File size: 4,902 Bytes
e26e560
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
_base_ = [
    '../_base_/datasets/coco_detection.py', '../_base_/default_runtime.py'
]
model = dict(
    type='DETR',
    pretrained='torchvision://resnet50',
    backbone=dict(
        type='ResNet',
        depth=50,
        num_stages=4,
        out_indices=(3, ),
        frozen_stages=1,
        norm_cfg=dict(type='BN', requires_grad=False),
        norm_eval=True,
        style='pytorch'),
    bbox_head=dict(
        type='TransformerHead',
        num_classes=80,
        in_channels=2048,
        num_fcs=2,
        transformer=dict(
            type='Transformer',
            embed_dims=256,
            num_heads=8,
            num_encoder_layers=6,
            num_decoder_layers=6,
            feedforward_channels=2048,
            dropout=0.1,
            act_cfg=dict(type='ReLU', inplace=True),
            norm_cfg=dict(type='LN'),
            num_fcs=2,
            pre_norm=False,
            return_intermediate_dec=True),
        positional_encoding=dict(
            type='SinePositionalEncoding', num_feats=128, normalize=True),
        loss_cls=dict(
            type='CrossEntropyLoss',
            bg_cls_weight=0.1,
            use_sigmoid=False,
            loss_weight=1.0,
            class_weight=1.0),
        loss_bbox=dict(type='L1Loss', loss_weight=5.0),
        loss_iou=dict(type='GIoULoss', loss_weight=2.0)),
    # training and testing settings
    train_cfg=dict(
        assigner=dict(
            type='HungarianAssigner',
            cls_cost=dict(type='ClassificationCost', weight=1.),
            reg_cost=dict(type='BBoxL1Cost', weight=5.0),
            iou_cost=dict(type='IoUCost', iou_mode='giou', weight=2.0))),
    test_cfg=dict(max_per_img=100))
img_norm_cfg = dict(
    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
# train_pipeline, NOTE the img_scale and the Pad's size_divisor is different
# from the default setting in mmdet.
train_pipeline = [
    dict(type='LoadImageFromFile'),
    dict(type='LoadAnnotations', with_bbox=True),
    dict(type='RandomFlip', flip_ratio=0.5),
    dict(
        type='AutoAugment',
        policies=[[
            dict(
                type='Resize',
                img_scale=[(480, 1333), (512, 1333), (544, 1333), (576, 1333),
                           (608, 1333), (640, 1333), (672, 1333), (704, 1333),
                           (736, 1333), (768, 1333), (800, 1333)],
                multiscale_mode='value',
                keep_ratio=True)
        ],
                  [
                      dict(
                          type='Resize',
                          img_scale=[(400, 1333), (500, 1333), (600, 1333)],
                          multiscale_mode='value',
                          keep_ratio=True),
                      dict(
                          type='RandomCrop',
                          crop_type='absolute_range',
                          crop_size=(384, 600),
                          allow_negative_crop=True),
                      dict(
                          type='Resize',
                          img_scale=[(480, 1333), (512, 1333), (544, 1333),
                                     (576, 1333), (608, 1333), (640, 1333),
                                     (672, 1333), (704, 1333), (736, 1333),
                                     (768, 1333), (800, 1333)],
                          multiscale_mode='value',
                          override=True,
                          keep_ratio=True)
                  ]]),
    dict(type='Normalize', **img_norm_cfg),
    dict(type='Pad', size_divisor=1),
    dict(type='DefaultFormatBundle'),
    dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels'])
]
# test_pipeline, NOTE the Pad's size_divisor is different from the default
# setting (size_divisor=32). While there is little effect on the performance
# whether we use the default setting or use size_divisor=1.
test_pipeline = [
    dict(type='LoadImageFromFile'),
    dict(
        type='MultiScaleFlipAug',
        img_scale=(1333, 800),
        flip=False,
        transforms=[
            dict(type='Resize', keep_ratio=True),
            dict(type='RandomFlip'),
            dict(type='Normalize', **img_norm_cfg),
            dict(type='Pad', size_divisor=1),
            dict(type='ImageToTensor', keys=['img']),
            dict(type='Collect', keys=['img'])
        ])
]
data = dict(
    samples_per_gpu=2,
    workers_per_gpu=2,
    train=dict(pipeline=train_pipeline),
    val=dict(pipeline=test_pipeline),
    test=dict(pipeline=test_pipeline))
# optimizer
optimizer = dict(
    type='AdamW',
    lr=0.0001,
    weight_decay=0.0001,
    paramwise_cfg=dict(
        custom_keys={'backbone': dict(lr_mult=0.1, decay_mult=1.0)}))
optimizer_config = dict(grad_clip=dict(max_norm=0.1, norm_type=2))
# learning policy
lr_config = dict(policy='step', step=[100])
runner = dict(type='EpochBasedRunner', max_epochs=150)