TensorFlow Test 4

Question 1

What is the difference between model.test_on_batch() and model.evaluate() in Keras?

Accepted Answer

test_on_batch processes one batch without looping; evaluate loops over the full dataset

Answer

test_on_batch() runs a single forward pass on one batch and returns metrics immediately, while evaluate() iterates over all batches.

Question 2

In TensorFlow, what does AUC stand for and what does it measure in binary classification testing?

Accepted Answer

Area Under the Curve; measures the ROC curve area representing ranking quality

Answer

AUC (Area Under the ROC Curve) summarizes classifier performance across all decision thresholds; 1.0 is perfect, 0.5 is random.

Question 3

When testing a TF model for fairness, you want to measure accuracy across demographic subgroups. Which approach is most appropriate?

Accepted Answer

Filter the test set per subgroup and call model.evaluate() on each subset

Answer

Slicing the test set by subgroup and evaluating each slice separately reveals performance disparities across groups.

Question 4

Which TensorFlow Model Analysis (TFMA) concept allows you to evaluate metrics on slices of data?

Accepted Answer

SlicingSpec

Answer

SlicingSpec in TFMA defines which feature columns to slice on, enabling per-slice metric computation during evaluation.

Question 5

What does the return_dict=True argument do in model.evaluate()?

Accepted Answer

Returns metrics as a Python dict keyed by metric name instead of a list

Answer

With return_dict=True, evaluate() returns {'loss': ..., 'accuracy': ..., ...} making it easier to access metrics by name.

TensorFlow Practice Test