jacobgil/keras-grad-cam
An implementation of Grad-CAM with keras
When you have a deep learning model classifying images, it can be hard to understand why it made a particular decision. This tool takes an image and a pre-trained Keras model, then highlights the specific regions in the image that most influenced the model's classification. It's used by machine learning engineers or researchers to interpret and debug their image classification models.
666 stars. No commits in the last 6 months.
Use this if you need to visualize which parts of an image an image classification model focuses on when making a prediction.
Not ideal if you are working with non-image data or deep learning models that are not built with Keras.
Stars
666
Forks
232
Language
Python
License
MIT
Category
Last pushed
Apr 08, 2019
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/jacobgil/keras-grad-cam"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
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++,...
ramprs/grad-cam
[ICCV 2017] Torch code for Grad-CAM
matlab-deep-learning/Explore-Deep-Network-Explainability-Using-an-App
This repository provides an app for exploring the predictions of an image classification network...
innat/HybridModel-GradCAM
A Keras implementation of hybrid efficientnet swin transformer model.