Home of cats, dreams, and interpretable neural networks.
(Name may change before public release.)
XYZ_Project is a collection of infrastructure and tools for research in neural network interpretability.
In particular, it provides state of the art implementations of feature visualization techniques, and flexible abstractions that make it very easy to explore new research directions.
Quick start: dXYZ_Project-tutorial (TODO)
How XYZ_Project is structured:
- modelzoo: Easily import models for visualization
- optvis: Framework for optimization-based feature visualization
- scratch: Incubating code that needs to be shared between notebooks.
- misc: More mature code that doesn't fit into a large cluster.
- recipes: Less general code that makes a particular visualization.
Note that we do a lot of our research in colab notebooks and transition code here as it matures.
You may use this software under the Apache 2.0 License. See LICENSE.
This project is research code. It is not an official Google product.