marcusnk237 / Gradcam_plus_plus

One of the first implementations of Grad-CAM ++ for time series / 1d signal.

Gradcam_plus_plus

Grad-CAM ++ for time series classification

Table of Contents

1. About
   • Built With
2. Getting Started
   • Prerequisites
   • Installation
3. Usage
4. Contact
5. Acknowledgments

About The Project

One of the main challenges in artificial intelligence for the researchers is to understands how model predictions works. Many contributions has been made, especially GRAD-CAM++. Grad-CAM++ give a visual representation of the keys features responsible of the classification, and give human-level understanding of the model prediction. Despite its advantages, GRAD-CAM ++ is not initially design for time series

The program give a GRAD-CAM ++ visualisation for time series

(back to top)

Built With

(back to top)

Getting Started

Prerequisites

Installation

Clone the repo

sh git clone https://github.com/marcusnk237/Gradcam_plus_plus.git

(back to top)

Usage

compute_cam_1d_output (model, data , layer_name , N)
Arguments:
> - model : The model trained
> - data : The data sample
> - layer_name : The last layer of the feature extraction part of the model. Usually, it is the last layer before the Flattening operation.
> - N : data length

Contact

• 

• Project Link: https://github.com/marcusnk237/Gradcam_plus_plus

(back to top)

Acknowledgments

The authors of the original article about GRAD-CAM++

• Aditya Chattopadhay; Anirban Sarkar; Prantik Howlader; Vineeth N Balasubramanian : Grad-CAM++: Generalized Gradient-Based Visual Explanations for Deep Convolutional Networks

(back to top)