README

Start here

Library

Reference

Tutorials

Other

Getting started

In FluxTraining, a Learner holds all state necessary for training. To get started, you need

Models and datasets are not included with FluxTraining.jl, so see ecosystem for supporting packages.

Let’s look at a simple training example.

First we define the necessary pieces:

model = ...
traindata, valdata = ...
lossfn = Flux.Losses.mse
opt = Flux.ADAM(0.01)

Then we construct a Learner:

learner = Learner(model, (traindata, valdata), opt, lossfn)

And train for 10 epochs:

fit!(learner, 10)