ultralytics/docs/macros/augmentation-args.md

Argument	Type	Default	Supported Tasks	Range	Description
hsv_h	float	{{ hsv_h }}	detect, segment, pose, obb, classify	0.0 - 1.0	Adjusts the hue of the image by a fraction of the color wheel, introducing color variability. Helps the model generalize across different lighting conditions.
hsv_s	float	{{ hsv_s }}	detect, segment, pose, obb, classify	0.0 - 1.0	Alters the saturation of the image by a fraction, affecting the intensity of colors. Useful for simulating different environmental conditions.
hsv_v	float	{{ hsv_v }}	detect, segment, pose, obb, classify	0.0 - 1.0	Modifies the value (brightness) of the image by a fraction, helping the model to perform well under various lighting conditions.
degrees	float	{{ degrees }}	detect, segment, pose, obb	0.0 - 180	Rotates the image randomly within the specified degree range, improving the model's ability to recognize objects at various orientations.
translate	float	{{ translate }}	detect, segment, pose, obb	0.0 - 1.0	Translates the image horizontally and vertically by a fraction of the image size, aiding in learning to detect partially visible objects.
scale	float	{{ scale }}	detect, segment, pose, obb, classify	0 - 1	Scales the image by a gain factor, simulating objects at different distances from the camera.
shear	float	{{ shear }}	detect, segment, pose, obb	-180 - +180	Shears the image by a specified degree, mimicking the effect of objects being viewed from different angles.
perspective	float	{{ perspective }}	detect, segment, pose, obb	0.0 - 0.001	Applies a random perspective transformation to the image, enhancing the model's ability to understand objects in 3D space.
flipud	float	{{ flipud }}	detect, segment, pose, obb, classify	0.0 - 1.0	Flips the image upside down with the specified probability, increasing the data variability without affecting the object's characteristics.
fliplr	float	{{ fliplr }}	detect, segment, pose, obb, classify	0.0 - 1.0	Flips the image left to right with the specified probability, useful for learning symmetrical objects and increasing dataset diversity.
bgr	float	{{ bgr }}	detect, segment, pose, obb	0.0 - 1.0	Flips the image channels from RGB to BGR with the specified probability, useful for increasing robustness to incorrect channel ordering.
mosaic	float	{{ mosaic }}	detect, segment, pose, obb	0.0 - 1.0	Combines four training images into one, simulating different scene compositions and object interactions. Highly effective for complex scene understanding.
mixup	float	{{ mixup }}	detect, segment, pose, obb	0.0 - 1.0	Blends two images and their labels, creating a composite image. Enhances the model's ability to generalize by introducing label noise and visual variability.
cutmix	float	{{ cutmix }}	detect, segment, pose, obb	0.0 - 1.0	Combines portions of two images, creating a partial blend while maintaining distinct regions. Enhances model robustness by creating occlusion scenarios.
copy_paste	float	{{ copy_paste }}	segment	0.0 - 1.0	Copies and pastes objects across images to increase object instances.
copy_paste_mode	str	{{ copy_paste_mode }}	segment	-	Specifies the copy-paste strategy to use. Options include 'flip' and 'mixup'.
auto_augment	str	{{ auto_augment }}	classify	-	Applies a predefined augmentation policy ('randaugment', 'autoaugment', or 'augmix') to enhance model performance through visual diversity.
erasing	float	{{ erasing }}	classify	0.0 - 0.9	Randomly erases regions of the image during training to encourage the model to focus on less obvious features.
augmentations	list	{{ augmentations }}	detect, segment, pose, obb	-	Custom Albumentations transforms for advanced data augmentation (Python API only). Accepts a list of transform objects for specialized augmentation needs.