EMCqMRI.core.engine.data_loader module

class EMCqMRI.core.engine.data_loader.SampleDatabase(config_object, path=[])[source]

Bases: torch.utils.data.dataset.Dataset

Wrapper function for custom dataset subclasses.

EMCqMRI.core.engine.data_loader.create_dataloader(config_object)[source]

Creates the dataloader handler

Parameters

  • config_object ([Configuration]) – [Object containing all backend configuration settings]

  • config_object.args (Required) –

    • mode

    • dataset

    • trainingDataPath, validationDataPath and/or testingDataPath

    • batchSize

    • usePatches

    • useSimulatedData

    • runValidation

Returns

List]: List of DataLoader objects. If mode==’training’, it returns

[trainingDataloader, validationDataloader]. If mode==’testing’, it returns [testingDataloader]

Return type

[type