Skip to content

GitLab

Switch branch/tag
Find file Normal viewHistoryPermalink
ssd300_wider_face.py 3.92 KB
Newer Older
Vladislav Sovrasov's avatar
Add support of the wider face dataset (#765)  
Vladislav Sovrasov committed
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 
# model settings
input_size = 300
model = dict(
    type='SingleStageDetector',
    pretrained='open-mmlab://vgg16_caffe',
    backbone=dict(
        type='SSDVGG',
        input_size=input_size,
        depth=16,
        with_last_pool=False,
        ceil_mode=True,
        out_indices=(3, 4),
        out_feature_indices=(22, 34),
        l2_norm_scale=20),
    neck=None,
    bbox_head=dict(
        type='SSDHead',
        input_size=input_size,
        in_channels=(512, 1024, 512, 256, 256, 256),
        num_classes=2,
        anchor_strides=(8, 16, 32, 64, 100, 300),
        basesize_ratio_range=(0.15, 0.9),
        anchor_ratios=([2], [2, 3], [2, 3], [2, 3], [2], [2]),
        target_means=(.0, .0, .0, .0),
        target_stds=(0.1, 0.1, 0.2, 0.2)))
cudnn_benchmark = True
train_cfg = dict(
    assigner=dict(
        type='MaxIoUAssigner',
        pos_iou_thr=0.5,
        neg_iou_thr=0.5,
        min_pos_iou=0.,
        ignore_iof_thr=-1,
        gt_max_assign_all=False),
    smoothl1_beta=1.,
    allowed_border=-1,
    pos_weight=-1,
    neg_pos_ratio=3,
    debug=False)
test_cfg = dict(
    nms=dict(type='nms', iou_thr=0.45),
    min_bbox_size=0,
    score_thr=0.02,
    max_per_img=200)
# model training and testing settings
# dataset settings
dataset_type = 'WIDERFaceDataset'
data_root = 'data/WIDERFace/'
img_norm_cfg = dict(mean=[123.675, 116.28, 103.53], std=[1, 1, 1], to_rgb=True)
data = dict(
    imgs_per_gpu=60,
    workers_per_gpu=2,
    train=dict(
        type='RepeatDataset',
        times=2,
        dataset=dict(
            type=dataset_type,
            ann_file=[
                data_root + 'train.txt',
            ],
            img_prefix=[data_root + 'WIDER_train/'],
            img_scale=(300, 300),
            min_size=17,  # throw away very small faces to improve training,
            # because 300x300 is too low resolution to detect them
            img_norm_cfg=img_norm_cfg,
            size_divisor=None,
            flip_ratio=0.5,
            with_mask=False,
            with_crowd=False,
            with_label=True,
            test_mode=False,
            extra_aug=dict(
                photo_metric_distortion=dict(
                    brightness_delta=32,
                    contrast_range=(0.5, 1.5),
                    saturation_range=(0.5, 1.5),
                    hue_delta=18),
                expand=dict(
                    mean=img_norm_cfg['mean'],
                    to_rgb=img_norm_cfg['to_rgb'],
                    ratio_range=(1, 4)),
                random_crop=dict(
                    min_ious=(0.1, 0.3, 0.5, 0.7, 0.9), min_crop_size=0.3)),
            resize_keep_ratio=False)),
    val=dict(
        type=dataset_type,
        ann_file=data_root + '/val.txt',
        img_prefix=data_root + 'WIDER_val/',
        img_scale=(300, 300),
        img_norm_cfg=img_norm_cfg,
        size_divisor=None,
        flip_ratio=0,
        with_mask=False,
        with_label=False,
        test_mode=True,
        resize_keep_ratio=False),
    test=dict(
        type=dataset_type,
        ann_file=data_root + '/val.txt',
        img_prefix=data_root + 'WIDER_val/',
        img_scale=(300, 300),
        img_norm_cfg=img_norm_cfg,
        size_divisor=None,
        flip_ratio=0,
        with_mask=False,
        with_label=False,
        test_mode=True,
        resize_keep_ratio=False))
# optimizer
optimizer = dict(type='SGD', lr=1e-3, momentum=0.9, weight_decay=5e-4)
optimizer_config = dict()
# learning policy
lr_config = dict(
    policy='step',
    warmup='linear',
    warmup_iters=1000,
    warmup_ratio=1.0 / 3,
    step=[16, 20])
checkpoint_config = dict(interval=1)
# yapf:disable
log_config = dict(
    interval=1,
    hooks=[
        dict(type='TextLoggerHook'),
        dict(type='TensorboardLoggerHook')
    ])
# yapf:enable
# runtime settings
total_epochs = 24
dist_params = dict(backend='nccl')
log_level = 'INFO'
work_dir = './work_dirs/ssd300_wider'
load_from = None
resume_from = None
workflow = [('train', 1)]