deepfx/netlens
A toolkit for interpreting and analyzing neural networks (vision)
This tool helps people who work with computer vision models understand what their neural networks are "looking" at and how they make decisions. You provide an image or a trained neural network, and it generates visual explanations, highlighting the most important parts of the input image for a specific prediction, or creating images that show what a network or a specific part of it has learned to recognize. This is useful for machine learning engineers, researchers, and data scientists developing and debugging vision models.
No commits in the last 6 months.
Use this if you need to visualize and interpret how your neural network processes images, attribute specific predictions to parts of an input image, or generate images that represent what different layers or classes within your model have learned.
Not ideal if you are looking for advanced or robust style transfer capabilities, as that feature is currently experiencing bugs and may not produce optimal results.
Stars
31
Forks
2
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Jul 28, 2020
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/deepfx/netlens"
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!