`pixano_inference.pydantic.tasks.video.mask_generation`

Pydantic models for mask generation task.

`VideoMaskGenerationInput`

Input for mask generation.

Attributes:

Name	Type	Description
`video`	`str \| Path \| list[str] \| list[Path]`	Can be a path to the video or list of paths to the frames or a base64 encoded video or a list of base64 encoded frames.
`points`	`list[list[list[int]]] \| None`	Points for the mask generation. The first fimension is the number of objects the second the number of points for each object and the third the coordinates of the points.
`labels`	`list[list[int]] \| None`	Labels for the mask generation. The first fimension is the number of objects, the second the number of labels for each object.
`boxes`	`list[list[int]] \| None`	Boxes for the mask generation. The first fimension is the number of objects, the second the coordinates of the boxes.
`objects_ids`	`list[int]`	IDs of the objects to generate masks for.
`frame_indexes`	`list[int]`	Indexes of the frames where the objects are located.

Output for mask generation.

Attributes:

Name	Type	Description
`objects_ids`	`list[int]`	IDs of the objects.
`frame_indexes`	`list[int]`	Indexes of the frames where the objects are located.
`masks`	`list[CompressedRLE]`	Masks for the objects.

Request for mask generation.

Convert the request to the input.

Source code in pixano_inference/pydantic/tasks/video/mask_generation.py

def to_input(self) -> VideoMaskGenerationInput:
    """Convert the request to the input."""
    return self.to_base_model(VideoMaskGenerationInput)

Response for mask generation.

Attributes:

Name	Type	Description
`data`	`VideoMaskGenerationOutput`	Output of the generation.