PCALoss

class lightning_pose.losses.losses.PCALoss[source]

Bases: Loss

Penalize predictions that fall outside a low-dimensional subspace.

Attributes Summary

LOSS_NAME_MULTIVIEW

LOSS_NAME_SINGLEVIEW

Methods Summary

__call__(keypoints_pred[,Β stage])

Call self as a function.

compute_loss(predictions)

remove_nans(**kwargs)

Attributes Documentation

LOSS_NAME_MULTIVIEW = 'pca_multiview'
LOSS_NAME_SINGLEVIEW = 'pca_singleview'

Methods Documentation

__call__(keypoints_pred: Tensor, stage: Literal['train', 'val', 'test'] | None = None, **kwargs) → tuple[~torch.Annotated[~torch.Tensor, {'__torchtyping__': True, 'details': ((),), 'cls_name': 'TensorType'}], list[dict]][source]

Call self as a function.

compute_loss(predictions: Tensor, {'__torchtyping__': True, 'details': ('num_samples', 'sample_dim'), 'cls_name': 'TensorType'}]) → Tensor, {'__torchtyping__': True, 'details': ('num_samples', -1,), 'cls_name': 'TensorType'}][source]
remove_nans(**kwargs)[source]
__init__(loss_name: Literal['pca_singleview', 'pca_multiview'], components_to_keep: int | float = 0.95, empirical_epsilon_percentile: float = 99.0, epsilon: float | None = None, empirical_epsilon_multiplier: float = 1.0, mirrored_column_matches: ListConfig | list | None = None, columns_for_singleview_pca: ListConfig | list | None = None, data_module: BaseDataModule | UnlabeledDataModule | None = None, log_weight: float = 0.0, device: Literal['cpu', 'cuda'] | device = 'cpu', centering_method: Literal['mean', 'median'] | None = None, **kwargs) → None[source]

Initialize PCALoss.

Fits a KeypointPCA object on the training data and uses the resulting low-dimensional subspace to penalize out-of-subspace predictions at training time.

Parameters:

  • loss_name – "pca_singleview" penalizes single-camera predictions; "pca_multiview" penalizes predictions that are inconsistent across views.

  • components_to_keep – passed to KeypointPCA; see its docstring for details.

  • empirical_epsilon_percentile – percentile of the training-data reprojection error used to set epsilon when epsilon is None; in [0, 100].

  • epsilon – if not None, use this fixed epsilon value and ignore empirical_epsilon_percentile.

  • empirical_epsilon_multiplier – scalar multiplier applied to the empirically computed epsilon before use.

  • mirrored_column_matches – required for "pca_multiview"; see KeypointPCA for details.

  • columns_for_singleview_pca – subset of keypoint indices to use for singleview PCA; None uses all keypoints.

  • data_module – data module used by KeypointPCA to extract training data.

  • log_weight – final weight in front of the loss term in the objective function is computed as 1.0 / (2.0 * exp(log_weight)).

  • device – device on which PCA parameters are stored and loss is computed.

  • centering_method – if not None, subtract the per-frame keypoint centroid before fitting PCA. "mean" uses the arithmetic mean; "median" uses the median.

__new__(**kwargs)