← Back to all transforms
MaskDropout
Description
Image & mask augmentation that zero out mask and image regions corresponding to randomly chosen object instance from mask. Mask must be single-channel image, zero values treated as background. Image can be any number of channels. Args: max_objects: Maximum number of labels that can be zeroed out. Can be tuple, in this case it's [min, max] image_fill_value: Fill value to use when filling image. Can be 'inpaint' to apply inpainting (works only for 3-channel images) mask_fill_value: Fill value to use when filling mask. Targets: image, mask Image types: uint8, float32 Reference: https://www.kaggle.com/c/severstal-steel-defect-detection/discussion/114254
Parameters
- p: float (default: 0.5)
- max_objects: int | tuple[int, int] | float | tuple[float, float] (default: (1, 1))
- image_fill_value: float | Literal['inpaint'] (default: 0)
- mask_fill_value: float (default: 0)
Targets
- Image
- Mask
Try it out
Original Image (width = 484, height = 733):
Transformed Image:
Transform not yet applied