Giter VIP home page Giter VIP logo

dlvc2017's Introduction

DLVC2017

This repository contains tutorials and resources for the Deep Learning for Visual Computing summer school 2017.

Torch7 documentation: http://torch.ch/
More tutorials on torch: http://torch.ch/docs/tutorials.html

Day 1

Tutorial 1: Python for Visual Computing

 File: tut01-Python for Visual Computing.ipynb

Tutorial 2: MNIST Digits Classification (Classical Approach).

 File: tut02-MNIST Digits Classification (Classical Approach).ipynb

Link to download data.

Tutorial 3: ImageNet Classification (Classical Approach)

 File1_v1: tut03-ImageNet Classification (Classical Approach).ipynb
 File1_v2: tut03.py

Link to download full dataset
Link to download truncated dataset (10 classes,train images only)

Day 2

Tutorial 4: Torch for Deep Neural Networks

File1: 1_Tensors.lua 
File2: 2_NeuralNet.lua
File3: 3_NNtrain.lua
File4: myNet.lua (support code for 3_NNtrain.lua)

Reference for tutorial 4: https://github.com/soumith/cvpr2015/blob/master/Deep%20Learning%20with%20Torch.ipynb

Tutorial 5: MNIST Digits Classification (Autoencoders)

File1: AE_approach2.lua (Full training of autorncoder (AE))

Day 3

Tutorial 7: ImageNet-Tiny Classification (Autoencoders)

 File1: SDSAE_approach1.lua (Layer-wise training of Stacked Denoising Sparse AE)

Tutorial 8: Cost Functions and their Properties & Tutorial 9: Stochastic Gradient Descent and Learning Rate Dynamic

 File1: main_loss.lua     
 File2: 1_abs.lua
 File3: 2_smoothabs.lua
 File4: 3_MSE.lua
 File5: main_optim.lua
 File6: 3_MSE_SGD.lua
 File7: 3_MSE_adagrad.lua
 File8: 3_MSE_adam.lua

Day 4

Tutorial 10: MNIST Cifar10 Classification (LeNet)

 File: tut10_LeNet.lua

Link to download data.

Tutorial 11: ImageNet Classification (AlexNet)

 File1: trainAlexNet.lua
 File2: generate_filenames.cpp

Link to download full dataset
Link to download truncated dataset (10 classes,train images only)

Tutorial 12: Learning Rules and Batch Updates

 File: tut12_LeNet_batchWise.lua

Link to download data.

Day 5

 File: generate_filenames.cpp

Tutorial 13: ImageNet Classification (VGGNet)

 File: tut13_trainVgg.lua

Link to download full dataset
Link to download truncated dataset (10 classes,train images only)

Tutorial 14: ImageNet Classification (GoogLeNet)

 File: tut14_trainIncep.lua

Link to download full dataset
Link to download truncated dataset (10 classes,train images only)

Tutorial 15: ImageNet Classification (ResNet / DenseNet)

 File: tut15_trainResnet18.lua

Link to download full dataset
Link to download truncated dataset (10 classes,train images only)

dlvc2017's People

Contributors

rachana-sathish avatar

Watchers

James Cloos avatar  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.