dataeval.metrics

Metrics are a way to measure the performance of your models or datasets that can then be analyzed in the context of a given problem.

Submodules

bias

Bias metrics check for skewed or imbalanced datasets and incomplete feature representation which may impact model performance.

estimators

Estimators calculate performance bounds and the statistical distance between datasets.

stats

Statistics metrics calculate a variety of image properties and pixel statistics and label statistics against the images and labels of a dataset.