https://github.com/zeloe/noa_i
(Very) Easy ML network
https://github.com/zeloe/noa_i
machine-learning maxmsp neural-network processing python3 rave
Last synced: about 1 month ago
JSON representation
(Very) Easy ML network
- Host: GitHub
- URL: https://github.com/zeloe/noa_i
- Owner: zeloe
- License: gpl-3.0
- Created: 2022-08-23T13:20:35.000Z (almost 4 years ago)
- Default Branch: main
- Last Pushed: 2022-10-20T14:31:59.000Z (over 3 years ago)
- Last Synced: 2025-05-14T15:17:17.999Z (about 1 year ago)
- Topics: machine-learning, maxmsp, neural-network, processing, python3, rave
- Language: Max
- Homepage:
- Size: 190 KB
- Stars: 3
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# NoA_I
Influenced by Arnold Schönbergs dodecaphonism.
## Python requirements
- pip3 install opencv-python
- pip3 install python-osc
- pip3 install numpy
## Install processing
https://processing.org/
- install osc5 (external library)
## Get MaxMsp
https://cycling74.com/
## Download Rave and follow Instructions for training and compiling the external
https://github.com/acids-ircam/RAVE
## How to use
- From Terminal or Visual Studio Code launch NoA_1.py or NoA_1_random.py or both
- Open the Sequencer_Grid.pde or Sequencer_Grid_random.pde with processing or both
- Open the MaxMsp patches (use your own RAVE models)
## How it works
- This is an installation, which uses camera input.
- When it detects a face it starts the actual processing.
- It saves every 50 x 50 pixel and computes the mean and adds it to the part before.
- The highest pixel mean will play a sound.
- The highest pixel mean will be reset to 0.
- Like this every sound has a higher possibility to get played.
## Why...
- This was part of an university project.