inspirehep/magpie

Deep neural network framework for multi-label text classification

51
/ 100
Established

Builds word2vec embeddings and trains Keras neural networks on paired text/label files, with configurable train-test splitting and memory-efficient batch processing for large datasets. Returns confidence-scored predictions across all labels rather than single classifications. Originally developed at CERN for Physics abstract categorization, supporting custom label sets and model persistence across word vectors, scalers, and trained weights.

688 stars. No commits in the last 6 months.

Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 25 / 25

How are scores calculated?

Stars

688

Forks

190

Language

Python

License

MIT

Last pushed

Jan 31, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/inspirehep/magpie"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.