TensorFlow Keras Model Building 2

Question 1

Which Keras layer is typically used as the final layer for binary classification?

Accepted Answer

Dense with sigmoid activation

Answer

A Dense layer with sigmoid activation outputs a probability between 0 and 1, suitable for binary classification.

Question 2

What loss function should you use for multi-class classification with integer labels in Keras?

Accepted Answer

sparse_categorical_crossentropy

Answer

sparse_categorical_crossentropy is used when labels are integers rather than one-hot encoded vectors.

Question 3

How do you save a full Keras model including architecture and weights?

Accepted Answer

model.save('model.keras') or model.save('model/')

Answer

model.save() serializes the entire model including architecture, weights, and optimizer state.

Question 4

Which callback stops training when a monitored metric stops improving?

Accepted Answer

EarlyStopping

Answer

EarlyStopping monitors a metric and halts training after a specified number of epochs with no improvement.

Question 5

What does the validation_split parameter in model.fit() do?

Accepted Answer

Reserves a fraction of training data for validation

Answer

validation_split takes a float (e.g., 0.2) and reserves that fraction of training data to evaluate loss and metrics each epoch.

TensorFlow Practice Test