Java Deep Learning Projects

Restoring the trained model and evaluating it on the test set

Once the training has been completed, the next task will be to evaluate the model. We will evaluate the model's performance on the test set. For the evaluation, we will be using Evaluation(), which creates an evaluation object with two possible classes.

First, let's iterate the evaluation on every test sample and get the network's prediction from the trained model. Finally, the eval() method checks the prediction against the true class:

public static void networkEvaluator() throws Exception {      System.out.println("Starting the evaluation ...");      boolean saveUpdater = true;      //Load the model      MultiLayerNetwork restoredModel = ModelSerializer.restoreMultiLayerNetwork(modelPath, saveUpdater); ...