Coder Social home page Coder Social logo

changjinhan / tensorflow Goto Github PK

View Code? Open in Web Editor NEW

This project forked from deeplearningzerotoall/tensorflow

0.0 1.0 0.0 1.53 MB

๐Ÿ“ Deep Learning Zero to All - Tensorflow

Jupyter Notebook 97.29% Python 2.48% Dockerfile 0.23% Shell 0.01%

tensorflow's Introduction

๋ชจ๋‘๋ฅผ ์œ„ํ•œ ๋”ฅ๋Ÿฌ๋‹ ์‹œ์ฆŒ 2 : ๋ชจ๋‘๊ฐ€ ๋งŒ๋“œ๋Š” ๋ชจ๋‘๋ฅผ ์œ„ํ•œ ๋”ฅ๋Ÿฌ๋‹

๋ชจ๋‘๊ฐ€ ๋งŒ๋“œ๋Š” ๋ชจ๋‘๋ฅผ ์œ„ํ•œ ๋”ฅ๋Ÿฌ๋‹ ์‹œ์ฆŒ 2์— ์˜ค์‹  ์—ฌ๋Ÿฌ๋ถ„๋“ค ํ™˜์˜ํ•ฉ๋‹ˆ๋‹ค.

Getting Started

์•„๋ž˜ ๋งํฌ์—์„œ ์Šฌ๋ผ์ด๋“œ์™€ ์˜์ƒ์„ ํ†ตํ•ด ํ•™์Šต์„ ์‹œ์ž‘ํ•  ์ˆ˜ ์žˆ์Šต๋‹ˆ๋‹ค.

Docker ์‚ฌ์šฉ์ž๋ฅผ ์œ„ํ•œ ์•ˆ๋‚ด

๋™์ผํ•œ ์‹ค์Šต ํ™˜๊ฒฝ์„ ์œ„ํ•ด docker๋ฅผ ์‚ฌ์šฉํ•˜์‹ค ๋ถ„์€ docker_user_guide.md ํŒŒ์ผ์„ ์ฐธ๊ณ ํ•˜์„ธ์š”! :)

Install Requirements

pip install -r requirements.txt

TensorFlow

Deep Learning Zero to All - TensorFlow

๋ชจ๋“  ์ฝ”๋“œ๋Š” Tensorflow 1.12(stable)๋ฅผ ๊ธฐ๋ฐ˜์œผ๋กœ ์ž‘์„ฑํ–ˆ์œผ๋ฉฐ Tensorflow 2.0์ด ์ถœ์‹œ๋˜๋Š” ๋Œ€๋กœ ์ถ”ํ›„ ๋ฐ˜์˜ํ•  ์˜ˆ์ •์ž…๋‹ˆ๋‹ค.

Standarad of Code

์ฝ”๋“œ๋Š” Tensorflow ๊ณต์‹ ํ™ˆํŽ˜์ด์ง€ ๊ถŒ์žฅ์— ๋”ฐ๋ผ Keras + Eager๋กœ ์ž‘์„ฑํ–ˆ์œผ๋ฉฐ

Session ๋ฒ„์ „์€ code_session_version / Keras ๋ฒ„์ „์€ other์—์„œ ํ™•์ธํ•˜์‹ค ์ˆ˜ ์žˆ์Šต๋‹ˆ๋‹ค.

Contributions/Comments

์–ธ์ œ๋‚˜ ์—ฌ๋Ÿฌ๋ถ„๋“ค์˜ ์ฐธ์—ฌ๋ฅผ ํ™˜์˜ํ•ฉ๋‹ˆ๋‹ค. Comments๋‚˜ Pull requests๋ฅผ ๋‚จ๊ฒจ์ฃผ์„ธ์š”.

We always welcome your comments and pull requests.

