π Geometric Computer Vision Library for Spatial AI
Python artificial-intelligencecomputer-visiondeep-learninghacktoberfestimage-processingmachine-learningneural-networkpythonpytorchroboticsspatial-ai
:orphan:
Image Augmentations
===================
.. meta::
:description: The Image Augmentations module in Kornia provides a wide range of 2D and 3D data augmentation transforms. It includes intensity-based augmentations, geometric transformations, mix-based augmentations, and normalization operations for both 2D and 3D image tensors. Key functions include random color shifts, rotations, cropping, elastic transformations, and more.
.. currentmodule:: kornia.augmentation
The augmentation operators, grouped by what they change. They take float tensors of shape ``(B, C, H, W)``, or
``(B, C, D, H, W)`` for the 3D transforms; color transforms expect values in ``[0, 1]``. Each operator applies
with probability ``p``, drawn per sample, except the crops, the resizes, ``RandomMixUpV2``, ``RandomCutMixV2``,
``PatchMix``, ``Normalize``, ``Denormalize`` and ``RandomDissolving``, which transform the whole batch or none of
it. ``same_on_batch=True`` makes any other operator use one draw for the whole batch. In the class descriptions,
"selected" samples are the ones ``p`` picked. Combine operators with
:class:`~kornia.augmentation.container.AugmentationSequential`.
.. list-table::
:widths: 30 70
* - :doc:`augmentation.intensity`
- 2D transforms that change pixel values but not their positions: color jitter, blur, noise, illumination, JPEG, weather effects.
* - :doc:`augmentation.geometric`
- 2D transforms that move pixels: crops, flips, affine, perspective, elastic, thin-plate-spline, erasing.
* - :doc:`augmentation.mix`
- 2D transforms that combine several images: CutMix, MixUp, Mosaic, Jigsaw, Transplantation.
* - :doc:`augmentation.transforms3d`
- Geometric, intensity and mix transforms for volumetric ``(B, C, D, H, W)`` data.