XYMasking

Targets:

image

mask

bboxes

keypoints

Image Types:uint8, float32

Apply horizontal or vertical masking strips to simulate occlusion. Useful for spectrograms (spectral/frequency masking).

Useful for training with varied visibility conditions; spectral and frequency masking can improve model robustness (e.g. SpecAugment-style). At least one of max_x_length or max_y_length must be specified, dictating the mask's maximum size along each axis.

Arguments

num_masks_x_range

tuple[int, int]

[0,0]

Range of horizontal regions to mask. Defaults to (0, 0).

num_masks_y_range

tuple[int, int]

[0,0]

Range of vertical regions to mask. Defaults to (0, 0).

mask_x_length_range

tuple[int, int]

[0,0]

Range (min, max) of mask length along the X (horizontal) axis. The length is randomly chosen within this range for each mask. Defaults to (0, 0).

mask_y_length_range

tuple[int, int]

[0,0]

Range (min, max) of mask height along the Y (vertical) axis. The height is randomly chosen within this range for each mask. Defaults to (0, 0).

fill

Value for the dropped pixels. Can be:

int or float: all channels are filled with this value
tuple: tuple of values for each channel
'random': each pixel is filled with random values
'random_uniform': each hole is filled with a single random color
'inpaint_telea': uses OpenCV Telea inpainting method
'inpaint_ns': uses OpenCV Navier-Stokes inpainting method Default: 0

fill_mask

tuple[float, ...] | float | None

Fill value for dropout regions in the mask. If None, mask regions corresponding to image dropouts are unchanged. Default: None

p

float

0.5

Probability of applying the transform. Defaults to 0.5.

Notes

Either mask_x_length_range or mask_y_length_range or both must have a positive max.