A library to facilitate machine learning on multi-dimensional images.

gunpowder allows you to assemble a pipeline from data loading over pre-processing, random batch sampling, data augmentation, pre-caching, training/prediction, to storage of results on arbitrarily large volumes of multi-dimensional images. gunpowder is not tied to a particular learning framework, and thus complements libraries like tensorflow or caffe.

The full documentation can be found here.

gunpowder was originally written by Jan Funke and is inspired by PyGreentea by William Grisaitis, Fabian Tschopp, and Srini Turaga.