๋ชฉ์ฐจ

PART 1: Basic Machine Learning

  • Lec 01: ๊ธฐ๋ณธ์ ์ธ Machine Learning์˜ ์šฉ์–ด์™€ ๊ฐœ๋… ์„ค๋ช…
  • Lab 01: (์ถ”๊ฐ€ ์˜ˆ์ •)
  • Lec 02: Simple Linear Regression
  • Lab 02: Simple Linear Regression๋ฅผ TensorFlow๋กœ ๊ตฌํ˜„ํ•˜๊ธฐ
  • Lec 03: Linear Regression and How to minimize cost
  • Lab 03: Linear Regression and How to minimize cost๋ฅผ TensorFlow๋กœ ๊ตฌํ˜„ํ•˜๊ธฐ
  • Lec 04: Multi-variable Linear Regression
  • Lab 04: Multi-variable Linear Regression๋ฅผ TensorFlow๋กœ ๊ตฌํ˜„ํ•˜๊ธฐ
  • Lec 05-1: Logistic Regression/Classification์˜ ์†Œ๊ฐœ
  • Lec 05-2: Logistic Regression/Classification์˜ cost ํ•จ์ˆ˜, ์ตœ์†Œํ™”
  • Lab 05-3: Logistic Regression/Classification๋ฅผ TensorFlow๋กœ ๊ตฌํ˜„ํ•˜๊ธฐ
  • Lec 06-1: Softmax Regression: ๊ธฐ๋ณธ ๊ฐœ๋… ์†Œ๊ฐœ
  • Lec 06-2: Softmax Classifier์˜ cost ํ•จ์ˆ˜
  • Lab 06-1: Softmax classifier๋ฅผ TensorFlow๋กœ ๊ตฌํ˜„ํ•˜๊ธฐ
  • Lab 06-2: Fancy Softmax classifier๋ฅผ TensorFlow๋กœ ๊ตฌํ˜„ํ•˜๊ธฐ
  • Lab 07-1: Application & Tips: ํ•™์Šต๋ฅ (Learning Rate)๊ณผ ๋ฐ์ดํ„ฐ ์ „์ฒ˜๋ฆฌ(Data Preprocessing)
  • Lab 07-2-1: Application & Tips: ์˜ค๋ฒ„ํ”ผํŒ…(Overfitting) & Solutions
  • Lab 07-2-2: Application & Tips: ํ•™์Šต๋ฅ , ์ „์ฒ˜๋ฆฌ, ์˜ค๋ฒ„ํ”ผํŒ…์„ TensorFlow๋กœ ์‹ค์Šต
  • Lab 07-3-1: Application & Tips: Data & Learning
  • Lab 07-3-2: Application & Tips: ๋‹ค์–‘ํ•œ Dataset์œผ๋กœ ์‹ค์Šต

PART 2: Basic Deep Learning

  • Lec 08-1: ๋”ฅ๋Ÿฌ๋‹์˜ ๊ธฐ๋ณธ ๊ฐœ๋…: ์‹œ์ž‘๊ณผ XOR ๋ฌธ์ œ
  • Lec 08-2: ๋”ฅ๋Ÿฌ๋‹์˜ ๊ธฐ๋ณธ ๊ฐœ๋… 2: Back-propagation ๊ณผ 2006/2007 '๋”ฅ'์˜ ์ถœํ˜„
  • Lec 09-1: XOR ๋ฌธ์ œ ๋”ฅ๋Ÿฌ๋‹์œผ๋กœ ํ’€๊ธฐ
  • Lec 09-2: ๋”ฅ๋„ทํŠธ์› ํ•™์Šต ์‹œํ‚ค๊ธฐ (backpropagation)
  • Lab 09-1: Neural Net for XOR
  • Lab 09-2: Tensorboard (Neural Net for XOR)
  • Lab 10-1: Sigmoid ๋ณด๋‹ค ReLU๊ฐ€ ๋” ์ข‹์•„
  • Lab 10-2: Weight ์ดˆ๊ธฐํ™” ์ž˜ํ•ด๋ณด์ž
  • Lab 10-3: Dropout
  • Lab 10-4: Batch Normalization

PART 3: Convolutional Neural Network

  • Lec 11-1: ConvNet์˜ Conv ๋ ˆ์ด์–ด ๋งŒ๋“ค๊ธฐ
  • Lec 11-2: ConvNet Max pooling ๊ณผ Full Network
  • Lec 11-3: ConvNet์˜ ํ™œ์šฉ ์˜ˆ
  • Lab 11-0-1: CNN Basic: Convolution
  • Lab 11-0-2: CNN Basic: Pooling
  • Lab 11-1: mnist cnn keras sequential eager
  • Lab 11-2: mnist cnn keras functional eager
  • Lab-11-3: mnist cnn keras subclassing eager
  • Lab-11-4: mnist cnn keras ensemble eager
  • Lab-11-5: mnist cnn best keras eager

PART 4: Recurrent Neural Network

  • Lec 12: NN์˜ ๊ฝƒ RNN ์ด์•ผ๊ธฐ
  • Lab 12-0: rnn basics
  • Lab 12-1: many to one (word sentiment classification)
  • Lab 12-2: many to one stacked (sentence classification, stacked)
  • Lab 12-3: many to many (simple pos-tagger training)
  • Lab 12-4: many to many bidirectional (simpled pos-tagger training, bidirectional)
  • Lab 12-5: seq to seq (simple neural machine translation)
  • Lab 12-6: seq to seq with attention (simple neural machine translation, attention)

ํ•จ๊ป˜ ๋งŒ๋“  ์ด๋“ค

Main Instructor

Main Creator

Docker Developer

Support

  • ๋„ค์ด๋ฒ„ ์ปค๋„ฅํŠธ์žฌ๋‹จ : ์ดํšจ์€, ์žฅ์ง€์ˆ˜, ์ž„์šฐ๋‹ด

tensorflow's People

Contributors

danpatpang avatar financedata avatar healess avatar juneoh avatar jwlee-ml avatar lzino avatar rainmaker712 avatar seopbo avatar simonjisu avatar taki0112 avatar y2o2u2n avatar zagoshipda avatar

Watchers

 avatar

Recommend Projects

  • React photo React

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

  • Vue.js photo Vue.js

    ๐Ÿ–– 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. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

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 โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.