Load DL4J model checkpoint and continue training.

ContinueTrainingFromCheckpoint.java

// Train your model and save the model if the training loss is better than the previous. Set saveUpdater boolean as "true" if you plan to continue training. Needed for updaters like Adam.
for (int i = 1; i < epochs + 1; i++) {
    tunedModel.fit(trainIterator);
    if (tunedModel.score() < lowest) {
        lowest = tunedModel.score();
        String modelFilename = new File(".").getAbsolutePath() + "/ImageClassifier_loss" + lowest + "_ep" + i + ".zip";
        ModelSerializer.writeModel(tunedModel, modelFilename, true);
    }
    System.out.println(String.format("Completed epoch %d.", i));
}

//Load your model and continue to train, remember to set loadUpdater as "true".
tunedModel = ModelSerializer.restoreComputationGraph("ImageClassifier_loss0.38684930801391604_ep100_ResNet50.zip", true);

//Reuse the training block earlier.
int previousEpoch = 100
for (int i = 1+previousEpoch; i < epochs +previousEpoch+ 1; i++) {
    tunedModel.fit(trainIterator);
    if (tunedModel.score() < lowest) {
        lowest = tunedModel.score();
        String modelFilename = new File(".").getAbsolutePath() + "/ImageClassifier_loss" + lowest + "_ep" + i + ".zip";
        ModelSerializer.writeModel(tunedModel, modelFilename, true);
    }
    System.out.println(String.format("Completed epoch %d.", i));
}