Source code for mmpose.datasets.datasets.bottom_up.bottom_up_crowdpose
# Copyright (c) OpenMMLab. All rights reserved.
import warnings
import json_tricks as json
from mmcv import Config
from xtcocotools.cocoeval import COCOeval
from mmpose.datasets.builder import DATASETS
from .bottom_up_coco import BottomUpCocoDataset
[docs]@DATASETS.register_module()
class BottomUpCrowdPoseDataset(BottomUpCocoDataset):
"""CrowdPose dataset for bottom-up pose estimation.
"CrowdPose: Efficient Crowded Scenes Pose Estimation and
A New Benchmark", CVPR'2019.
More details can be found in the `paper
<https://arxiv.org/abs/1812.00324>`__.
The dataset loads raw features and apply specified transforms
to return a dict containing the image tensors and other information.
CrowdPose keypoint indexes::
0: 'left_shoulder',
1: 'right_shoulder',
2: 'left_elbow',
3: 'right_elbow',
4: 'left_wrist',
5: 'right_wrist',
6: 'left_hip',
7: 'right_hip',
8: 'left_knee',
9: 'right_knee',
10: 'left_ankle',
11: 'right_ankle',
12: 'top_head',
13: 'neck'
Args:
ann_file (str): Path to the annotation file.
img_prefix (str): Path to a directory where images are held.
Default: None.
data_cfg (dict): config
pipeline (list[dict | callable]): A sequence of data transforms.
dataset_info (DatasetInfo): A class containing all dataset info.
test_mode (bool): Store True when building test or
validation dataset. Default: False.
"""
def __init__(self,
ann_file,
img_prefix,
data_cfg,
pipeline,
dataset_info=None,
test_mode=False):
if dataset_info is None:
warnings.warn(
'dataset_info is missing. '
'Check https://github.com/open-mmlab/mmpose/pull/663 '
'for details.', DeprecationWarning)
cfg = Config.fromfile('configs/_base_/datasets/crowdpose.py')
dataset_info = cfg._cfg_dict['dataset_info']
super(BottomUpCocoDataset, self).__init__(
ann_file,
img_prefix,
data_cfg,
pipeline,
dataset_info=dataset_info,
test_mode=test_mode)
self.ann_info['use_different_joint_weights'] = False
print(f'=> num_images: {self.num_images}')
def _do_python_keypoint_eval(self, res_file):
"""Keypoint evaluation using COCOAPI."""
stats_names = [
'AP', 'AP .5', 'AP .75', 'AR', 'AR .5', 'AR .75', 'AP(E)', 'AP(M)',
'AP(H)'
]
with open(res_file, 'r') as file:
res_json = json.load(file)
if not res_json:
info_str = list(zip(stats_names, [
0,
] * len(stats_names)))
return info_str
coco_det = self.coco.loadRes(res_file)
coco_eval = COCOeval(
self.coco,
coco_det,
'keypoints_crowd',
self.sigmas,
use_area=False)
coco_eval.params.useSegm = None
coco_eval.evaluate()
coco_eval.accumulate()
coco_eval.summarize()
info_str = list(zip(stats_names, coco_eval.stats))
return info_str