distribution#
Module containing the distribution checks in the vision package.
Classes
Calculate label drift between train dataset and test dataset, using statistical measures. |
|
Calculate prediction drift between train dataset and test dataset, using statistical measures. |
|
Calculate drift between the entire train and test datasets (based on image properties) using a trained model. |
|
Check if the average image brightness (or bbox location if applicable) is similar between train and test set. |
|
Calculate drift between train dataset and test dataset per image property, using statistical measures. |
|
Find outliers images with respect to the given properties. |
|
Find outliers labels with respect to the given properties. |
|
Detects labels that apper only in the test set. |