frgfm/torch-cam

Class activation maps for your PyTorch models (CAM, Grad-CAM, Grad-CAM++, Smooth Grad-CAM++, Score-CAM, SS-CAM, IS-CAM, XGrad-CAM, Layer-CAM)

52
/ 100
Established

This tool helps machine learning engineers and researchers understand why their image classification models make certain decisions. You input a trained PyTorch model and an image, and it outputs a heatmap highlighting the specific regions in the image that most influenced the model's classification. This allows you to visually interpret and debug your model's predictions.

2,290 stars.

Use this if you need to visualize the parts of an image that your deep learning model is focusing on to make its classification, particularly with PyTorch models.

Not ideal if you are working with non-image data or models built with frameworks other than PyTorch.

deep-learning model-interpretability computer-vision image-classification AI-explainability
No Package No Dependents
Maintenance 6 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 20 / 25

How are scores calculated?

Stars

2,290

Forks

221

Language

Python

License

Apache-2.0

Last pushed

Dec 15, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/frgfm/torch-cam"

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