funkelab/gunpowder
A library to facilitate machine learning on multi-dimensional images.
This helps machine learning researchers and scientists train models on very large, multi-dimensional image datasets. You can create a step-by-step workflow to load, preprocess, augment, and sample image data, then train a model, and finally store the results. This is for machine learning practitioners working with complex image data.
Use this if you need to build and manage a flexible pipeline for training machine learning models on extremely large, multi-dimensional images, like those found in microscopy or medical imaging.
Not ideal if you are working with standard 2D images or smaller datasets that do not require specialized memory management and pipeline orchestration.
Stars
89
Forks
59
Language
Python
License
MIT
Category
Last pushed
Mar 23, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/funkelab/gunpowder"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
scikit-image/scikit-image
Image processing in Python
rerun-io/rerun
An open source SDK for logging, storing, querying, and visualizing multimodal and multi-rate data
rapidsai/cucim
cuCIM - RAPIDS GPU-accelerated image processing library
visioncortex/visioncortex
Core library for computer graphics & vision applications
imagej/ImageJ
Public domain software for processing and analyzing scientific images