Skip to content

old-julia-codes/DDL.jl

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

9 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

DDL.jl

  • This package aims to provide utilities for working with any kind of data for Machine Learning (Deep Learning specifically)
  • The main objective is to have a data loader of sorts which works with Flux.jl for any data
  • This package also provides easy ways of downloading standard datasets from Computer Vision, Natural Language processing etc

Documentation!!

  • Please go to this link : Docs

Features (So far; I need it for my research so more is being added every day)

Planned features -> roadmap

  • Direct download of commonly used datasets for Computer vision, NLP etc(Beyond CIFAR and MNIST -.-) [Courtesy fastai]
  • Image loader from multiple folders, CSV files
  • Labeller based on file paths/custom functions
  • Labeller based on patterns
  • Label encoder
  • Flux compatible data loader (aka use this library to load the data -> do whatever you want in Flux)