cnncam 1.0.0

Gradient Based Class Activation Maps for TensorFlow models.

cnncam

Introduction

An open python library for researchers and developers to generate GradCAM explanations for the tensorflow CNN models.

Other popular python ML frameworks will soon be supported by the cnn-cam library

Install

The below instructions assume you already have pip installed and exposed to the python environment where you want to run cnncam. Official instructions for installing pip can be found here

Run the below pip command in a shell of your choice.

pip install cnncam

Demo

We currently support two ways of obtaining GradCAM heatmaps:

1. Display heatmap. If you're only interested in seeing the heatmap images for your model's prediction, you can run the below script:

from cnncam import display_heatmap

display_heatmap(model=model, # your keras model
                img=img, # your image
                predicted_class=pred, # your models prediction for the image 
                layer_name='block5_conv3', # the layer you would like to see GradCAM for 
                alpha=0.6 # opacity of heatmap overlayed on image
                )

See /examples for executable examples, including the above application of our implementation of GradCAM on VGG-16 with the ower of this repo's very cute cat, meso.