GitHub - matpalm/evolved_channel_selection: rather than use all 13 channels in a multi spectral image for classification can we train a model that is robust to all combos, at all resolutions, and use a genetic algorithm to choose which are the most valuable? · GitHub

This repository was archived by the owner on Aug 18, 2026. It is now read-only.

Name		Name	Last commit message	Last commit date
.gitignore		.gitignore
README.md		README.md
accuracy.py		accuracy.py
data.py		data.py
derive_channel_stats.ipynb		derive_channel_stats.ipynb
eg_imgs.py		eg_imgs.py
ga_channel_selection.py		ga_channel_selection.py
gen_runs.py		gen_runs.py
models.py		models.py
sample_channel_fitnesses.py		sample_channel_fitnesses.py
simple_ga.py		simple_ga.py
train.py		train.py
util.py		util.py

Repository files navigation

see blog post it's super super great!

About

rather than use all 13 channels in a multi spectral image for classification can we train a model that is robust to all combos, at all resolutions, and use a genetic algorithm to choose which are the most valuable?

matpalm.com/blog/evolved_channel_selection/

9 stars

1 watching

Report repository

Releases

Packages

Contributors

Languages