FrancescoSaverioZuppichini/A-journey-into-Convolutional-Neural-Network-visualization-
A journey into Convolutional Neural Network visualization
This project helps computer vision practitioners understand how their Convolutional Neural Networks (CNNs) are making decisions. It takes a trained CNN model and input images, then generates visualizations that reveal which parts of an image the model focuses on or what features it has learned. Data scientists, machine learning engineers, and researchers working with image recognition models can use this to diagnose issues and ensure models learn the intended patterns.
275 stars. No commits in the last 6 months.
Use this if you need to interpret the internal workings of a Convolutional Neural Network and verify that it's focusing on relevant visual information, rather than spurious correlations.
Not ideal if you are looking for a high-level performance metric or a tool to simply train and deploy a model without needing to peek inside its decision-making process.
Stars
275
Forks
49
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Feb 19, 2019
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/FrancescoSaverioZuppichini/A-journey-into-Convolutional-Neural-Network-visualization-"
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!