private_prediction.py [391:408]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    num_classes = int(data["train"]["targets"].max()) + 1
    num_samples, num_features = data["train"]["features"].size()
    model = modeling.initialize_model(num_features, num_classes, device=args.device)
    criterion = nn.CrossEntropyLoss()
    regularized_criterion = modeling.add_l2_regularization(
        criterion, model, args.weight_decay
    )

    # train classifier:
    logging.info("Training non-private classifier...")
    modeling.train_model(model, data["train"],
                         criterion=regularized_criterion,
                         optimizer=args.optimizer,
                         num_epochs=args.num_epochs,
                         learning_rate=args.learning_rate,
                         batch_size=args.batch_size,
                         visualizer=visualizer,
                         title=title)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



private_prediction.py [448:465]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    num_classes = int(data["train"]["targets"].max()) + 1
    num_samples, num_features = data["train"]["features"].size()
    model = modeling.initialize_model(num_features, num_classes, device=args.device)
    criterion = nn.CrossEntropyLoss()
    regularized_criterion = modeling.add_l2_regularization(
        criterion, model, args.weight_decay
    )

    # train classifier:
    logging.info("Training non-private classifier...")
    modeling.train_model(model, data["train"],
                         criterion=regularized_criterion,
                         optimizer=args.optimizer,
                         num_epochs=args.num_epochs,
                         learning_rate=args.learning_rate,
                         batch_size=args.batch_size,
                         visualizer=visualizer,
                         title=title)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -