keplr-io/quiver

Interactive convnet features visualization for Keras

47
/ 100
Emerging

This tool helps machine learning engineers and researchers understand how their convolutional neural networks (CNNs) 'see' and interpret images. You input a Keras deep learning model and a folder of images, and it outputs an interactive dashboard. This dashboard visualizes the activation patterns within each layer of your CNN, showing you which features the network is detecting for each input image.

1,794 stars. No commits in the last 6 months.

Use this if you need to debug, explain, or gain insights into the internal workings of your Keras-based image classification or object detection models.

Not ideal if you are working with non-Keras models, non-image data, or require only basic performance metrics without deep interpretability.

deep-learning-interpretability computer-vision neural-network-debugging model-explanation image-recognition
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 21 / 25

How are scores calculated?

Stars

1,794

Forks

223

Language

JavaScript

License

MIT

Last pushed

Sep 04, 2020

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/keplr-io/quiver"

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