Metrics

Evaluating the performance of a machine learning model is crucial for understanding its effectiveness and pinpointing areas for improvement. sorix provides a variety of standard metrics to evaluate models across different tasks.

Regression Metrics

• Regression: Metrics for assessing continuous predictions. Includes MAE, MSE, RMSE, and R2.

Classification Metrics

• Classification: Metrics for categorical predictions. Features Accuracy, Precision, Recall, and F1 Score.

All metrics are designed to work seamlessly with sorix tensors and support both scalar and batch computations.