HeatmapLoss

class lightning_pose.losses.losses.HeatmapLoss

Bases: Loss

Parent class for different heatmap losses (MSE, Wasserstein, etc).

Methods Summary

__call__(heatmaps_targ, heatmaps_pred[, stage])	Call self as a function.
compute_loss(**kwargs)
remove_nans(targets, predictions)

Methods Documentation

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

Call self as a function.

compute_loss(**kwargs)

remove_nans(targets: Tensor, {'__torchtyping__': True, 'details': ('batch', 'num_keypoints', 'heatmap_height', 'heatmap_width'), 'cls_name': 'TensorType'}], predictions: Tensor, {'__torchtyping__': True, 'details': ('batch', 'num_keypoints', 'heatmap_height', 'heatmap_width'), 'cls_name': 'TensorType'}]) → Tensor, {'__torchtyping__': True, 'details': ('num_valid_keypoints', 'heatmap_height', 'heatmap_width',), 'cls_name': 'TensorType'}]]

__init__(data_module: BaseDataModule | UnlabeledDataModule | None = None, 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)