Binary classification model in TensorFlow - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to create a binary classification model using TensorFlow Keras.

TensorFlow

model = tf.keras.Sequential([
    tf.keras.layers.Dense(16, activation='relu', input_shape=(10,)),
    tf.keras.layers.Dense(1, activation=[1])
])

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

A'softmax'

B'sigmoid'

C'relu'

D'tanh'

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'softmax' activation for a single output neuron.

Using 'relu' activation in the output layer.

For binary classification, the output layer uses a sigmoid activation to output probabilities between 0 and 1.

2fill in blank

medium

Complete the code to compile the binary classification 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'binary_crossentropy'

B'hinge'

C'mean_squared_error'

D'categorical_crossentropy'

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'categorical_crossentropy' for binary classification.

Using regression loss functions like 'mean_squared_error'.

Binary classification models use 'binary_crossentropy' as the loss function.

3fill in blank

hard

Fix the error in the code to correctly train the binary classification model.

TensorFlow

history = model.fit(X_train, y_train, epochs=[1], batch_size=32)

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

ANone

B'10'

C5

D'twenty'

Attempts:

3 left

💡 Hint

Common Mistakes

Passing epochs as a string instead of an integer.

Passing None as epochs.

The number of epochs must be an integer, not a string or None.

4fill in blank

hard

Fill both blanks to evaluate the model on test data and print accuracy.

TensorFlow

loss, [1] = model.evaluate(X_test, y_test)
print('Test [2]:', [1])

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

Aaccuracy

Bloss

Dscore

Attempts:

3 left

💡 Hint

Common Mistakes

Confusing loss and accuracy variables.

Printing the wrong variable.

The evaluate method returns loss and accuracy. We assign accuracy to a variable and print it.

5fill in blank

hard

Fill all three blanks to predict classes for new data and convert probabilities to binary labels.

TensorFlow

predictions = model.predict([1])
binary_predictions = (predictions [2] 0.5).astype([3])

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

AX_new

B>

Cint

DX_test

Attempts:

3 left

💡 Hint

Common Mistakes

Using test data instead of new data for prediction.

Using wrong comparison operator.

Not converting boolean array to integers.

We predict on new data X_new, compare probabilities to 0.5 to get True/False, then convert to integers 0 or 1.