MisaOgura/flashtorch
Visualization toolkit for neural networks in PyTorch! Demo -->
This toolkit helps AI practitioners understand why their neural networks make specific predictions on images. You input a trained image recognition model and an image, and it generates visual explanations like 'saliency maps' to show which parts of the image the network focused on. Data scientists and machine learning engineers can use this to debug models or build trust in AI systems.
745 stars. No commits in the last 6 months.
Use this if you need to interpret the decision-making process of your PyTorch-based image classification models.
Not ideal if your primary goal is to train new models or if you are working with non-image data.
Stars
745
Forks
88
Language
HTML
License
MIT
Category
Last pushed
Sep 21, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/MisaOgura/flashtorch"
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!