Callbacks (EarlyStopping, ModelCheckpoint) in TensorFlow - Practice Problems & Coding Challenges

Challenge - 5 Problems

❓ Predict Output

intermediate

What is the output of this EarlyStopping callback configuration?

Consider the following code snippet for training a TensorFlow model with EarlyStopping callback:

early_stop = tf.keras.callbacks.EarlyStopping(monitor='val_loss', patience=3, restore_best_weights=True)
model.fit(x_train, y_train, epochs=20, validation_data=(x_val, y_val), callbacks=[early_stop])

What will happen if the validation loss does not improve for 4 consecutive epochs?

A Training stops after 3 epochs without improvement, and model weights are restored to the best epoch.

B Training continues for all 20 epochs regardless of validation loss.

C Training stops after 4 epochs without improvement, and model weights are restored to the best epoch.

D Training stops immediately after the first epoch without improvement, and weights are not restored.

💡 Hint

Patience defines how many epochs to wait after last improvement before stopping.

The EarlyStopping callback stops training after 'patience' epochs without improvement. Here, patience=3 means training stops after 3 epochs without val_loss improvement. Since restore_best_weights=True, the model weights revert to the best epoch's weights.

❓ Model Choice

intermediate

Which ModelCheckpoint option saves the model only when validation accuracy improves?

You want to save your TensorFlow model only when the validation accuracy improves during training. Which ModelCheckpoint callback configuration achieves this?

A tf.keras.callbacks.ModelCheckpoint('model.h5', monitor='val_accuracy', save_best_only=False, mode='max')

B tf.keras.callbacks.ModelCheckpoint('model.h5', monitor='val_accuracy', save_best_only=True, mode='max')

C tf.keras.callbacks.ModelCheckpoint('model.h5', monitor='accuracy', save_best_only=False)

D tf.keras.callbacks.ModelCheckpoint('model.h5', monitor='val_loss', save_best_only=True, mode='min')

💡 Hint

You want to monitor validation accuracy and save only the best model.

To save the model only when validation accuracy improves, monitor='val_accuracy', save_best_only=True, and mode='max' (because higher accuracy is better) are required.

❓ Hyperparameter

advanced

What is the effect of setting 'restore_best_weights=False' in EarlyStopping?

In the EarlyStopping callback, what happens if you set restore_best_weights=False and training stops due to no improvement?

A The model weights remain as they were at the last epoch before stopping, not necessarily the best.

B The model weights are reset to the initial random weights before training.

C The model weights are restored to the best epoch's weights automatically.

D Training restarts from the best epoch automatically.

💡 Hint

Consider what happens to weights if you do not restore best weights.

If restore_best_weights=False, when EarlyStopping stops training, the model keeps the weights from the last epoch run, which may not be the best performing weights.

🔧 Debug

advanced

Why does this ModelCheckpoint callback not save any model files?

Given this callback:

checkpoint = tf.keras.callbacks.ModelCheckpoint('best_model.h5', monitor='val_accuracy', save_best_only=True, mode='min')

and training where validation accuracy improves, why might no model files be saved?

A Because monitor='val_accuracy' is not a valid metric name.

B Because save_best_only=True disables saving any model files.

C Because mode='min' expects validation accuracy to decrease, so no improvement is detected.

D Because the file path 'best_model.h5' is invalid and causes silent failure.

💡 Hint

Think about whether validation accuracy should increase or decrease for improvement.

Validation accuracy improves by increasing, but mode='min' tells ModelCheckpoint to look for decreases. So it never detects improvement and never saves the model.

🧠 Conceptual

expert

Why combine EarlyStopping with ModelCheckpoint in training?

What is the main advantage of using both EarlyStopping and ModelCheckpoint callbacks together during model training?

A Both callbacks perform the same function, so using both doubles the saving frequency.

B EarlyStopping saves the model after every epoch, and ModelCheckpoint stops training when performance degrades.

C EarlyStopping increases training epochs, and ModelCheckpoint deletes old models automatically.

D EarlyStopping stops training early to avoid overfitting, while ModelCheckpoint saves the best model weights during training.

💡 Hint

Think about how each callback helps training and model saving.

EarlyStopping helps stop training when no improvement occurs to prevent overfitting and save time. ModelCheckpoint saves the best model weights so you can load the best version later. Together, they ensure efficient training and best model preservation.