tensorspace-team/tensorspace
Neural network 3D visualization framework, build interactive and intuitive model in browsers, support pre-trained deep learning models from TensorFlow, Keras, TensorFlow.js
Constructs 3D neural network visualizations by building layer-by-layer models using a Keras-like API, then loads preprocessed weights from TensorFlow/Keras/TensorFlow.js models to render interactive tensor flows through the network. Built on Three.js for 3D rendering and TensorFlow.js for browser-based inference, it enables front-end developers to inspect intermediate layer activations and feature abstractions during model prediction without server-side computation.
5,169 stars and 123 monthly downloads. No commits in the last 6 months. Available on npm.
Stars
5,169
Forks
447
Language
JavaScript
License
Apache-2.0
Category
Last pushed
Dec 05, 2022
Monthly downloads
123
Commits (30d)
0
Dependencies
7
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/tensorspace-team/tensorspace"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Compare
Related frameworks
lutzroeder/netron
Visualizer for neural network, deep learning and machine learning models
raghakot/keras-vis
Neural network visualization toolkit for keras
mert-kurttutan/torchview
torchview: visualize pytorch models
visualDust/neetbox
[Beta] 🚀 NEETBOX provides the visualization and tooling needed for machine learning experimentation.
dvgodoy/deepreplay
Deep Replay - Generate visualizations as in my "Hyper-parameters in Action!" series!