File size: 4,435 Bytes
a249588
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
# model settings
data_preprocessor = dict(
    type='DetDataPreprocessor',
    mean=[123.675, 116.28, 103.53],
    std=[58.395, 57.12, 57.375],
    bgr_to_rgb=True,
    pad_size_divisor=1)
model = dict(
    type='SingleStageDetector',
    data_preprocessor=data_preprocessor,
    backbone=dict(
        type='MobileNetV2',
        out_indices=(4, 7),
        norm_cfg=dict(type='BN', eps=0.001, momentum=0.03),
        init_cfg=dict(type='TruncNormal', layer='Conv2d', std=0.03)),
    neck=dict(
        type='SSDNeck',
        in_channels=(96, 1280),
        out_channels=(96, 1280, 512, 256, 256, 128),
        level_strides=(2, 2, 2, 2),
        level_paddings=(1, 1, 1, 1),
        l2_norm_scale=None,
        use_depthwise=True,
        norm_cfg=dict(type='BN', eps=0.001, momentum=0.03),
        act_cfg=dict(type='ReLU6'),
        init_cfg=dict(type='TruncNormal', layer='Conv2d', std=0.03)),
    bbox_head=dict(
        type='SSDHead',
        in_channels=(96, 1280, 512, 256, 256, 128),
        num_classes=80,
        use_depthwise=True,
        norm_cfg=dict(type='BN', eps=0.001, momentum=0.03),
        act_cfg=dict(type='ReLU6'),
        init_cfg=dict(type='Normal', layer='Conv2d', std=0.001),

        # set anchor size manually instead of using the predefined
        # SSD300 setting.
        anchor_generator=dict(
            type='SSDAnchorGenerator',
            scale_major=False,
            strides=[16, 32, 64, 107, 160, 320],
            ratios=[[2, 3], [2, 3], [2, 3], [2, 3], [2, 3], [2, 3]],
            min_sizes=[48, 100, 150, 202, 253, 304],
            max_sizes=[100, 150, 202, 253, 304, 320]),
        bbox_coder=dict(
            type='DeltaXYWHBBoxCoder',
            target_means=[.0, .0, .0, .0],
            target_stds=[0.1, 0.1, 0.2, 0.2])),
    # model training and testing settings
    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),
        sampler=dict(type='PseudoSampler'),
        smoothl1_beta=1.,
        allowed_border=-1,
        pos_weight=-1,
        neg_pos_ratio=3,
        debug=False),
    test_cfg=dict(
        nms_pre=1000,
        nms=dict(type='nms', iou_threshold=0.45),
        min_bbox_size=0,
        score_thr=0.02,
        max_per_img=200))
env_cfg = dict(cudnn_benchmark=True)

# dataset settings
dataset_type = 'CocoDataset'
data_root = 'data/coco/'

input_size = 320
train_pipeline = [
    dict(type='LoadImageFromFile'),
    dict(type='LoadAnnotations', with_bbox=True),
    dict(
        type='Expand',
        mean=data_preprocessor['mean'],
        to_rgb=data_preprocessor['bgr_to_rgb'],
        ratio_range=(1, 4)),
    dict(
        type='MinIoURandomCrop',
        min_ious=(0.1, 0.3, 0.5, 0.7, 0.9),
        min_crop_size=0.3),
    dict(type='Resize', scale=(input_size, input_size), keep_ratio=False),
    dict(type='RandomFlip', prob=0.5),
    dict(
        type='PhotoMetricDistortion',
        brightness_delta=32,
        contrast_range=(0.5, 1.5),
        saturation_range=(0.5, 1.5),
        hue_delta=18),
    dict(type='PackDetInputs')
]
test_pipeline = [
    dict(type='LoadImageFromFile'),
    dict(type='Resize', scale=(input_size, input_size), keep_ratio=False),
    dict(type='LoadAnnotations', with_bbox=True),
    dict(
        type='PackDetInputs',
        meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
                   'scale_factor'))
]
train_dataloader = dict(
    batch_size=24,
    num_workers=4,
    batch_sampler=None,
    dataset=dict(
        _delete_=True,
        type='RepeatDataset',
        times=5,
        dataset=dict(
            type=dataset_type,
            data_root=data_root,
            ann_file='annotations/instances_train2017.json',
            data_prefix=dict(img='train2017/'),
            filter_cfg=dict(filter_empty_gt=True, min_size=32),
            pipeline=train_pipeline)))
val_dataloader = dict(
    batch_size=8,
    num_workers=2,
    persistent_workers=True,
    drop_last=False,
    sampler=dict(type='DefaultSampler', shuffle=False),
    dataset=dict(
        type=dataset_type,
        data_root=data_root,
        ann_file='annotations/instances_val2017.json',
        data_prefix=dict(img='val2017/'),
        test_mode=True,
        pipeline=test_pipeline))
test_dataloader = val_dataloader