Giter Club home page Giter Club logo

tf-keras-rnn-time-pred's Introduction

Readme for RNN time prediction in tf.keras

  • Final update: 2018 Oct
  • All right reserved @ Chanhee Jeong and Jaewook Kang 2018

요구사항 (코드 최종 작성 후 삭제 예정)

찬희님 RNN time prediction example code 작성을 요청드립니다. :-) 요구사항은 아래와 같습니다

  • tf.keras를 이용해서 실행가능한 .py 코드 작성

  • 주피터 노트북이나 colab이 아닌 파이참에서 돌아가는 파일 필요

  • AWS에서 GPU로 동작하는 코드 (tf.device()필요?)

  • 적절하게 readme.md 수정

  • 아래에서 구분하는 6가지 파일 + alpha로 코드를 구분해서 작성

  • 실행되는 파일은 eval.pytrainer.py

  • 간단한 데이터셋을 다운로드하는 코드가 data_loader.py에 포함되야함 (아니면 데이터셋 다운로드 방법을 readme.md에 표시)

  • 어플리케이션은 구글의 예제 를 그대로 따라서 해도 무방하고 주식차트 예측 같은 것이 가능하면 선호함

  • 기타 질문은 언제든지 슬랙으로

  • 코드 리뷰는 깃헙의 풀리퀘스트

  • 작업은 develop에서 features/branch_name으로 브랜치 따서 작업 요망

  • 프로젝트 형식 참고

  • deadline: 10/8 월요일 23:00 (협의가능)

About

아래 적절하게 수정

The aim of this repository is to introduce an exemplary TF project in practice. We show the example with respect to MNIST classification by Lenet5. This project is composed of several .py files, each of which undertakes single role and responsibility according to the OOP philosophy.

아래 적절하게 수정, 파일은 추가가 가능하나 아래 요소들은 꼭 필요함

- data_loader.py    : Preparing and feeding the dataset in batchwise by using tf.data
- model_builder.py  : Building a model in tensorflow computational graph.
- model_config.py   : Specifying a configulation for the model 
- trainer.py        : Training the model by importing the dataloader and the model_builer
- train_config.py   : Including a configulation for the training
- eval.py           : Evaluating the model with respect to test dataset by loading a ckpt

How to Run

Training

python ./tf_module/trainer.py

Inference

python ./tfmodule/eval.py

Components

아래를 적절하게 수정

./tfmodule/
├── data
│   └── mnist
├── export
│   └── tf_logs
├── data_loader.py
├── eval.py
├── model_builder.py
├── model_config.py
├── testcodes
│   └── test_dataloader.py
├── train_config.py
└── trainer.py

Compiler/Interface Dependencies

아래를 적절하게 수정

  • Tensorflow >=1.9
  • Python2 <= 2.7.12
  • Python3 <= 3.6.0

Related Materials

Feedback

License

  • Apach License 2.0

Authors information

  • Jaewook Kang Ph.D.

  • Chanhee Jeong

여기 추가 바람요

tf-keras-rnn-time-pred's People

Contributors

jwkangmarco avatar

Watchers

Chanhee Jeong avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.