pytorch-grad-cam
Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more.
Use advanced methods to understand and explain how computer vision models make predictions.
From the README
- FasterRCNN: model.backbone
- Resnet18 and 50: model.layer4[-1]
- VGG, densenet161 and mobilenet: model.features[-1]
- mnasnet10: model.layers[-1]
- ViT: model.blocks[-1].norm1
- SwinT: model.layers[-1].blocks[-1].norm1
Excerpts from the project README on GitHub. Copyright and licensing remain with the respective authors.
Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.
Get an email alert on its next release or when it starts trending — never miss the moment.
Free · no card · unsubscribe anytimeAdvanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more.
pytorch-grad-cam has 12.9k stars on GitHub. It has been forked 1.7k times. pytorch-grad-cam is written mainly in Python. It has been in active development since 2017. pytorch-grad-cam is available under the MIT license. Its main topics are class-activation-maps, computer-vision, deep-learning, explainable-ai.
What is pytorch-grad-cam?
Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more.
Is pytorch-grad-cam open source?
pytorch-grad-cam is an open-source project. It is released under the MIT license.
Is pytorch-grad-cam free?
Yes. pytorch-grad-cam is free and open source — you can use, modify and self-host it.
What license does pytorch-grad-cam use?
pytorch-grad-cam is available under the MIT license.
What language is pytorch-grad-cam written in?
pytorch-grad-cam is written mainly in Python.
Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.
[](https://olud.ai/project/jacobgil-pytorch-grad-cam.html)
Measured from GitHub topics shared by both projects, weighted by how rare each topic is.