dgs.models.dataset.posetrack21¶
Load bboxes and poses from an existing .json file of the PoseTrack21
dataset.
See https://github.com/anDoer/PoseTrack21/blob/main/doc/dataset_structure.md#reid-pose-tracking for type definitions.
PoseTrack21 format:
Bounding boxes have format XYWH
The 17 key points and their respective visibilities are stored in one list of len 51. The list contains the x- and y-coordinate and the visibility: n [
x
i,y
i,vis
i, …]
Notes
The original P21-paper said, that during evaluation they ignore all person detections that overlap with the ignore regions.
Module Functions
|
Given the path to the |
|
Given the path to a json file containing images and annotations in the PT21 style, extract all the bbox image crops. |
|
This function will extract the image crops and image-crop-local key-point coordinates, given the full |
|
Check whether the given json is valid for the PoseTrack21 dataset. |
Module Classes
|
Abstract base class for the |
|
Load PoseTrack21 as torchreid dataset. |
|
Load a single precomputed json file from the |
|
Load a single precomputed json file from the |
|
A |