我正在嘗試使用 MNIST 數據集訓練深度神經網絡，這是我的 jupyter notebook 的一些代碼：第一個塊工作正常：# Select the hyperparameter batch sizeBATCH_SIZE = 100# Batch the train, validatiion and test datatrain_data = train_data.batch(BATCH_SIZE)validation_data = validation_data.batch(num_validation_samples)test_data = test_data.batch(num_test_samples)# Transform the validation data into tuples for the inputs and targetsvalidation_inputs, validation_targets = next(iter(validation_data))# Defining model hyperparametersinput_size = 784output_size = 10hidden_layer_size = 50# Defining the modelmodel = tf.keras.Sequential([    tf.keras.layers.Flatten(input_shape=(28, 28, 1)),    tf.keras.layers.Dense(hidden_layer_size, activation='relu'),    tf.keras.layers.Dense(hidden_layer_size, activation='relu'),    tf.keras.layers.Dense(output_size, activation='softmax')])# Select the optimizer algorithm and the loss functionmodel.compile(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['accuracy'])