tensorflow 예제 및 실용 코드

tensorflow는 모델을 기반으로 학습하고 그 데이터를 예측하는 시스템으로 분석된다.

해당건에 대하여 학습시키려면 실용 예제가 필요한데

좋은 예제는 아래를 보면 될듯..

https://github.com/aymericdamien/TensorFlow-Examples

1개씩 봐야지..

TensorFlow Examples

TensorFlow Tutorial with popular machine learning algorithms implementation. This tutorial was designed for easily diving into TensorFlow, through examples.

It is suitable for beginners who want to find clear and concise examples about TensorFlow. For readability, the tutorial includes both notebook and code with explanations.

Note: If you are using older TensorFlow version (before 0.12), please have a look here

Tutorial index

0 – Prerequisite

  • Introduction to Machine Learning (notebook)
  • Introduction to MNIST Dataset (notebook)

1 – Introduction

2 – Basic Models

3 – Neural Networks

4 – Utilities

  • Save and Restore a model (notebook) (code)
  • Tensorboard – Graph and loss visualization (notebook) (code)
  • Tensorboard – Advanced visualization (code)

5 – Multi GPU

Dataset

Some examples require MNIST dataset for training and testing. Don’t worry, this dataset will automatically be downloaded when running examples (with input_data.py). MNIST is a database of handwritten digits, for a quick description of that dataset, you can check this notebook.

Official Website: http://yann.lecun.com/exdb/mnist/

More Examples

The following examples are coming from TFLearn, a library that provides a simplified interface for TensorFlow. You can have a look, there are many examples and pre-built operations and layers.

Tutorials

  • TFLearn Quickstart. Learn the basics of TFLearn through a concrete machine learning task. Build and train a deep neural network classifier.

Basics

Computer Vision

Natural Language Processing

Reinforcement Learning

Others

Notebooks

Extending TensorFlow

  • Layers. Use TFLearn layers along with TensorFlow.
  • Trainer. Use TFLearn trainer class to train any TensorFlow graph.
  • Built-in Ops. Use TFLearn built-in operations along with TensorFlow.
  • Summaries. Use TFLearn summarizers along with TensorFlow.
  • Variables. Use TFLearn variables along with TensorFlow.

Dependencies

tensorflow 1.0alpha
numpy
matplotlib
cuda
tflearn (if using tflearn examples)

For more details about TensorFlow installation, you can check TensorFlow Installation Guide

Tensorflow Study

TensorFlow는 Apache 2.0  기반의 오픈소스 프레임워크 이다.

현재 진행상황으로는, tensorflow를 사용하기 위한 환경 조성은 OK인데…

이것을 어떻게 적용할까?? 라는 의문점은 사라지지 않는다.

(왜냐니, How to learn ML using tensorflow.)

그래서 좀 찾아봤더니 이런 것이 있더라.

1. 텐서 플로우 설치도 했고, 튜토리얼도 봤고, 기초 예제도 짜봤다면..

2. 텐서 플로우의background, Tutorial – Logistic regression, CNN, RNN

(아 이건 Neural 신경망쪽 인데… 이건 좀 study를 심도있게 고려를 해봐야 겠다.)

3. 텐서 플로우의 예제들, 그리고 파이썬 함수를 찾는데 참조한 것들.

https://github.com/nlintz/TensorFlow-Tutorials/

https://docs.scipy.org/doc/numpy/reference/

텐서플로우 Study를 위한 pdf정보, pptx (다 원서이다..)

– 원서PDF

http://www.jorditorres.org/wp-content/uploads/2016/02/LibroTF.english.PART0_RevByRTOUS.pdf

– 원서PDF를 PPTX로

https://github.com/jorditorresBCN/FirstContactWithTensorFlow

https://github.com/jorditorresBCN

First Contact with TensorFlow

http://jorditorres.org/?s=FirstContactWithTensorFlow

(한국어로 번역한 자료가 있긴한데, 원서 읽고 나중에 참조해봐야겠다..)

설치 튜토리얼은 OK, 그런데 머신러닝은 HOW?

 

우선 아래꺼 부터 봐야겠다.. 영어로 되어있는데, PPT내용이 훌륭해..

http://www.jorditorres.org/wp-content/uploads/2016/02/FirstContactWithTensorFlow.part1_.pdf