You create a multi-class image classification deep learning model that uses the PyTorch deep learning framework. You must configure Azure Machine Learning Hyperdrive to optimize the hyperparameters…

Question

Options

• ASet the primary_metric_goal of the estimator used to run the bird_classifier_train.py script to
• BAdd code to the bird_classifier_train.py script to calculate the validation loss of the model and log
• CSet the primary_metric_goal of the estimator used to run the bird_classifier_train.py script to
• DSet the primary_metric_name of the estimator used to run the bird_classifier_train.py script to
• ESet the primary_metric_name of the estimator used to run the bird_classifier_train.py script to
• FAdd code to the bird_classifier_train.py script to calculate the validation accuracy of the model

• A
  81% (39)
• B
  10% (5)
• C
  2% (1)
• E
  6% (3)

Explanation

Three actions are required to configure Hyperdrive to optimize for accuracy. First (F): the training script bird_classifier_train.py must contain code that calculates validation accuracy and logs it using run.log('validation_accuracy', value). Hyperdrive reads metrics from the run logs, so the metric must be explicitly logged inside the training script. Second (D): the primary_metric_name in the HyperDriveConfig must be set to the exact string name logged in the script (e.g., 'validation_accuracy'). This tells Hyperdrive which logged value to track across child runs. Third (A): primary_metric_goal must be set to PrimaryMetricGoal.MAXIMIZE, because a higher accuracy score is better. Options B and C are distractors likely involving validation loss (which would be minimized, not maximized) and options E references the wrong metric name, none of which align with optimizing for accuracy.

No community discussion yet for this question.