Source code for mmpose.datasets.datasets.top_down.topdown_h36m_dataset
# Copyright (c) OpenMMLab. All rights reserved.
import os.path as osp
import tempfile
import warnings
from collections import OrderedDict
import json_tricks as json
import numpy as np
from mmcv import Config, deprecated_api_warning
from ...builder import DATASETS
from ..base import Kpt2dSviewRgbImgTopDownDataset
[docs]@DATASETS.register_module()
class TopDownH36MDataset(Kpt2dSviewRgbImgTopDownDataset):
"""Human3.6M dataset for top-down 2D pose estimation.
"Human3.6M: Large Scale Datasets and Predictive Methods for 3D Human
Sensing in Natural Environments", TPAMI`2014.
More details can be found in the `paper
<http://vision.imar.ro/human3.6m/pami-h36m.pdf>`__.
Human3.6M keypoint indexes::
0: 'root (pelvis)',
1: 'right_hip',
2: 'right_knee',
3: 'right_foot',
4: 'left_hip',
5: 'left_knee',
6: 'left_foot',
7: 'spine',
8: 'thorax',
9: 'neck_base',
10: 'head',
11: 'left_shoulder',
12: 'left_elbow',
13: 'left_wrist',
14: 'right_shoulder',
15: 'right_elbow',
16: 'right_wrist'
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/h36m.py')
dataset_info = cfg._cfg_dict['dataset_info']
super().__init__(
ann_file,
img_prefix,
data_cfg,
pipeline,
dataset_info=dataset_info,
test_mode=test_mode)
self.db = self._get_db()
print(f'=> num_images: {self.num_images}')
print(f'=> load {len(self.db)} samples')
def _get_db(self):
"""Load dataset."""
gt_db = []
bbox_id = 0
num_joints = self.ann_info['num_joints']
for img_id in self.img_ids:
ann_ids = self.coco.getAnnIds(imgIds=img_id, iscrowd=False)
objs = self.coco.loadAnns(ann_ids)
for obj in objs:
if max(obj['keypoints']) == 0:
continue
joints_3d = np.zeros((num_joints, 3), dtype=np.float32)
joints_3d_visible = np.zeros((num_joints, 3), dtype=np.float32)
keypoints = np.array(obj['keypoints']).reshape(-1, 3)
joints_3d[:, :2] = keypoints[:, :2]
joints_3d_visible[:, :2] = np.minimum(1, keypoints[:, 2:3])
image_file = osp.join(self.img_prefix, self.id2name[img_id])
gt_db.append({
'image_file': image_file,
'rotation': 0,
'joints_3d': joints_3d,
'joints_3d_visible': joints_3d_visible,
'dataset': self.dataset_name,
'bbox': obj['bbox'],
'bbox_score': 1,
'bbox_id': bbox_id
})
bbox_id = bbox_id + 1
gt_db = sorted(gt_db, key=lambda x: x['bbox_id'])
return gt_db
[docs] @deprecated_api_warning(name_dict=dict(outputs='results'))
def evaluate(self, results, res_folder=None, metric='PCK', **kwargs):
"""Evaluate human3.6m 2d keypoint results. The pose prediction results
will be saved in `${res_folder}/result_keypoints.json`.
Note:
- batch_size: N
- num_keypoints: K
- heatmap height: H
- heatmap width: W
Args:
results (list[dict]): Testing results containing the following
items:
- preds (np.ndarray[N,K,3]): The first two dimensions are
coordinates, score is the third dimension of the array.
- boxes (np.ndarray[N,6]): [center[0], center[1], scale[0],
scale[1],area, score]
- image_paths (list[str]): For example, ['data/coco/val2017
/000000393226.jpg']
- heatmap (np.ndarray[N, K, H, W]): model output heatmap
- bbox_id (list(int)).
res_folder (str, optional): The folder to save the testing
results. If not specified, a temp folder will be created.
Default: None.
metric (str | list[str]): Metric to be performed. Defaults: 'PCK'.
Returns:
dict: Evaluation results for evaluation metric.
"""
metrics = metric if isinstance(metric, list) else [metric]
allowed_metrics = ['PCK', 'EPE']
for metric in metrics:
if metric not in allowed_metrics:
raise KeyError(f'metric {metric} is not supported')
if res_folder is not None:
tmp_folder = None
res_file = osp.join(res_folder, 'result_keypoints.json')
else:
tmp_folder = tempfile.TemporaryDirectory()
res_file = osp.join(tmp_folder.name, 'result_keypoints.json')
kpts = []
for result in results:
preds = result['preds']
boxes = result['boxes']
image_paths = result['image_paths']
bbox_ids = result['bbox_ids']
batch_size = len(image_paths)
for i in range(batch_size):
image_id = self.name2id[image_paths[i][len(self.img_prefix):]]
kpts.append({
'keypoints': preds[i].tolist(),
'center': boxes[i][0:2].tolist(),
'scale': boxes[i][2:4].tolist(),
'area': float(boxes[i][4]),
'score': float(boxes[i][5]),
'image_id': image_id,
'bbox_id': bbox_ids[i]
})
kpts = self._sort_and_unique_bboxes(kpts)
self._write_keypoint_results(kpts, res_file)
info_str = self._report_metric(res_file, metrics)
name_value = OrderedDict(info_str)
if tmp_folder is not None:
tmp_folder.cleanup()
return name_value
@staticmethod
def _write_keypoint_results(keypoints, res_file):
"""Write results into a json file."""
with open(res_file, 'w') as f:
json.dump(keypoints, f, sort_keys=True, indent=4)