File size: 5,108 Bytes
b3478e4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
# _base_ = [
#     '../../../../_base_/default_runtime.py',
#     '../../../../_base_/datasets/coco.py'
# ]
evaluation = dict(interval=10, metric='mAP', save_best='AP')

optimizer = dict(
    type='Adam',
    lr=5e-4,
)
optimizer_config = dict(grad_clip=None)
# learning policy
lr_config = dict(
    policy='step',
    warmup='linear',
    warmup_iters=500,
    warmup_ratio=0.001,
    step=[170, 200])
total_epochs = 210
channel_cfg = dict(
    num_output_channels=17,
    dataset_joints=17,
    dataset_channel=[
        [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16],
    ],
    inference_channel=[
        0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16
    ])

# model settings
model = dict(
    type='TopDown',
    pretrained='https://download.openmmlab.com/mmpose/'
    'pretrain_models/hrnet_w48-8ef0771d.pth',
    backbone=dict(
        type='HRNet',
        in_channels=3,
        extra=dict(
            stage1=dict(
                num_modules=1,
                num_branches=1,
                block='BOTTLENECK',
                num_blocks=(4, ),
                num_channels=(64, )),
            stage2=dict(
                num_modules=1,
                num_branches=2,
                block='BASIC',
                num_blocks=(4, 4),
                num_channels=(48, 96)),
            stage3=dict(
                num_modules=4,
                num_branches=3,
                block='BASIC',
                num_blocks=(4, 4, 4),
                num_channels=(48, 96, 192)),
            stage4=dict(
                num_modules=3,
                num_branches=4,
                block='BASIC',
                num_blocks=(4, 4, 4, 4),
                num_channels=(48, 96, 192, 384))),
    ),
    keypoint_head=dict(
        type='TopdownHeatmapSimpleHead',
        in_channels=48,
        out_channels=channel_cfg['num_output_channels'],
        num_deconv_layers=0,
        extra=dict(final_conv_kernel=1, ),
        loss_keypoint=dict(type='JointsMSELoss', use_target_weight=True)),
    train_cfg=dict(),
    test_cfg=dict(
        flip_test=True,
        post_process='default',
        shift_heatmap=True,
        modulate_kernel=11))

data_cfg = dict(
    image_size=[192, 256],
    heatmap_size=[48, 64],
    num_output_channels=channel_cfg['num_output_channels'],
    num_joints=channel_cfg['dataset_joints'],
    dataset_channel=channel_cfg['dataset_channel'],
    inference_channel=channel_cfg['inference_channel'],
    soft_nms=False,
    nms_thr=1.0,
    oks_thr=0.9,
    vis_thr=0.2,
    use_gt_bbox=False,
    det_bbox_thr=0.0,
    bbox_file='data/coco/person_detection_results/'
    'COCO_val2017_detections_AP_H_56_person.json',
)

train_pipeline = [
    dict(type='LoadImageFromFile'),
    dict(type='TopDownGetBboxCenterScale', padding=1.25),
    dict(type='TopDownRandomShiftBboxCenter', shift_factor=0.16, prob=0.3),
    dict(type='TopDownRandomFlip', flip_prob=0.5),
    dict(
        type='TopDownHalfBodyTransform',
        num_joints_half_body=8,
        prob_half_body=0.3),
    dict(
        type='TopDownGetRandomScaleRotation', rot_factor=40, scale_factor=0.5),
    dict(type='TopDownAffine'),
    dict(type='ToTensor'),
    dict(
        type='NormalizeTensor',
        mean=[0.485, 0.456, 0.406],
        std=[0.229, 0.224, 0.225]),
    dict(type='TopDownGenerateTarget', sigma=2),
    dict(
        type='Collect',
        keys=['img', 'target', 'target_weight'],
        meta_keys=[
            'image_file', 'joints_3d', 'joints_3d_visible', 'center', 'scale',
            'rotation', 'bbox_score', 'flip_pairs'
        ]),
]

val_pipeline = [
    dict(type='LoadImageFromFile'),
    dict(type='TopDownGetBboxCenterScale', padding=1.25),
    dict(type='TopDownAffine'),
    dict(type='ToTensor'),
    dict(
        type='NormalizeTensor',
        mean=[0.485, 0.456, 0.406],
        std=[0.229, 0.224, 0.225]),
    dict(
        type='Collect',
        keys=['img'],
        meta_keys=[
            'image_file', 'center', 'scale', 'rotation', 'bbox_score',
            'flip_pairs'
        ]),
]

test_pipeline = val_pipeline

data_root = 'data/coco'
data = dict(
    samples_per_gpu=32,
    workers_per_gpu=2,
    val_dataloader=dict(samples_per_gpu=32),
    test_dataloader=dict(samples_per_gpu=32),
    train=dict(
        type='TopDownCocoDataset',
        ann_file=f'{data_root}/annotations/person_keypoints_train2017.json',
        img_prefix=f'{data_root}/train2017/',
        data_cfg=data_cfg,
        pipeline=train_pipeline,
        dataset_info={{_base_.dataset_info}}),
    val=dict(
        type='TopDownCocoDataset',
        ann_file=f'{data_root}/annotations/person_keypoints_val2017.json',
        img_prefix=f'{data_root}/val2017/',
        data_cfg=data_cfg,
        pipeline=val_pipeline,
        dataset_info={{_base_.dataset_info}}),
    test=dict(
        type='TopDownCocoDataset',
        ann_file=f'{data_root}/annotations/person_keypoints_val2017.json',
        img_prefix=f'{data_root}/val2017/',
        data_cfg=data_cfg,
        pipeline=test_pipeline,
        dataset_info={{_base_.dataset_info}}),
)