TemporalLoss

class lightning_pose.losses.losses.TemporalLoss

Bases: Loss

Penalize temporal differences for each target.

Motion model: x_t = x_(t-1) + e_t, e_t ~ N(0, s)

Methods Summary

__call__(keypoints_pred[, confidences, stage])	Call self as a function.
compute_loss(predictions)
rectify_epsilon(loss)	Rectify supporting a list of epsilons, one per bodypart.
remove_nans(loss, confidences)

Methods Documentation

__call__(keypoints_pred: Tensor, {'__torchtyping__': True, 'details': ('batch', 'two_x_num_keypoints'), 'cls_name': 'TensorType'}], confidences: Tensor, {'__torchtyping__': True, 'details': ('batch', 'num_keypoints'), 'cls_name': 'TensorType'}] | None = None, stage: Literal['train', 'val', 'test'] | None = None, **kwargs) → Tensor, {'__torchtyping__': True, 'details': ((),), 'cls_name': 'TensorType'}], list[dict]]

Call self as a function.

compute_loss(predictions: Tensor, {'__torchtyping__': True, 'details': ('batch', 'two_x_num_keypoints'), 'cls_name': 'TensorType'}]) → Tensor, {'__torchtyping__': True, 'details': ('batch_minus_one', 'num_keypoints',), 'cls_name': 'TensorType'}]

rectify_epsilon(loss: Tensor, {'__torchtyping__': True, 'details': ('batch_minus_one', 'num_keypoints'), 'cls_name': 'TensorType'}]) → Tensor, {'__torchtyping__': True, 'details': ('batch_minus_one', 'num_keypoints',), 'cls_name': 'TensorType'}]

Rectify supporting a list of epsilons, one per bodypart. Not implemented in Loss class, because shapes of broadcasting may vary

remove_nans(loss: Tensor, {'__torchtyping__': True, 'details': ('batch_minus_one', 'num_keypoints'), 'cls_name': 'TensorType'}], confidences: Tensor, {'__torchtyping__': True, 'details': ('batch', 'num_keypoints'), 'cls_name': 'TensorType'}]) → Tensor, {'__torchtyping__': True, 'details': ('batch_minus_one', 'num_keypoints',), 'cls_name': 'TensorType'}]

__init__(data_module: BaseDataModule | UnlabeledDataModule | None = None, epsilon: float | list[float] = 0.0, prob_threshold: float = 0.0, log_weight: float = 0.0, **kwargs) → None

Parameters:

• data_module – give losses access to data for computing data-specific loss params

• epsilon – loss values below epsilon will be zeroed out

• log_weight – natural log of the weight in front of the loss term in the final objective function

__new__(**kwargs)