File size: 4,358 Bytes
d7a991a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
# Copyright (c) OpenMMLab. All rights reserved.
import os
import warnings
from argparse import ArgumentParser

from mmpose.apis import (inference_top_down_pose_model, init_pose_model,
                         vis_pose_result)
from mmpose.datasets import DatasetInfo

try:
    import face_recognition
    has_face_det = True
except (ImportError, ModuleNotFoundError):
    has_face_det = False


def process_face_det_results(face_det_results):
    """Process det results, and return a list of bboxes.

    :param face_det_results: (top, right, bottom and left)
    :return: a list of detected bounding boxes (x,y,x,y)-format
    """

    person_results = []
    for bbox in face_det_results:
        person = {}
        # left, top, right, bottom
        person['bbox'] = [bbox[3], bbox[0], bbox[1], bbox[2]]
        person_results.append(person)

    return person_results


def main():
    """Visualize the demo images.

    Using mmdet to detect the human.
    """
    parser = ArgumentParser()
    parser.add_argument('pose_config', help='Config file for pose')
    parser.add_argument('pose_checkpoint', help='Checkpoint file for pose')
    parser.add_argument('--img-root', type=str, default='', help='Image root')
    parser.add_argument('--img', type=str, default='', help='Image file')
    parser.add_argument(
        '--show',
        action='store_true',
        default=False,
        help='whether to show img')
    parser.add_argument(
        '--out-img-root',
        type=str,
        default='',
        help='root of the output img file. '
        'Default not saving the visualization images.')
    parser.add_argument(
        '--device', default='cuda:0', help='Device used for inference')
    parser.add_argument(
        '--kpt-thr', type=float, default=0.3, help='Keypoint score threshold')
    parser.add_argument(
        '--radius',
        type=int,
        default=4,
        help='Keypoint radius for visualization')
    parser.add_argument(
        '--thickness',
        type=int,
        default=1,
        help='Link thickness for visualization')

    assert has_face_det, 'Please install face_recognition to run the demo. ' \
                         '"pip install face_recognition", For more details, ' \
                         'see https://github.com/ageitgey/face_recognition'

    args = parser.parse_args()

    assert args.show or (args.out_img_root != '')
    assert args.img != ''

    # build the pose model from a config file and a checkpoint file
    pose_model = init_pose_model(
        args.pose_config, args.pose_checkpoint, device=args.device.lower())

    dataset = pose_model.cfg.data['test']['type']
    dataset_info = pose_model.cfg.data['test'].get('dataset_info', None)
    if dataset_info is None:
        warnings.warn(
            'Please set `dataset_info` in the config.'
            'Check https://github.com/open-mmlab/mmpose/pull/663 for details.',
            DeprecationWarning)
    else:
        dataset_info = DatasetInfo(dataset_info)

    image_name = os.path.join(args.img_root, args.img)

    # test a single image, the resulting box is (top, right, bottom and left)
    image = face_recognition.load_image_file(image_name)
    face_det_results = face_recognition.face_locations(image)

    # keep the person class bounding boxes.
    face_results = process_face_det_results(face_det_results)

    # optional
    return_heatmap = False

    # e.g. use ('backbone', ) to return backbone feature
    output_layer_names = None

    pose_results, returned_outputs = inference_top_down_pose_model(
        pose_model,
        image_name,
        face_results,
        bbox_thr=None,
        format='xyxy',
        dataset=dataset,
        dataset_info=dataset_info,
        return_heatmap=return_heatmap,
        outputs=output_layer_names)

    if args.out_img_root == '':
        out_file = None
    else:
        os.makedirs(args.out_img_root, exist_ok=True)
        out_file = os.path.join(args.out_img_root, f'vis_{args.img}')

    # show the results
    vis_pose_result(
        pose_model,
        image_name,
        pose_results,
        radius=args.radius,
        thickness=args.thickness,
        dataset=dataset,
        dataset_info=dataset_info,
        kpt_score_thr=args.kpt_thr,
        show=args.show,
        out_file=out_file)


if __name__ == '__main__':
    main()