Accuracy and loss monitoring in TensorFlow - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to print the training accuracy after each epoch.

TensorFlow

model.fit(x_train, y_train, epochs=5, callbacks=[tf.keras.callbacks.LambdaCallback(on_epoch_end=lambda epoch, logs: print('Accuracy:', logs.get('[1]')))])

Drag options to blanks, or click blank then click option'

Aaccuracy

Bloss

Cval_loss

Dval_accuracy

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'loss' instead of 'accuracy' to print accuracy.

Using validation keys like 'val_accuracy' when training accuracy is needed.

The 'accuracy' key in logs contains the training accuracy for the current epoch.

2fill in blank

medium

Complete the code to include validation loss monitoring during training.

TensorFlow

model.fit(x_train, y_train, epochs=10, validation_data=(x_val, y_val), callbacks=[tf.keras.callbacks.LambdaCallback(on_epoch_end=lambda epoch, logs: print('Validation Loss:', logs.get('[1]')))])

Drag options to blanks, or click blank then click option'

Aval_accuracy

Baccuracy

Closs

Dval_loss

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'loss' instead of 'val_loss' to get validation loss.

Using 'val_accuracy' when loss is needed.

The 'val_loss' key in logs contains the validation loss after each epoch.

3fill in blank

hard

Fix the error in the callback to correctly print validation accuracy.

TensorFlow

model.fit(x_train, y_train, epochs=3, validation_data=(x_val, y_val), callbacks=[tf.keras.callbacks.LambdaCallback(on_epoch_end=lambda epoch, logs: print('Val Accuracy:', logs.get('[1]')))])

Drag options to blanks, or click blank then click option'

Aval_accuracy

Bloss

Caccuracy

Dval_loss

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'accuracy' instead of 'val_accuracy' for validation accuracy.

Using 'val_loss' when accuracy is needed.

Validation accuracy is stored under the key 'val_accuracy' in logs.

4fill in blank

hard

Fill both blanks to create a dictionary that stores training loss and validation accuracy after each epoch.

TensorFlow

history_dict = { 'train_loss': logs.get('[1]'), 'val_acc': logs.get('[2]') }

Drag options to blanks, or click blank then click option'

Aloss

Baccuracy

Cval_accuracy

Dval_loss

Attempts:

3 left

💡 Hint

Common Mistakes

Mixing up training and validation keys.

Using 'accuracy' instead of 'loss' for training loss.

'loss' is the training loss key and 'val_accuracy' is the validation accuracy key in logs.

5fill in blank

hard

Fill all three blanks to create a dictionary comprehension that stores metric values greater than 0.5 from logs.

TensorFlow

filtered_metrics = {k: v for k, v in logs.items() if v [1] 0.5 and 'acc' [2] k and 'val' [3] k}

Drag options to blanks, or click blank then click option'

A>

Bin

Cnot in

D<

Attempts:

3 left

💡 Hint

Common Mistakes

Using '<' instead of '>' for value comparison.

Confusing 'in' and 'not in' for substring checks.

We want values greater than 0.5, keys containing 'acc', and keys not containing 'val'.