Kakao Brain

fast-autoaugment

Official Implementation of 'Fast AutoAugment' in PyTorch.

pororo

PORORO: Platform Of neuRal mOdels for natuRal language prOcessing

kogpt

KakaoBrain KoGPT (Korean Generative Pre-trained Transformer)

torchgpipe

A GPipe implementation in PyTorch

minDALL-E

PyTorch implementation of a 1.3B text-to-image generation model trained on 14 million image-text pairs

rq-vae-transformer

The official implementation of Autoregressive Image Generation using Residual Quantization (CVPR '22)

word2word

Easy-to-use word-to-word translations for 3,564 language pairs.

torchlars

A LARS implementation in PyTorch

g2pM

A Neural Grapheme-to-Phoneme Conversion Package for Mandarin Chinese Based on a New Open Benchmark Dataset

KorNLUDatasets

KorNLI and KorSTS: New Benchmark Datasets for Korean Natural Language Understanding

autoclint

A specially designed light version of Fast AutoAugment

HOTR

Official repository for HOTR: End-to-End Human-Object Interaction Detection with Transformers (CVPR'21, Oral Presentation)

scrl

PyTorch Implementation of Spatially Consistent Representation Learning(SCRL)

kortok

The code and models for "An Empirical Study of Tokenization Strategies for Various Korean NLP Tasks" (AACL-IJCNLP 2020)

sparse-detr

PyTorch Implementation of Sparse DETR

helo_word

Team Kakao&Brain's Grammatical Error Correction System for the ACL 2019 BEA Shared Task

jejueo

Jejueo Datasets for Machine Translation and Speech Synthesis

bassl

autowu

Official repository for Automated Learning Rate Scheduler for Large-Batch Training (8th ICML Workshop on AutoML)

irm-empirical-study

An Empirical Study of Invariant Risk Minimization

miro

Official PyTorch implementation of MIRO

learning-loss-for-tta

"Learning Loss for Test-Time Augmentation (NeurIPS 2020)"

bc-hyperopt-example

brain cloud hyperopt example (mnist)