You have an Azure Machine Learning workspace. You plan to use the workspace to set up automated machine learning training for an image classification model. You need to choose the primary metric to…

r2_score (coefficient of determination) is a regression metric that measures variance explained by the model and is not applicable to classification tasks.

mean_absolute_error measures the average magnitude of prediction errors for continuous numeric outputs and is only valid for regression tasks, not classification.

Image classification is a multi-class classification problem, and accuracy measures the fraction of images correctly labeled by the model. Azure AutoML supports accuracy as a primary metric for classification tasks and uses it to compare and select the best model during training iterations.

root_mean_squared_log_error is a regression metric designed for targets with exponential growth and is incompatible with classification label outputs.