SemiSupervisedRegressionTracker

class lightning_pose.models.regression_tracker.SemiSupervisedRegressionTracker(num_keypoints: int, loss_factory: LossFactory | None = None, loss_factory_unsupervised: LossFactory | None = None, backbone: Literal['resnet18', 'resnet34', 'resnet50', 'resnet101', 'resnet152', 'resnet50_contrastive', 'resnet50_animal_apose', 'resnet50_animal_ap10k', 'resnet50_human_jhmdb', 'resnet50_human_res_rle', 'resnet50_human_top_res', 'resnet50_human_hand', 'efficientnet_b0', 'efficientnet_b1', 'efficientnet_b2', 'vit_b_sam'] = 'resnet50', pretrained: bool = True, torch_seed: int = 123, lr_scheduler: str = 'multisteplr', lr_scheduler_params: DictConfig | dict | None = None, **kwargs: Any)

Bases: SemiSupervisedTrackerMixin, RegressionTracker

Model produces vectors of keypoints from labeled/unlabeled images.

Methods Summary

get_loss_inputs_unlabeled(batch_dict)

Return predicted heatmaps and their softmaxes (estimated keypoints).

Methods Documentation

get_loss_inputs_unlabeled(batch_dict: UnlabeledBatchDict) → Dict

Return predicted heatmaps and their softmaxes (estimated keypoints).