tralfamadude

druid-1

Metamarkets Druid Data Store

pdf_trio

A PDF classifier ensemble with REST API service. Achieves up to 98% accuracy.

bert

TensorFlow code and pre-trained models for BERT

fictionlens

BERT_propaganda_detection

Propaganda detection using fine-tuned BERT

CGP-IP

dhSegment

Generic framework for historical document processing

DL_Architectures

pdf_image_classifier

A way to classify PDFs via images of their first page.

TonY

TonY is a framework to natively run deep learning frameworks on Apache Hadoop.

ufilm_segment

A system for extracting text (title, authors, ToC, bibliography) from microfilm images of journals.

visiongp_trans

genetic programming for image transformation

wasserstein-style-transfer

Performs style transfer by defining the style loss as the Wasserstein distance between the distribution of the the style image features and the generated image features.

whirr

Mirror of Apache Whirr