ag027592

EDL-LRL

The implementation of "Facial Emotion Distribution Learning by Exploiting Low-Rank Label Correlations Locally".

ffmpeg-normalize

Audio Normalization for Python/ffmpeg

LDL-SCL

The implementation of "Distribution Learning with Label Correlations on Local Samples".

Additive-Margin-Softmax-Loss-Pytorch

Additive margin softmax loss in pytorch

AttentioNN

All about attention in neural networks. Soft attention, attention maps, local and global attention and multi-head attention.

ckiptagger

CKIP Neural Chinese Word Segmentation, POS Tagging, and NER

DistCal

Code for the ICML 2019 paper: Distribution Calibration for Regression

gt-nlp-class

Course materials for Georgia Tech CS 4650 and 7650, "Natural Language"

ICASSP_2020_Support

Created for supporting the manuscript submitted to ICASSP 2020

kedro

A Python library for building robust production-ready data and analytics pipelines

keras_lookahead

lookahead optimizer for keras

Latex-Resume

Resume created using Latex template

LDL

Pytorch implementation of "Joint Acne Image Grading and Counting via Label Distribution Learning"

lookahead.pytorch

lookahead optimizer (Lookahead Optimizer: k steps forward, 1 step back) for pytorch

LookaheadOptimizer-mx

Lookahead Optimizer: k steps forward, 1step back for MXNet

LSAN

Label-Specific Document Representation for Multi-Label Text Classification

morfist

Multi-target Random Forest implementation that can mix both classification and regression tasks

nova

NOVA is a tool for annotating and analyzing behaviours in social interactions. It supports Annotators using Machine Learning already during the coding process. Further it features both, discrete labels and continuous scores and a visuzalization of streams recorded with the SSI Framework.

openface

Face recognition with deep neural networks.

OpenFace-1

OpenFace – a state-of-the art tool intended for facial landmark detection, head pose estimation, facial action unit recognition, and eye-gaze estimation.

openXDATA

pytorch-lightning

Rapid research framework for PyTorch. The researcher's version of Keras

RAVEN

SGM

Sequence Generation Model for Multi-label Classification (COLING 2018)

shap

A unified approach to explain the output of any machine learning model.

snorkel

A system for quickly generating training data with weak supervision

snorkel-superglue

Applying Snorkel to SuperGLUE

Transformer

Transformer seq2seq model, program that can build a language translator from parallel corpus

unsupervised_learning_of_dense_shape_correspondence

xlnet

XLNet: Generalized Autoregressive Pretraining for Language Understanding