Giter Club home page Giter Club logo

imagenetloader.torch's Introduction

imagenetloader.torch

some old code that i wrote, might be useful to others.

If your dataset is of the form:

  • dogs/[image files of dogs]
  • cats/[image files of cats]
  • .
  • .
  • .

then this loader loads the dataset nicely, and you have class-balanced sampling, a test iterator and other useful things.

I also used it to load imagenet (both the 1.2million set and the 14 million full imagenet).

imagenetloader.torch's People

Contributors

soumith avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

imagenetloader.torch's Issues

require 'chex'

Could you please state the dependencies for resolving an error caused bei require 'chex':

th testDataset.lua 
/usr/local/bin/luajit: /usr/local/share/lua/5.1/trepl/init.lua:383: module 'chex' not found:No Luarockt module found for chex

Thank you!

Does it work with mac osx?

I would like to read images from desk and save them in Torch's format to use for classification problem and I found this code but I do not know if this works with osx operating system. By the way, my data saved in folders as same as described here.

Please, waiting for help

Run w/o GPUs?

Hi,

Thanks for sharing your work! I want run on it on my cheap Windows 7 desktop, which I plan to do with Cygwin. Will it break if I don't have the GPUs?

I have Windows 7, 32-bit, Core i5, 2.6 GHz, 4 GB RAM. Am I hopeless?

can't open .sh file

Hey! I'm would to be training some resnet models using this imagenet dataset
So i've git cloned imagenetloader.torch to my PC (os: windows10)
But when i'm launch valprep.sh file it doesn't work
All folders are creating, but jpges cannot load to my folders
error looks like mv: cannot stat no such file or directory
Any sugestions?

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.