data

sleap_nn.data

Modules related to data loading and processing.

Modules:

Name	Description
augmentation	This module implements data pipeline blocks for augmentation operations.
confidence_maps	Generate confidence maps.
custom_datasets	Custom torch.utils.data.Datasets for different model types.
edge_maps	Transformers for generating edge confidence maps and part affinity fields.
identity	Utilities for generating data for track identity models.
instance_centroids	Handle calculation of instance centroids.
instance_cropping	Handle cropping of instances.
normalization	This module implements data pipeline blocks for normalization operations.
providers	This module implements pipeline blocks for reading input data such as labels.
resizing	This module implements image resizing and padding.
segmentation_maps	Generate ground truth tensors for instance segmentation from SegmentationMask objects.
skia_augmentation	Skia-based augmentation functions that operate on uint8 tensors.
splitting	Group-aware train/val splitter, decided before training.
tiling	Shared tiling primitives for splitting large images into overlapping tiles.
utils	Miscellaneous utility functions for data processing.