sar-gupta/gradcam-pytorch
Implementation of GradCAM algorithm in Pytorch
This tool helps researchers and deep learning practitioners understand why a convolutional neural network makes a specific decision. By inputting an image and a pre-trained image classification model, it generates a heatmap highlighting the critical regions in the image that influenced the model's prediction. This allows users to interpret and debug their computer vision models more effectively.
No commits in the last 6 months.
Use this if you need to visualize and interpret the decision-making process of your PyTorch convolutional neural network for image classification.
Not ideal if you are working with non-image data or require model interpretability methods beyond gradient-based heatmaps.
Stars
7
Forks
1
Language
Jupyter Notebook
License
—
Category
Last pushed
Feb 13, 2018
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/sar-gupta/gradcam-pytorch"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
jacobgil/pytorch-grad-cam
Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers,...
frgfm/torch-cam
Class activation maps for your PyTorch models (CAM, Grad-CAM, Grad-CAM++, Smooth Grad-CAM++,...
jacobgil/keras-grad-cam
An implementation of Grad-CAM with keras
ramprs/grad-cam
[ICCV 2017] Torch code for Grad-CAM
innat/HybridModel-GradCAM
A Keras implementation of hybrid efficientnet swin transformer model.