pocketpose#

Subpackages#

Submodules#

Package Contents#

Classes#

PoseInferencer

PoseInferencer provides a unified interface to infer poses from images.

class pocketpose.PoseInferencer(model_name, radius: float = 5, thickness: int = 3, kpt_thr: float = 0.3, draw_bbox: bool = False, return_vis: bool = False, vis_out_dir: str | None = None)#

PoseInferencer provides a unified interface to infer poses from images.

Args:

model_name (str): Name of the model to use radius (float): Sets the visualization keypoint radius. thickness (int): Determines the link thickness for visualization. kpt_thr (float): Sets the keypoint score threshold. Keypoints with scores exceeding

this threshold will be displayed.

draw_bbox (bool): Decides whether to display the bounding boxes of instances. return_vis (bool): Decides whether to include visualization images in the results. vis_out_dir (str): Defines the folder path to save the visualization images. If unset,

the visualization images will not be saved.

infer(image_path: str)#

Infer poses from an image file.

Args:

image_path (str): Path to the image file.