ExtractBatchAligned

class lib.infer.objects.ExtractBatchAligned(landmarks: ndarray[tuple[Any, ...], dtype[float32]] | None = None, landmark_type: LandmarkType | None = None)

Bases: object

Dataclass for working with batches of aligned images

Parameters:

landmarks (numpy.ndarray[tuple[Any, ...], numpy.dtype[numpy.float32]] | None) – The face landmarks found for this batch in frame space or None if not available. Default: None (to be populated later)
landmark_type (lib.align.constants.LandmarkType | None) – The type of landmarks that the batch holds or None if not available. Default: None (to be populated later)

Attributes Summary

`landmark_type`	The type of landmarks that the batch holds
`landmarks`	The face landmarks found for this batch in frame space or `None` if not populated
`landmarks_68`	The stored landmarks as 68 point landmarks if supported, or original landmarks if not ( 4 point ROI landmarks)
`landmarks_normalized`	The normalized, aligned 68 point landmarks
`matrices`	The face alignment matrices to transform from frame space to normalized (0, 1) space
`matrices_face`	The alignment matrices to transform from normalized legacy space (0, 1) to normalized face space
`matrices_head`	The alignment matrices to transform from normalized legacy space (0, 1) to normalized head space
`offsets_face`	The (N, x, y) offsets required to shift from normalized (legacy) centering to face centering
`offsets_head`	The (N, x, y) offsets required to shift from normalized (legacy) centering to head centering
`offsets_legacy`	The (N, x, y) offsets for normalized (legacy) centering.
`rotation`	The estimated (N, 3, 1) rotation vectors
`translation`	The estimated (N, 3, 1) translation vectors

Methods Summary

`append`(batch)	Append the data from the given batch object to this batch object
`apply_mask`(mask)	Apply a boolean mask to the batch object.

Attributes Documentation

landmark_type: LandmarkType | None = None: The type of landmarks that the batch holds

landmarks: ndarray[tuple[Any, ...], dtype[float32]] | None = None: The face landmarks found for this batch in frame space or None if not populated

landmarks_68: The stored landmarks as 68 point landmarks if supported, or original landmarks if not ( 4 point ROI landmarks)

landmarks_normalized: The normalized, aligned 68 point landmarks

matrices: The face alignment matrices to transform from frame space to normalized (0, 1) space

matrices_face: The alignment matrices to transform from normalized legacy space (0, 1) to normalized face space

matrices_head: The alignment matrices to transform from normalized legacy space (0, 1) to normalized head space

offsets_face: The (N, x, y) offsets required to shift from normalized (legacy) centering to face centering

offsets_head: The (N, x, y) offsets required to shift from normalized (legacy) centering to head centering

offsets_legacy: The (N, x, y) offsets for normalized (legacy) centering. This is always (0, 0) for all items in the batch

rotation: The estimated (N, 3, 1) rotation vectors

translation: The estimated (N, 3, 1) translation vectors

Methods Documentation

append(batch: ExtractBatchAligned) → None

Append the data from the given batch object to this batch object

Parameters:: batch (ExtractBatchAligned) – The object containing data to be appended to this object
Return type:: None

apply_mask(mask: ndarray[tuple[Any, ...], dtype[bool]]) → None

Apply a boolean mask to the batch object. True values are kept, False values are discarded

Parameters:: mask (ndarray[tuple[Any, ...], dtype[bool]]) – The boolean mask to apply to the object. Must be of size (landmarks, )
Return type:: None

append(batch: ExtractBatchAligned) → None

Append the data from the given batch object to this batch object

Parameters:: batch (ExtractBatchAligned) – The object containing data to be appended to this object
Return type:: None

apply_mask(mask: ndarray[tuple[Any, ...], dtype[bool]]) → None

Apply a boolean mask to the batch object. True values are kept, False values are discarded

Parameters:: mask (ndarray[tuple[Any, ...], dtype[bool]]) – The boolean mask to apply to the object. Must be of size (landmarks, )
Return type:: None

landmark_type: LandmarkType | None = None: The type of landmarks that the batch holds

landmarks: ndarray[tuple[Any, ...], dtype[float32]] | None = None: The face landmarks found for this batch in frame space or None if not populated

property landmarks_68: ndarray[tuple[Any, ...], dtype[float32]]: The stored landmarks as 68 point landmarks if supported, or original landmarks if not ( 4 point ROI landmarks)

property landmarks_normalized: ndarray[tuple[Any, ...], dtype[float32]]: The normalized, aligned 68 point landmarks

property matrices: ndarray[tuple[Any, ...], dtype[float32]]: The face alignment matrices to transform from frame space to normalized (0, 1) space

property matrices_face: ndarray[tuple[Any, ...], dtype[float32]]: The alignment matrices to transform from normalized legacy space (0, 1) to normalized face space

property matrices_head: ndarray[tuple[Any, ...], dtype[float32]]: The alignment matrices to transform from normalized legacy space (0, 1) to normalized head space

property offsets_face: ndarray[tuple[Any, ...], dtype[float32]]: The (N, x, y) offsets required to shift from normalized (legacy) centering to face centering

property offsets_head: ndarray[tuple[Any, ...], dtype[float32]]: The (N, x, y) offsets required to shift from normalized (legacy) centering to head centering

property offsets_legacy: ndarray[tuple[Any, ...], dtype[float32]]: The (N, x, y) offsets for normalized (legacy) centering. This is always (0, 0) for all items in the batch

property rotation: ndarray[tuple[Any, ...], dtype[float32]]: The estimated (N, 3, 1) rotation vectors

property translation: ndarray[tuple[Any, ...], dtype[float32]]: The estimated (N, 3, 1) translation vectors