Answer-first summary for fast verification
Answer: accuracy
For image classification models in Azure Machine Learning's automated ML, the primary metric should be 'accuracy' for binary and multi-class classification tasks. This is explicitly stated in Microsoft's official documentation for AutoML image models, which indicates accuracy is the primary metric for classification scenarios. The community discussion confirms this with upvoted comments referencing the official documentation and explaining that accuracy is the standard metric for evaluating classification model performance. Other metrics like r2_score, mean_absolute_error, and root_mean_squared_log_error are more suitable for regression tasks, not classification problems.
Author: LeetQuiz Editorial Team
Ultimate access to all questions.
You have an Azure Machine Learning workspace that you will use to configure an automated machine learning job for training an image classification model.
You must select a primary metric to optimize for the model training.
Which primary metric should you use?
A
r2_score
B
mean_absolute_error
C
accuracy
D
root_mean_squared_log_error
No comments yet.