Why thorough evaluation ensures reliability in TensorFlow - Test Your Understanding

Practice - 5 Tasks

1fill in blank

easy

Complete the code to compile the TensorFlow model with the correct loss function.

TensorFlow

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

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

A'mse'

B'hinge'

C'mean_absolute_error'

D'sparse_categorical_crossentropy'

Attempts:

3 left

💡 Hint

Common Mistakes

Using a regression loss like 'mse' for classification tasks.

The 'sparse_categorical_crossentropy' loss is used for multi-class classification with integer labels, which fits many classification tasks.

2fill in blank

medium

Complete the code to fit the model on training data for 10 epochs.

TensorFlow

history = model.fit(x_train, y_train, epochs=[1], validation_split=0.2)

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

A10

B5

C20

D50

Attempts:

3 left

💡 Hint

Common Mistakes

Setting epochs too low or too high without validation.

Training for 10 epochs is a common choice to balance learning and overfitting.

3fill in blank

hard

Fix the error in the code to evaluate the model on test data and get accuracy.

TensorFlow

test_loss, [1] = model.evaluate(x_test, y_test)

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

Aaccuracy

Bloss

Cacc

Dscore

Attempts:

3 left

💡 Hint

Common Mistakes

Using variable names that don't match the metric names.

The model.evaluate returns loss and metrics in order; here, the second value is accuracy as specified during compile.

4fill in blank

hard

Fill both blanks to create a confusion matrix and print it.

TensorFlow

from sklearn.metrics import [1]
cm = [2](y_test, y_pred)
print(cm)

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

Aconfusion_matrix

Bclassification_report

Cconfusion_matrix_score

Daccuracy_score

Attempts:

3 left

💡 Hint

Common Mistakes

Using incorrect function names or metrics for confusion matrix.

The confusion_matrix function from sklearn.metrics computes the confusion matrix, which helps evaluate classification reliability.

5fill in blank

hard

Fill all three blanks to calculate precision, recall, and F1-score.

TensorFlow

from sklearn.metrics import [1], [2], [3]
precision = [1](y_test, y_pred)
recall = [2](y_test, y_pred)
f1 = [3](y_test, y_pred)
print(f"Precision: {precision}\nRecall: {recall}\nF1-score: {f1}")

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

Aprecision_score

Brecall_score

Cf1_score

Daccuracy_score

Attempts:

3 left

💡 Hint

Common Mistakes

Mixing up metric function names or using accuracy instead of F1-score.

Precision, recall, and F1-score are key metrics to evaluate classification models thoroughly for reliability.