train_test_validation#
Module containing the train test validation check in the vision package.
Classes
Check if the average image brightness (or bbox location if applicable) is similar between train and test set. |
|
Calculate drift between the entire train and test datasets (based on image properties) using a trained model. |
|
Calculate drift between train dataset and test dataset per image property, using statistical measures. |
|
Detects labels that appear only in the test set. |
|
Return the Predictive Power Score of image properties, in order to estimate their ability to predict the label. |
|
The TrainTestLabelDrift check is deprecated and will be removed in the 0.14 version. |
|
Calculate label drift between train dataset and test dataset, using statistical measures. |