pocketpose.benchmarks.eval_coco_full
#
Module Contents#
Functions#
|
Crop an image. |
|
Scale keypoints from the bbox coordinates to the original image coordinates. |
|
Run inference on an image and convert the results to COCO format. |
|
Run inference for each image and store results in a JSON file. |
- pocketpose.benchmarks.eval_coco_full.crop(image_path, box)#
Crop an image.
- Args:
image_path (str): The path to the image. box (list): The bounding box coordinates as [xmin, ymin, width, height].
- Returns:
numpy.array: The cropped and resized image.
- pocketpose.benchmarks.eval_coco_full.scale_keypoints(keypoints, original_size, bbox)#
Scale keypoints from the bbox coordinates to the original image coordinates.
- Args:
keypoints (list): The keypoints in the cropped image. original_size (tuple): The size of the original image (width, height). box (list): The bounding box coordinates [xmin, ymin, width, height].
- Returns:
list: The scaled keypoints.
- pocketpose.benchmarks.eval_coco_full.infer_person(inferencer, image_path, bbox, kpt_thr=0.3, save_vis=None)#
Run inference on an image and convert the results to COCO format.
- Args:
inferencer (PoseInferencer): The PoseInferencer object. image_path (str): The path to the image. bbox (list): The bounding box coordinates [xmin, ymin, width, height]. kpt_thr (float): The score threshold to keep a keypoint (default: 0.3). save_vis (bool): Path to save the visualization of the keypoints. This will
slow down the evaluation, so it is recommended to only use this option for debugging purposes. If not None, it must point to an existing directory (default: None).
- pocketpose.benchmarks.eval_coco_full.infer_coco_full(inferencer, images_path, det_annotations_path, kpt_thr=0.3, save_vis=None)#
Run inference for each image and store results in a JSON file.
- Args:
inferencer (PoseInferencer): The PoseInferencer object. images_path (str): The path to the dataset images folder. det_annotations_path (str): The path to the detection annotations file. kpt_thr (float): The score threshold to keep a keypoint (default: 0.3). save_vis (bool): Path to save the visualization of the keypoints. This will
slow down the evaluation, so it is recommended to only use this option for debugging purposes (default: None).