(train_x, train_y), (test_x, test_y) = load_data(ds=tf.keras.datasets.fashion_mnist) Creating and Compiling the Model The create_model() function, described below, uses the standard tensorflow APIs to create

model using the ground-truth labels. The distillation_loss_fn is used as the loss function when compiling the model, and the categorical_accuracy method is used as the metric. This is pretty much all there