FrancescoSaverioZuppichini/mirror

Visualisation tool for CNNs in pytorch

39
/ 100
Emerging

This tool helps machine learning engineers and researchers understand how their PyTorch Convolutional Neural Networks (CNNs) process images. You input trained CNN models and images, and it outputs interactive visualizations like Deep Dream, Grad-CAM, and guided backpropagation, showing what different layers 'see' or focus on. This is for anyone building and debugging image classification or computer vision models.

256 stars. No commits in the last 6 months.

Use this if you need to visually debug your PyTorch CNNs to understand their internal workings and decision-making process for image-based tasks.

Not ideal if you are working with non-image data, or if you need to visualize models from frameworks other than PyTorch.

deep-learning computer-vision model-interpretability neural-network-debugging image-analysis
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 13 / 25

How are scores calculated?

Stars

256

Forks

22

Language

Jupyter Notebook

License

MIT

Last pushed

Dec 27, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/FrancescoSaverioZuppichini/mirror"

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