haven-jeon / Ko_en_neural_machine_translation
Korean English NMT(Neural Machine Translation) with Gluon
Stars: ✭ 55
Projects that are alternatives of or similar to Ko en neural machine translation
Aws Machine Learning University Accelerated Tab
Machine Learning University: Accelerated Tabular Data Class
Stars: ✭ 718 (+1205.45%)
Mutual labels: jupyter-notebook, mxnet, gluon
Aws Machine Learning University Accelerated Nlp
Machine Learning University: Accelerated Natural Language Processing Class
Stars: ✭ 1,695 (+2981.82%)
Mutual labels: jupyter-notebook, mxnet, gluon
Aws Machine Learning University Accelerated Cv
Machine Learning University: Accelerated Computer Vision Class
Stars: ✭ 1,068 (+1841.82%)
Mutual labels: jupyter-notebook, mxnet, gluon
Adaptis
[ICCV19] AdaptIS: Adaptive Instance Selection Network, https://arxiv.org/abs/1909.07829
Stars: ✭ 314 (+470.91%)
Mutual labels: jupyter-notebook, mxnet
D2l Pytorch
This project reproduces the book Dive Into Deep Learning (https://d2l.ai/), adapting the code from MXNet into PyTorch.
Stars: ✭ 3,810 (+6827.27%)
Mutual labels: jupyter-notebook, mxnet
MXNet-EfficientNet
A Gluon Implement of EfficientNet
Stars: ✭ 12 (-78.18%)
Mutual labels: mxnet, gluon
Deep Learning Vm
Sets up a VM with Keras, TensorFlow, TFLearn and Theano installed
Stars: ✭ 23 (-58.18%)
Mutual labels: jupyter-notebook, mxnet
Deeplearning
深度学习入门教程, 优秀文章, Deep Learning Tutorial
Stars: ✭ 6,783 (+12232.73%)
Mutual labels: jupyter-notebook, mxnet
Mxnet Centernet
Gluon implementation of "Objects as Points", aka "CenterNet"
Stars: ✭ 29 (-47.27%)
Mutual labels: mxnet, gluon
Autogluon
AutoGluon: AutoML for Text, Image, and Tabular Data
Stars: ✭ 3,920 (+7027.27%)
Mutual labels: mxnet, gluon
Gluon Face
An unofficial Gluon FR Toolkit for face recognition. https://gluon-face.readthedocs.io
Stars: ✭ 264 (+380%)
Mutual labels: mxnet, gluon
Deeplearningzerotoall
TensorFlow Basic Tutorial Labs
Stars: ✭ 4,239 (+7607.27%)
Mutual labels: jupyter-notebook, mxnet
gpu accelerated forecasting modeltime gluonts
GPU-Accelerated Deep Learning for Time Series using Modeltime GluonTS (Learning Lab 53). Event sponsors: Saturn Cloud, NVIDIA, & Business Science.
Stars: ✭ 20 (-63.64%)
Mutual labels: mxnet, gluon
Sockeye
Sequence-to-sequence framework with a focus on Neural Machine Translation based on Apache MXNet
Stars: ✭ 990 (+1700%)
Mutual labels: mxnet, gluon
Quantization.mxnet
Simulate quantization and quantization aware training for MXNet-Gluon models.
Stars: ✭ 42 (-23.64%)
Mutual labels: mxnet, gluon
baidu-salers-logo-prediction
baidu contest, url: http://dianshi.baidu.com/gemstone/competitions/detail?raceId=17
Stars: ✭ 16 (-70.91%)
Mutual labels: mxnet, gluon
model-zoo-old
The ONNX Model Zoo is a collection of pre-trained models for state of the art models in deep learning, available in the ONNX format
Stars: ✭ 38 (-30.91%)
Mutual labels: mxnet, gluon
Efficientnet
Gluon implementation of EfficientNet and EfficientNet-lite
Stars: ✭ 30 (-45.45%)
Mutual labels: mxnet, gluon
Neural Korean to English Machine Translater with Gluon
2018 마이크로소프트웨어 기사를 통해 오신분은 이곳을 참고하세요.
특징
- Seq2Seq with Attention
- Gluon 기반 Hybridize
- 공개 학습셋 (from https://github.com/jungyeul/korean-parallel-corpora) 기반 학습
- multi gpu 학습 옵션 제공
- Variable Sentence Length 학습
요구사항
- Python 3.5 이상
- MXNet 1.0 이상
- tqdm, konlpy, stemming, gensim
구성
- 아키텍처
- seq2seq
- Attention
- bi-directional GRU encoder
- 영한 교차 임베딩 학습
TODO
- Beam Search 구현
How to
- 임베딩 학습
python main.py --embedding
- 번역 모형 학습
CUDA_VISIBLE_DEVICES='4,5,6,7' python main.py --train --gpu-count 4 --batch-size 100
- 번역 모형 테스트
python main.py --test --init-model "models/trained_model.params"
kor > 오바마는 대통령이다.
오바마는 대통령이다.
eng > obama is a presid .
kor > 좋은 아침.
좋은 아침.
eng > good morn
kor > 북한은 핵무기를 가지고 있다.
북한은 핵무기를 가지고 있다.
eng > north korea has a nuclear weapon .
kor >
- models/trained_model.params
- rmsprop(batch size : 100, lr : 0.01) : 7 epocs
- sgd (batch size : 100, lr : 0.01) : 33 epocs
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].