https://github.com/arogozhnikov/3d_nn
Raymarching neural network in browsers with WebGL shaders
https://github.com/arogozhnikov/3d_nn
neural-network raymarching-distance-fields shaders visualization webgl
Last synced: 4 months ago
JSON representation
Raymarching neural network in browsers with WebGL shaders
- Host: GitHub
- URL: https://github.com/arogozhnikov/3d_nn
- Owner: arogozhnikov
- Created: 2017-06-06T17:04:11.000Z (almost 8 years ago)
- Default Branch: master
- Last Pushed: 2022-12-05T17:31:17.000Z (over 2 years ago)
- Last Synced: 2024-12-27T02:10:34.547Z (4 months ago)
- Topics: neural-network, raymarching-distance-fields, shaders, visualization, webgl
- Language: JavaScript
- Homepage: https://arogozhnikov.github.io/3d_nn
- Size: 2.48 MB
- Stars: 195
- Watchers: 7
- Forks: 32
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Marching neural networks
Visualizing level surfaces of a neural network using webGL + raymarching technique.
Correction: technique is close raymarching, but step sizes are computed differently.
All the NN-related computing uses shaders, thus having GPU is recommended.
Demo: [https://arogozhnikov.github.io/3d_nn/](https://arogozhnikov.github.io/3d_nn/)
## Used libraries
Visualization relies on [THREE.js](https://github.com/mrdoob/three.js) for rendering and [CCapture.js](https://github.com/spite/ccapture.js) for capturing animations.
The code is minimalistic and a bit messy, but no other dependencies / frameworks.
