wormpose.commands.calibrate_dataset

Calculates the image similarity on a random selection of labeled frames from a dataset.

wormpose.commands.calibrate_dataset.calibrate(dataset_loader: str, dataset_path: str, **kwargs)[source]

Calculate the image score for a certain number of labelled frames in the dataset, this will give an indication on choosing the image similarity threshold when predicting all frames in the dataset.

Parameters
  • dataset_loader – Name of the dataset loader, for example “tierpsy”

  • dataset_path – Root path of the dataset containing videos of worm