matlab-deep-learning/Explore-Deep-Network-Explainability-Using-an-App

This repository provides an app for exploring the predictions of an image classification network using several deep learning visualization techniques. Using the app, you can: explore network predictions with occlusion sensitivity, Grad-CAM, and gradient attribution methods, investigate misclassifications using confusion and t-SNE plots, visualize layer activations, and many more techniques to help you understand and explain your deep network’s predictions.

38
/ 100
Emerging

This app helps you understand why an image classification deep learning model makes specific predictions. You input your trained image classification network and a collection of images, and it outputs visual explanations like 'heatmaps' showing important image regions, as well as plots that reveal misclassifications. This tool is designed for data scientists, researchers, or anyone deploying image classification models who needs to interpret their model's behavior.

No commits in the last 6 months.

Use this if you need to visually explain and diagnose the predictions and misclassifications of your deep learning image classification models.

Not ideal if you are working with non-image data, very large datasets that require custom performance optimization, or if you need to build the deep learning model from scratch.

deep-learning image-classification model-interpretability computer-vision AI-explainability
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 15 / 25

How are scores calculated?

Stars

37

Forks

7

Language

MATLAB

License

Last pushed

Sep 07, 2021

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/matlab-deep-learning/Explore-Deep-Network-Explainability-Using-an-App"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.