Tf-explain
Interpretability Methods for tf.keras models with Tensorflow 2.0
interpretability tensorflow tensorflow-2-0 article code keras library

tf-explain implements interpretability methods as Tensorflow 2.0 callbacks to ease neural network's understanding.

Don't forget to tag @sicara in your comment, otherwise they may not be notified.

Authors
Share this project
Similar projects
What does a CNN see?
First super clean notebook showcasing @TensorFlow 2.0. An example of end-to-end DL with interpretability.
Visualizing Class Activation Maps for CNNs
Visualizing Class Activation Maps for Convolutional Neural Networks
Integrated Gradients in TensorFlow 2
In this tutorial, you will walk through an implementation of IG step-by-step in TensorFlow 2 to understand the pixel feature importances of an image ...
Lucid
A collection of infrastructure and tools for research in neural network interpretability.
Top collections