nutsml 1.0.5

Flow-based data pre-processing for Machine Learning

Flow-based data pre-processing for (GPU/deep) machine learning.

nuts-ml is data pre-processing library for for (GPU/deep) machine learning that provides common pre-processing functions as independent units, so called ‘nuts’. Nuts can be freely arranged to build complex data flows based on chained iterators that are efficient, easy to read and easy to modify.

The following example gives a taste of a nuts-ml data-flow that trains a network on image data and prints training loss and accuracy

(train_samples >> Stratify(1) >> read_image >> transform >> augment >>
   Shuffle(100) >> build_batch >> network.train() >>
   Print('train loss:{} acc:{}') >> Consume())

nuts-ml is based on nuts-flow and reading its documentation is recommended.

Installation guide, API documentation and tutorials can be found here