easycv.datasets.pose package

class easycv.datasets.pose.PoseTopDownDataset(data_source, pipeline, profiling=False)

Bases: Generic[torch.utils.data.dataset.T_co]

PoseTopDownDataset dataset for top-down pose estimation. The dataset loads raw features and apply specified transforms to return a dict containing the image tensors and other information.

Parameters

• data_source – Data_source config dict

• pipeline – Pipeline config list

• profiling – If set True, will print pipeline time

__init__(data_source, pipeline, profiling=False)

Initialize self. See help(type(self)) for accurate signature.

evaluate(outputs, evaluators, **kwargs)

class easycv.datasets.pose.HandCocoWholeBodyDataset(data_source, pipeline, profiling=False)

Bases: Generic[torch.utils.data.dataset.T_co]

CocoWholeBodyDataset for top-down hand pose estimation.

Parameters

• data_source – Data_source config dict

• pipeline – Pipeline config list

• profiling – If set True, will print pipeline time

__init__(data_source, pipeline, profiling=False)

Initialize self. See help(type(self)) for accurate signature.

evaluate(outputs, evaluators, **kwargs)

class easycv.datasets.pose.WholeBodyCocoTopDownDataset(data_source, pipeline, profiling=False)

Bases: Generic[torch.utils.data.dataset.T_co]

CocoWholeBodyDataset dataset for top-down pose estimation.

Parameters

• data_source – Data_source config dict

• pipeline – Pipeline config list

• profiling – If set True, will print pipeline time

__init__(data_source, pipeline, profiling=False)

Initialize self. See help(type(self)) for accurate signature.

evaluate(outputs, evaluators, **kwargs)

Subpackages

• easycv.datasets.pose.data_sources package
  • Submodules
  • easycv.datasets.pose.data_sources.coco module
  • easycv.datasets.pose.data_sources.top_down module
• easycv.datasets.pose.pipelines package
  • Submodules
  • easycv.datasets.pose.pipelines.transforms module

Submodules

easycv.datasets.pose.top_down module

class easycv.datasets.pose.top_down.PoseTopDownDataset(data_source, pipeline, profiling=False)

Bases: Generic[torch.utils.data.dataset.T_co]

PoseTopDownDataset dataset for top-down pose estimation. The dataset loads raw features and apply specified transforms to return a dict containing the image tensors and other information.

Parameters

• data_source – Data_source config dict

• pipeline – Pipeline config list

• profiling – If set True, will print pipeline time

__init__(data_source, pipeline, profiling=False)

Initialize self. See help(type(self)) for accurate signature.

evaluate(outputs, evaluators, **kwargs)