Playing with Java Deep Learning (DJL), tutorial-01 / published by https://github.com/dacr/code-examples-manager #15d7706b-fdc7-4aab-a788-8a2262c5d189/e04f21877e2c9f4627a94b3d14de186db3f9c4a7

djl-tutorial-01.sc

// summary : Playing with Java Deep Learning (DJL), tutorial-01
// keywords : djl, machine-learning, tutorial, ai, @testable
// publish : gist
// authors : David Crosson
// license : Apache NON-AI License Version 2.0 (https://raw.githubusercontent.com/non-ai-licenses/non-ai-licenses/main/NON-AI-APACHE2)
// id : 15d7706b-fdc7-4aab-a788-8a2262c5d189
// created-on : 2021-03-05T09:23:01Z
// managed-by : https://github.com/dacr/code-examples-manager
// run-with : scala-cli $file

// ---------------------
//> using scala "3.4.2"
//> using dep "org.slf4j:slf4j-api:2.0.13"
//> using dep "org.slf4j:slf4j-simple:2.0.13"
//> using dep "ai.djl:api:0.28.0"
// ---------------------


// inspired from https://docs.djl.ai/jupyter/tutorial/01_create_your_first_network.html

import ai.djl._
import ai.djl.nn._
import ai.djl.nn.core._
import ai.djl.training._


val application = Application.CV.IMAGE_CLASSIFICATION
val inputSize = 28*28
val outputSize = 10

val block = new SequentialBlock()

block.add(Blocks.batchFlattenBlock(inputSize))
block.add(Linear.builder().setUnits(128).build())
block.add(arr => Activation.relu(arr))
block.add(Linear.builder().setUnits(64).build())
block.add(arr => Activation.relu(arr))
block.add(Linear.builder().setUnits(outputSize).build())

println(block)