/CNN-Visualization

TensorFlow implementations of visualization of convolutional neural networks, such as Grad-Class Activation Mapping and guided back propagation

Primary LanguagePythonMIT LicenseMIT

Visualization of Deep Covolutional Neural Networks

  • This repository contains implementations of visualizatin of CNN in recent papers.
  • The source code in the repository can be used to demostrate the algorithms as well as test on your own data.

Requirements

Algorithms

  • The most straightforward approach to visualize a CNN is to show the feature maps (activations) and filters.
  • Details of the implementation and more results can be found here

  • Pick a specific activation on a feature map and set other activation to zeros, then reconstruct an image by mapping back this new feature map to input pixel space.
  • Details of the implementation and more results can be found here. Some results:

  • Details of the implementation and more results can be found here. Some results:

gbp

  • The class activation map highlights the most informative image regions relevant to the predicted class. This map can be obtained by adding a global average pooling layer at the end of convolutional layers.
  • Details of the implementation and more results can be found here. Some results:

celtech_change

  • Grad-CAM generates similar class heatmap as CAM, but it does not require to re-train the model for visualizatin.
  • Details of the implementation and more results can be found here. Some results:

grad-cam-result