Skip to content

Implementation of Layerwise Relevance Propagation for heatmapping "deep" layers

Notifications You must be signed in to change notification settings

atulshanbhag/Layerwise-Relevance-Propagation

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

88 Commits
 
 
 
 
 
 
 
 

Repository files navigation

Layerwise-Relevance-Propagation

Implementation of Layerwise Relevance Propagation for heatmapping "deep" layers, using Tensorflow and Keras.

Results

MNIST

VGG

Instructions

MNIST

  • Run train.py to train model.
  • Weights will be saved in logs/.
  • Run lrp.py for Layerwise Relevance Propagation.

NOTE: If using Tensorflow version < 1.5.0, you need to change tf.nn.softmax_cross_entropy_with_logits_v2 to tf.nn.softmax_cross_entropy_with_logits.

VGG

  • Feed a list of images to run Layerwise Relevance Propagation on all images.
  • All results will be saved in results/.
  • Run lrp.py <image_1> <image_2> ... <image_n>.

Reference

About

Implementation of Layerwise Relevance Propagation for heatmapping "deep" layers

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages