeepDream effect to an input image. This effect tries to amplify the magnitude of activations of a particular layer of the neural network, which fills the image with psychedelic patterns

The observed performance in case of using an optimizing compiler is comparable with what I had with CPU Caffe in 2015. In particular, rendering 7 octaves of DeepDream on the default input image takes around 25 minutes on a MacBook Pro 2019.

This project was developed by me, Alexander Mordvintsev, to celebrate the 6th anniversary of the DeepDream creation. It all started with the art commission request by the k21.kanon.art project. Originally we planned to recreate a few first DeepDream images by running the original code from 2015. However it happened to be surprisingly challenging to bring even just a few year old code to life given all the dependences. This resonated with my overall frustration with the excessive complexity, bloat and over-reliance on frameworks of modern software. I decided to see how difficult would it be to implement the whole thing from scratch, using the technologies that are available for at least 30 years old, but still in active use today.

Leave a Comment