search

sicara / tf-explain

Interpretability Methods for tf.keras models with Tensorflow 2.x
https://tf-explain.readthedocs.io
MIT License
1.02k stars 112 forks source link

Separate attribution maps generation from visualizations #177

Open RaphaelMeudec opened 2 years ago

RaphaelMeudec commented 2 years ago

For v1.0.0, we should separate the computation of the attribution maps (i.e generate something with shape (N, H, W, 1)) from the visualization which is usually a grid.