...

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
tuple[int, int] | int
0

Number or range of horizontal regions to mask. Defaults to 0.

num_masks_y
tuple[int, int] | int
0

Number or range of vertical regions to mask. Defaults to 0.

mask_x_length
tuple[int, int] | int
0

Specifies the length of the masks along the X (horizontal) axis. If an integer is provided, it sets a fixed mask length. If a tuple of two integers (min, max) is provided, the mask length is randomly chosen within this range for each mask. This allows for variable-length masks in the horizontal direction.

mask_y_length
tuple[int, int] | int
0

Specifies the height of the masks along the Y (vertical) axis. Similar to mask_x_length, an integer sets a fixed mask height, while a tuple (min, max) allows for variable-height masks, chosen randomly within the specified range for each mask. This flexibility facilitates creating masks of various sizes in the vertical direction.

fill
tuple[float, ...] | float | random | random_uniform | inpaint_telea | inpaint_ns
0

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 max_x_length or max_y_length or both must be defined.