TensorFlow Test 5

Question 1

What is the purpose of tf.keras.callbacks.CSVLogger during model evaluation training runs?

Accepted Answer

Appends epoch-level metrics to a CSV file for later analysis

Answer

CSVLogger writes epoch number, loss, and metric values to a CSV after each epoch, making it easy to plot learning curves later.

Question 2

How can you measure inference latency of a TensorFlow model on a test input?

Accepted Answer

Time model.predict() calls using Python's time module or tf.timestamp()

Answer

Wrapping model.predict() with time.time() before and after gives wall-clock latency; averaging over multiple runs reduces variance.

Question 3

What does model.predict() return for a multi-output Keras model?

Accepted Answer

A list of numpy arrays, one per output

Answer

For multi-output models, predict() returns a list where each element corresponds to one output layer's predictions.

Question 4

When evaluating a TF model deployed via TensorFlow Serving, which protocol is used for REST inference requests?

Accepted Answer

HTTP/REST via the Predict API endpoint

Answer

TensorFlow Serving exposes both a gRPC interface and an HTTP/REST API; the REST endpoint accepts POST requests to /v1/models/{name}:predict.

Question 5

Which metric should you use when testing a TensorFlow model on a highly imbalanced binary classification dataset?

Accepted Answer

F1-Score or AUC-ROC

Answer

Accuracy is misleading on imbalanced data; F1-Score balances precision and recall, and AUC-ROC evaluates ranking across thresholds.

TensorFlow Practice Test