omni:us Engineering

omni:us Engineering's repositories

jsonargparse

Implement minimal boilerplate CLIs derived from type hints and parse from command line, config files and environment variables

Language:PythonMIT279 4 268

squeezedet-keras

Keras implementation of the Squeeze Det Object Detection Deep Learning Framework

Language:PythonMIT128 11 26

research-GANwriting

Source code for ECCV20 "GANwriting: Content-Conditioned Generation of Styled Handwritten Word Images"

Language:PythonMIT65 9 12

research-WriterAdaptation-HTR

Source code for WACV20 paper "Unsupervised Adaptation for Synthetic-to-Real Handwritten Word Recognition".

Language:PythonMIT14 7 3

pagexml

Library in C++ and a python wrapper for dealing with Page XML files

Language:C++MIT13 6 2

docker-command-line-interface

Script intended to ease the execution from the command line of commands inside docker containers

Language:ShellMIT11 50

research-e2e-pagereader

End-to-end recognition of text and named entities in full pages

Language:PythonApache-2.07 4 1

narchi

A neural network architecture definition package

Language:HTMLMIT4 60

research-ContentDistillation-HTR

Source code for ICFHR20 "Distilling Content from Style for Handwritten Word Recognition"

Language:PythonMIT4 6 1

pytorch-cnn-visualizations

Pytorch implementation of convolutional neural network visualization techniques

Language:PythonMIT3 60

research-das2018-joint-text-entities-results

Model and predictions for results presented in the paper "Joint Recognition of Handwritten Text and Named Entities with a Neural End-to-end Model"

Language:Python3 80

research-dataset-sGMB

Synthetic handwritten Groningen Meaning Bank (GMB) dataset for research on full page text and entity recognition

Language:CSS2 50

Script to convert emails to PDF from the command-line, as well as detach recognized attachments. Helps to process incoming emails and assist automatically with a non-paper paperwork workflow. Designed to work in tandem with getmail to convert forwarded emails to PDF automatically.

Language:PythonMIT1 40