raghakot/keras-vis

Neural network visualization toolkit for keras

60
/ 100
Established

This toolkit helps machine learning engineers and researchers understand how image classification neural networks 'think.' It takes a trained Keras model and produces visual maps and images that show which parts of an input image the network focuses on, or what kind of patterns activate specific parts of the network. This helps to debug models, assess their performance, and gain insights into their decision-making process.

2,997 stars. No commits in the last 6 months. Available on PyPI.

Use this if you need to visualize the inner workings of your Keras-trained image classification models to diagnose issues, improve performance, or explain predictions.

Not ideal if your models are not Keras-based, or if you are working with non-image data.

deep-learning computer-vision model-debugging neural-network-interpretation image-analysis
Stale 6m
Maintenance 0 / 25
Adoption 10 / 25
Maturity 25 / 25
Community 25 / 25

How are scores calculated?

Stars

2,997

Forks

645

Language

Python

License

MIT

Last pushed

Feb 07, 2022

Commits (30d)

0

Dependencies

5

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/raghakot/keras-vis"

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