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
This tool helps machine learning engineers and researchers create interactive 3D visualizations of their neural network models directly in a web browser. You input a pre-trained deep learning model from frameworks like TensorFlow or Keras, and it outputs an intuitive, explorable 3D representation showing the model's structure and how data flows through its layers during prediction. This is perfect for explaining complex models to stakeholders or for better understanding model behavior yourself.
5,169 stars. No commits in the last 6 months. Available on npm.
Use this if you need to visually explain or explore the internal workings of a pre-trained neural network model.
Not ideal if you are looking for advanced debugging tools or a library to build and train neural networks.
Stars
5,169
Forks
447
Language
JavaScript
License
Apache-2.0
Category
Last pushed
Dec 05, 2022
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.
Related frameworks
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!