File size: 2,946 Bytes
412c852
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
norm_cfg = dict(type='BN', requires_grad=True)
data_preprocessor = dict(
    type='SegDataPreProcessor',
    mean=[123.675, 116.28, 103.53],
    std=[58.395, 57.12, 57.375],
    bgr_to_rgb=True,
    pad_val=0,
    seg_pad_val=255)
model = dict(
    type='EncoderDecoder',
    data_preprocessor=data_preprocessor,
    pretrained=None,
    backbone=dict(
        type='STDCContextPathNet',
        backbone_cfg=dict(
            type='STDCNet',
            stdc_type='STDCNet1',
            in_channels=3,
            channels=(32, 64, 256, 512, 1024),
            bottleneck_type='cat',
            num_convs=4,
            norm_cfg=norm_cfg,
            act_cfg=dict(type='ReLU'),
            with_final_conv=False),
        last_in_channels=(1024, 512),
        out_channels=128,
        ffm_cfg=dict(in_channels=384, out_channels=256, scale_factor=4)),
    decode_head=dict(
        type='FCNHead',
        in_channels=256,
        channels=256,
        num_convs=1,
        num_classes=19,
        in_index=3,
        concat_input=False,
        dropout_ratio=0.1,
        norm_cfg=norm_cfg,
        align_corners=True,
        sampler=dict(type='OHEMPixelSampler', thresh=0.7, min_kept=10000),
        loss_decode=dict(
            type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)),
    auxiliary_head=[
        dict(
            type='FCNHead',
            in_channels=128,
            channels=64,
            num_convs=1,
            num_classes=19,
            in_index=2,
            norm_cfg=norm_cfg,
            concat_input=False,
            align_corners=False,
            sampler=dict(type='OHEMPixelSampler', thresh=0.7, min_kept=10000),
            loss_decode=dict(
                type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)),
        dict(
            type='FCNHead',
            in_channels=128,
            channels=64,
            num_convs=1,
            num_classes=19,
            in_index=1,
            norm_cfg=norm_cfg,
            concat_input=False,
            align_corners=False,
            sampler=dict(type='OHEMPixelSampler', thresh=0.7, min_kept=10000),
            loss_decode=dict(
                type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)),
        dict(
            type='STDCHead',
            in_channels=256,
            channels=64,
            num_convs=1,
            num_classes=2,
            boundary_threshold=0.1,
            in_index=0,
            norm_cfg=norm_cfg,
            concat_input=False,
            align_corners=True,
            loss_decode=[
                dict(
                    type='CrossEntropyLoss',
                    loss_name='loss_ce',
                    use_sigmoid=True,
                    loss_weight=1.0),
                dict(type='DiceLoss', loss_name='loss_dice', loss_weight=1.0)
            ]),
    ],
    # model training and testing settings
    train_cfg=dict(),
    test_cfg=dict(mode='whole'))