sleap.nn.data.augmentation¶
Transformers for applying data augmentation.
-
class
sleap.nn.data.augmentation.
ImgaugAugmenter
(augmenter: imgaug.augmenters.meta.Sequential)[source]¶ Data transformer based on the imgaug library.
This class can generate a tf.data.Dataset from an existing one that generates image and instance data. Element of the output dataset will have a set of augmentation transformations applied.
-
augmenter
¶ An instance of imgaug.augmenters.Sequential that will be applied to each element of the input dataset.
-
classmethod
from_config
(config: sleap.nn.config.optimization.AugmentationConfig) → sleap.nn.data.augmentation.ImgaugAugmenter[source]¶ Create an augmenter from a set of configuration parameters.
- Parameters
config – An AugmentationConfig instance with the desired parameters.
- Returns
An instance of this class with the specified augmentation configuration.
-
property
input_keys
¶ Return the keys that incoming elements are expected to have.
-
property
output_keys
¶ Return the keys that outgoing elements will have.
-
transform_dataset
(input_ds: tensorflow.python.data.ops.dataset_ops.DatasetV2) → tensorflow.python.data.ops.dataset_ops.DatasetV2[source]¶ Create a tf.data.Dataset with elements containing augmented data.
- Parameters
input_ds – A dataset with elements that contain the keys “image” and “instances”. This is typically raw data from a data provider.
- Returns
A tf.data.Dataset with the same keys as the input, but with images and instance points updated with the applied augmentations.
Notes
The “scale” key in examples are not modified when scaling augmentation is applied.
-