mednet.data.segment.drive¶
DRIVE dataset for vessel segmentation.
The DRIVE database has been established to enable comparative studies on segmentation of blood vessels in retinal images. The database contains annotations from 2 different experts (only for the test set).
Database reference: [SAN+04]
Data specifications:
Raw data input (on disk):
RGB images encoded in TIFF format with resolution (HxW) = 584 x 565 pixels
Total samples: 40
Output sample:
Split default
includes 20 images for training and another 20 for
testing. Split second-annotator
includes only the 20 test images with
different vessel annotations (expert 2).
This module contains the base declaration of common data modules and raw-data loaders for this database. All configured splits inherit from this definition.
Module Attributes
Pythonic name to refer to this database. |
|
Key to search for in the configuration file for the root directory of this database. |
Classes
|
DRIVE dataset for Vessel Segmentation. |
A specialized raw-data-loader for the Drive dataset. |
- mednet.data.segment.drive.DATABASE_SLUG = 'drive'¶
Pythonic name to refer to this database.
- mednet.data.segment.drive.CONFIGURATION_KEY_DATADIR = 'datadir.drive'¶
Key to search for in the configuration file for the root directory of this database.
- class mednet.data.segment.drive.RawDataLoader[source]¶
Bases:
RawDataLoader
A specialized raw-data-loader for the Drive dataset.
- class mednet.data.segment.drive.DataModule(split_path)[source]¶
Bases:
CachingDataModule
DRIVE dataset for Vessel Segmentation.
- Parameters:
split_path (
Path
|Traversable
) – Path or traversable (resource) with the JSON split description to load.