md-k-sarker / lucid

A collection of infrastructure and tools for research in neural network interpretability.

Lucid

Lucid 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.

Notebooks

Tutorial Notebooks

Feature Visualization Notebooks

Notebooks corresponding to the Feature Visualization article

Building Blocks Notebooks

Notebooks corresponding to the Building Blocks of Interpretability article

Miscellaneous Notebooks

Recomended Reading

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

Additional Information

License and Disclaimer

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.

Development

Style guide deviations

We use naming conventions to help differentiate tensors, operations, and values:

• Suffix variable names representing tensors with _t
• Suffix variable names representing operations with _op
• Don't suffix variable names representing concrete values

Usage example:

global_step_t = tf.train.get_or_create_global_step()
global_step_init_op = tf.variables_initializer([global_step_t])
global_step = global_step_t.eval()

Running Tests

Use tox to run the test suite on all supported environments.

To run tests only for a specific module, pass a folder to tox: tox tests/misc/io

To run tests only in a specific environment, pass the environment's identifier via the -e flag: tox -e py27.

After adding dependencies to setup.py, run tox with the --recreate flag to update the environments' dependencies.