modelzoo.vision.pytorch.unet.input.SkmDataProcessor.SkmDataProcessor#

class modelzoo.vision.pytorch.unet.input.SkmDataProcessor.SkmDataProcessor[source]#

Bases: modelzoo.vision.pytorch.unet.input.Hdf5BaseIterDataProcessor.Hdf5BaseIterDataProcessor

A SKM-TEA MRI DICOM Track (Stanford MRI Dataset) Data Processor class for U-Net Segmentation. This class includes data preprocessing and transforms that are necessary for utilizing the SkmDicomDataset class for training models.

Currently supports masks (segmentation) and does NOT support bounding boxes (detection).

Parameters

params (dict) – YAML config file with adaptable model and data configurations

Methods

create_dataloader

Classmethod to create the dataloader object.

preprocess_image

preprocess_mask

transform_image_and_mask

Preprocess the masks and images

__call__(*args: Any, **kwargs: Any) Any#

Call self as a function.

__init__(params)[source]#
static __new__(cls, *args: Any, **kwargs: Any) Any#
create_dataloader(is_training=True)#

Classmethod to create the dataloader object.

transform_image_and_mask(image, mask)[source]#

Preprocess the masks and images