Inspired by Lucid, Luna is a Feature Visualization package for Tensorflow. While Lucid does not support Tensorflow 2, Luna was built with Tensorflow 2 at its core.

Luna is under active development. It is research code and not production-ready.

To learn how to use Luna and for insights into its API, see our documentation.

We greatly appreciate any effort to improve Luna. If you want to contribute to its development, see our contribution guidelines.

• Feature Visualization
• The Building Blocks of Interpretability
• Using Artificial Intelligence to Augment Human Intelligence
• Visualizing Representations: Deep Learning and Human Beings
• Differentiable Image Parameterizations
• Activation Atlas

• Lessons from a year of Distill ML Research (Shan Carter, OpenVisConf)
• Machine Learning for Visualization (Ian Johnson, OpenVisConf)

While we admire their work, we have no affiliation with the Lucid authors or project. Nonetheless, if you are interested in research like this, the Distill slack (join link) might be a good place for you to get to know other people in this area.

On the awesome Distill slack, Lucid has its own #proj-lucid channel, where general questions about the technology are discussed.