StatsListener怎么使用
本文主要介绍"StatsListener如何使用",希望能够解决您遇到有关问题,下面我们一起来看这篇 "StatsListener如何使用" 文章。
import org.deeplearning4j.api.storage.StatsStorage; import org.deeplearning4j.examples.userInterface.util.UIExampleUtils; import org.deeplearning4j.nn.multilayer.MultiLayerNetwork; import org.deeplearning4j.optimize.listeners.ScoreIterationListener; import org.deeplearning4j.ui.api.UIServer; import org.deeplearning4j.ui.stats.StatsListener; import org.deeplearning4j.ui.storage.FileStatsStorage; import org.nd4j.linalg.dataset.api.iterator.DataSetIterator; import java.io.File; /** * A version of UIStorageExample showing how to saved network training data to a file, and then * reload it later, to display in in the UI * * @author Alex Black */ public class UIStorageExample { public static void main(String[] args){ //Run this example twice - once with collectStats = true, and then again with collectStats = false boolean collectStats = true; if(collectStats){ //First run: Collect training stats from the network //Note that we don't have to actually plot it when we collect it - though we can do that too, if required MultiLayerNetwork net = UIExampleUtils.getMnistNetwork(); DataSetIterator trainData = UIExampleUtils.getMnistData(); StatsStorage statsStorage = new FileStatsStorage(new File(System.getProperty("java.io.tmpdir"), "ui-stats.dl4j")); net.setListeners(new StatsListener(statsStorage), new ScoreIterationListener(10)); net.fit(trainData); System.out.println("Done"); } else { //Second run: Load the saved stats and visualize. Go to http://localhost:9000/train StatsStorage statsStorage = new FileStatsStorage(new File(System.getProperty("java.io.tmpdir"), "ui-stats.dl4j")); UIServer uiServer = UIServer.getInstance(); uiServer.attach(statsStorage); } } }
关于 "StatsListener如何使用" 就介绍到这。希望大家多多支持编程宝库。
本文主要介绍"pytorch的安装命令",希望能够解决您遇到有关问题,下面我们一起来看这篇 "pytorch的安装命令" 文章。安装GPU版pytorchconda install pytorch torchvis ...