https://github.com/machine-learning-tokyo/seq2seq-workshop
Seq2Seq workshop materials
https://github.com/machine-learning-tokyo/seq2seq-workshop
deep-learning machine-learning pytorch seq2seq workshop-materials
Last synced: 5 months ago
JSON representation
Seq2Seq workshop materials
- Host: GitHub
- URL: https://github.com/machine-learning-tokyo/seq2seq-workshop
- Owner: Machine-Learning-Tokyo
- License: mit
- Created: 2019-03-04T03:39:13.000Z (over 6 years ago)
- Default Branch: master
- Last Pushed: 2019-03-16T10:51:20.000Z (over 6 years ago)
- Last Synced: 2025-04-18T16:28:59.941Z (6 months ago)
- Topics: deep-learning, machine-learning, pytorch, seq2seq, workshop-materials
- Language: Jupyter Notebook
- Size: 6.62 MB
- Stars: 15
- Watchers: 3
- Forks: 8
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Seq2Seq-Workshop
Seq2Seq workshop materials
Presentation slides:
[NLP Basics](https://docs.google.com/presentation/d/1d66kraQablpfIPWLFo9_R_f2HB4_5uW8z0bvvUhsH_U/edit#slide=id.g54b76756f0_0_5601)
[Intro to Sequence to Sequence Learning](https://docs.google.com/presentation/d/1Zz1VzDHhRiF-QGyn_v7fHTSyoEOK7CH4nq2YpyZpVaY/edit?usp=sharing)
# Dependencies
* Python 3.6
* Pytorch 0.4.1
* MeCab with neologd dictionary
- [Instructions for Mac](https://qiita.com/taroc/items/b9afd914432da08dafc8)
- [Instructions for Ubuntu](https://qiita.com/ekzemplaro/items/c98c7f6698f130b55d53)
# Installation
1. Create a conda environment:
```
conda env create -n seq2seq python=3.6
```
2. Install dependencies
```
pip install spacy
pip install mecab-python3
```
3. Install Spacy `en` model:
```
python -m spacy download en
```
4. Install Pytorch `0.4.1`:
```
pip install torch==0.4.1
```
# Data
- English-Japanese Translation Corpus: (ftp://ftp.monash.edu/pub/nihongo/examples.utf.gz)
- [COCO Image Captioning Dataset](http://cocodataset.org/#download) (2014 train/val set)