FrancescoSaverioZuppichini/mirror
Visualisation tool for CNNs in pytorch
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.
Stars
256
Forks
22
Language
Jupyter Notebook
License
MIT
Category
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.
Higher-rated alternatives
lutzroeder/netron
Visualizer for neural network, deep learning and machine learning models
mert-kurttutan/torchview
torchview: visualize pytorch models
raghakot/keras-vis
Neural network visualization toolkit for keras
janosh/diagrams
Diagrams of concepts in physics/chemistry/ML
dvgodoy/deepreplay
Deep Replay - Generate visualizations as in my "Hyper-parameters in Action!" series!