Compiling models (optimizer, loss, metrics) in TensorFlow - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to compile the model with the Adam optimizer.

TensorFlow

model.compile(optimizer=[1], loss='sparse_categorical_crossentropy', metrics=['accuracy'])

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

A'adam'

B'sgd'

C'rmsprop'

D'adagrad'

Attempts:

3 left

💡 Hint

Common Mistakes

Using an optimizer name that is not supported or misspelled.

Passing an optimizer object instead of a string.

The Adam optimizer is specified as the string 'adam' in the compile method.

2fill in blank

medium

Complete the code to compile the model using Mean Squared Error as the loss function.

TensorFlow

model.compile(optimizer='adam', loss=[1], metrics=['mae'])

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

A'hinge'

B'categorical_crossentropy'

C'binary_crossentropy'

D'mean_squared_error'

Attempts:

3 left

💡 Hint

Common Mistakes

Using a classification loss for a regression problem.

Misspelling the loss function name.

Mean Squared Error loss is specified as 'mean_squared_error' in TensorFlow.

3fill in blank

hard

Fix the error in the code by selecting the correct metric name.

TensorFlow

model.compile(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=[[1]])

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

A'precision'

B'acc'

C'accuracy'

D'recall'

Attempts:

3 left

💡 Hint

Common Mistakes

Using deprecated metric names like 'acc'.

Misspelling metric names causing runtime errors.

The correct metric name is 'accuracy'. 'acc' is deprecated and misspelled options cause errors.

4fill in blank

hard

Fill both blanks to compile the model with RMSprop optimizer and binary crossentropy loss.

TensorFlow

model.compile(optimizer=[1], loss=[2], metrics=['accuracy'])

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

A'rmsprop'

B'adam'

C'binary_crossentropy'

D'categorical_crossentropy'

Attempts:

3 left

💡 Hint

Common Mistakes

Mixing optimizer and loss function names.

Using categorical loss for binary classification.

RMSprop optimizer is 'rmsprop' and binary crossentropy loss is 'binary_crossentropy'.

5fill in blank

hard

Fill all three blanks to compile the model with SGD optimizer, hinge loss, and precision metric.

TensorFlow

model.compile(optimizer=[1], loss=[2], metrics=[[3]])

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

A'adam'

B'sgd'

C'hinge'

D'precision'

Attempts:

3 left

💡 Hint

Common Mistakes

Using wrong optimizer or loss names.

Confusing precision with other metrics.

SGD optimizer is 'sgd', hinge loss is 'hinge', and precision metric is 'precision'.