Gradient Class Activation Map (Grad-CAM) for a particular category indicates the discriminative image regions used by the CNN to identify that category.

The goal of this blog is to:

• understand concept of Grad-CAM
• understand Grad-CAM is generalization of CAM
• understand how to use it using keras-vis
• implement it using Keras's backend functions.

Reference¶

• Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization

Image Specific Class Saliency Visualization allows better understanding of why a model makes a classification decision. The goal of this blog is to understand its concept and how to interpret the Saliency Map.

Reference¶

• Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps
• keras-vis

Reference in this blog¶

• Visualization of deep learning classification model using keras-vis

In the next few blog posts, I will review visualization techiniques.

Image Specific Visualization¶

• Visualization of deep learning classification model using keras-vis
• Saliency Map with keras-vis
• Grad-CAM with keras-vis

Create condo environment¶

conda create -n explainableAI python=3.5
source activate explainableAI
conda install tensorflow
conda install keras
conda install jupyter
pip install git+https://github.com/raghakot/keras-vis.git --upgrade --no-deps
pip install opencv-python==3.3.0.10
$CONDA_PREFIX/bin/jupyter notebook --no-browser

Download a json file containing ImageNet class names.¶

This is the first blog post of Object Detection with YOLO blog series. The goal of this blog series is to understand the state-of-art object detection algorithm, called YOLO (you only look once). Allegedly, Andrew Ng mentioned that YOLO is the best object detection algorithm in his course. See the youtube video below: