Skip to content

deeplearningzerotoall/PyTorch

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

96 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

모두를 위한 딥러닝 시즌2 : 모두가 만드는 모두를 위한 딥러닝

모두가 만드는 모두를 위한 딥러닝 시즌 2에 오신 여러분들 환영합니다.

Getting Started

아래 링크에서 슬라이드와 영상을 통해 학습을 시작할 수 있습니다.

Docker 사용자를 위한 안내

동일한 실습 환경을 위해 docker 를 사용하실 분은 docker_user_guide.md 파일을 참고하세요! :)

Install Requirements

pip install -r requirements.txt

Install PyTorch from website: https://pytorch.org/


PyTorch

Deep Learning Zero to All - PyTorch

모든 코드는 PyTorch 1.0.0 기준으로 작성하였습니다.

Contributions/Comments

언제나 여러분들의 참여를 환영합니다. Comments나 Pull requests를 남겨주세요

We always welcome your comments and pull requests

목차

PART 1: Machine Learning & PyTorch Basic

  • Lab-01-1 Tensor Manipulation 1
  • Lab-01-2 Tensor Manipulation 2
  • Lab-02 Linear regression
  • Lab-03 Deeper Look at GD
  • Lab-04-1 Multivariable Linear regression
  • Lab-04-2 Loading Data
  • Lab-05 Logistic Regression
  • Lab-06 Softmax Classification
  • Lab-07-1 Tips
  • Lab-07-2 MNIST Introduction

PART 2: Neural Network

  • Lab-08-1 Perceptron
  • Lab-08-2 Multi Layer Perceptron
  • Lab-09-1 ReLU
  • Lab-09-2 Weight initialization
  • Lab-09-3 Dropout
  • Lab-09-4 Batch Normalization

PART 3: Convolutional Neural Network

  • Lab-10-0 Convolution Neural Networkintro
  • Lab-10-1 Convolution
  • Lab-10-2 mnist cnn
  • Lab-10-3 visdom
  • Lab-10-4-1 ImageFolder1
  • Lab-10-4-2 ImageFolder2
  • Lab-10-5 Advance CNN(VGG)
  • Lab-10-6-1 Advanced CNN(RESNET-1)
  • Lab-10-6-2 Advanced CNN(RESNET-2)
  • Lab-10-7 Next step of CNN

PART 4: Recurrent Neural Network

  • Lab-11-0 RNN intro
  • Lab-11-1 RNN basics
  • Lab-11-2 RNN hihello and charseq
  • Lab-11-3 Long sequence
  • Lab-11-4 RNN timeseries
  • Lab-11-5 RNN seq2seq
  • Lab-11-6 PackedSequence