Skip to content

Repository of best practices for deep learning in Julia, inspired by fastai

License

Notifications You must be signed in to change notification settings

dave7895/FastAI.jl

This branch is 10 commits ahead of, 223 commits behind FluxML/FastAI.jl:master.

Folders and files

NameName
Last commit message
Last commit date
Feb 5, 2021
Mar 27, 2021
Mar 27, 2021
Mar 8, 2021
Feb 3, 2021
Feb 20, 2021
Mar 8, 2021
Mar 8, 2021
Mar 25, 2021
Feb 23, 2021
Mar 27, 2021
Aug 17, 2020
Mar 13, 2021

Repository files navigation

FastAI

Documentation

FastAI.jl is inspired by fastai, and is a repository of best practices for deep learning in Julia. Its goal is to easily enable creating state-of-the-art models. FastAI enables the design, training, and delivery of deep learning models that compete with the best in class, using few lines of code.

As an example, training an image classification model from scratch is as simple as

using FastAI
path = datasetpath("imagenette2-160")
data = loadtaskdata(path, ImageClassificationTask)
method = ImageClassification(Datasets.loadclassesclassification("imagenette2-160"), (160, 160))
learner = methodlearner(method, data, Models.xresnet18(), ToGPU(), Metrics(accuracy))
fitonecycle!(learner, 5)

Please read the documentation for more information and see the setup instructions.

About

Repository of best practices for deep learning in Julia, inspired by fastai

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Julia 100.0%