lacic

<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
	xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
	<modelVersion>4.0.0</modelVersion>
	<groupId>com.dl4j.test.project</groupId>
	<artifactId>dl4j-lib</artifactId>
	<version>1.0-SNAPSHOT</version>

	<name>DL Lib</name>
	<description>Forecasting lib using dl4j</description>
	<properties>

lacic

package com.issue2548;

import org.deeplearning4j.nn.multilayer.MultiLayerNetwork;
import org.nd4j.linalg.api.buffer.DataBuffer;
import org.nd4j.linalg.api.buffer.util.DataTypeUtil;
import org.nd4j.linalg.api.ndarray.INDArray;
import org.nd4j.linalg.dataset.api.preprocessor.NormalizerStandardize;
import org.nd4j.linalg.factory.Nd4j;

import java.io.BufferedReader;

lacic

9
10

lacic

8
9

lacic

2
3
4
5
6
7
8

lacic

1
2
3
4
5
6
7

lacic

public class EvaluationExample {

	public static void main(String... args) {
		// where are the trained model and the corresponding normalizers stored ?
		String modelPath = "data" + File.separator + "models" + File.separator;
		String normalizerPath = "data" + File.separator + "normalizers" + File.separator;

		String modelName = "train.model";

		// define the paths to the train features, test features and test labels

lacic

public class TrainExample {

	public static final int BATCH_SIZE = 100;
	public static final int N_EPOCHS = 150;


	public static void main(String... args) {
		// define some paths where you would like to store the model
		String modelPath = "data" + File.separator + "models" + File.separator;
		String normalizerPath = "data" + File.separator + "normalizers" + File.separator;

lacic

public class SerializationUtils {

	private final Logger logger = LoggerFactory.getLogger(getClass());

	private String modelPath;
	private String modelName;
	private String normalizerPath;
	private String configName;

	public SerializationUtils(String modelPath, String modelName, String normalizerPath) {

lacic

	hiddenWidth = 20;
		
		MultiLayerConfiguration conf = new NeuralNetConfiguration.Builder()
				.optimizationAlgo(OptimizationAlgorithm.STOCHASTIC_GRADIENT_DESCENT).iterations(1)
				.learningRate(0.05476383804339002) // 0.02 with BPTT
				.momentum(0.5358333571512998)
				.seed(12345)
				.regularization(true)
				.l2(0.016384859214629816)
				.dropOut(0.8145498131858961)