innat/HybridModel-GradCAM

A Keras implementation of hybrid efficientnet swin transformer model.

38
/ 100
Emerging

This project helps machine learning engineers and researchers visually interpret how a hybrid AI model makes decisions on image data. It takes an image and a trained hybrid model (combining EfficientNet and Swin Transformer) as input and outputs visual heatmaps, highlighting the specific regions within the image that the model focused on to reach its conclusions. This is useful for understanding and debugging complex image classification or recognition tasks.

No commits in the last 6 months.

Use this if you need to understand which parts of an image your hybrid EfficientNet-Swin Transformer model prioritizes when making predictions.

Not ideal if you are working with non-image data or need to interpret a different type of AI model (e.g., a pure CNN, a recurrent neural network, or a large language model).

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

How are scores calculated?

Stars

34

Forks

6

Language

Jupyter Notebook

License

Apache-2.0

Last pushed

Oct 14, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/innat/HybridModel-GradCAM"

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