Skip to content

yokoom/dl_lecture_2017w_team1

 
 

Repository files navigation

dl_lecture_2017w_team1

Requirements:

  • Tensorflow r1.0.1
  • Python 2.7
  • CUDA 7.5+ (For GPU)

Introduction

Apply Generative Adversarial Nets to generating sequences of discrete tokens.

The illustration of SeqGAN. Left: D is trained over the real data and the generated data by G. Right: G is trained by policy gradient where the final reward signal is provided by D and is passed back to the intermediate action value via Monte Carlo search.

The research paper SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient has been accepted at the Thirty-First AAAI Conference on Artificial Intelligence (AAAI-17).

本家のレポジトリより引用)

How to use

1.Twitterからデータ収集

$ python timeline.py

でNON STYLE 石田の「おはようございます。みなさんの」から始まるツイートを全て取ってこれます。

出力先はsave/raw_tweet.py

他のアカウントからツイートを持ってきたければ、24行目と48行目の"screen_name"を任意のアカウント名の@以下に変えて、

39〜41行目を削除して使ってください。

2.日本語のトークナイズ

$ python datacleaner.py

save/raw_tweet.pyからURLを除去後、形態素解析をMeCabで行います。

出力先はsave/parsed_tweet.py

3.SeqGANの学習

$ python sequence_gan.py

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 95.2%
  • Shell 2.3%
  • Jupyter Notebook 2.3%
  • Makefile 0.2%