tf-explain

tf-explain offers interpretability methods for Tensorflow 2.0 to ease neural network’s understanding. With either its core API or its tf.keras callbacks, you can get a feedback on the training of your models.

• Overview
  • Installation
  • Tensorflow Compatibility
• Usage
  • Core API
  • Callbacks
• Available Methods
  • Activations Visualization
  • Vanilla Gradients
  • Gradients*Inputs
  • Occlusion Sensitivity
  • Grad CAM
  • SmoothGrad
  • Integrated Gradients
• API
  • tf_explain.callbacks package
  • tf_explain.core package
  • tf_explain.utils package
• Contributing
  • What can I do?
  • Guidelines

Roadmap

Next features are listed as issues with the roadmap label.