Image Segmentation
Transformers
PyTorch
upernet
Inference Endpoints
File size: 2,196 Bytes
b13b124
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
# model settings
norm_cfg = dict(type='SyncBN', requires_grad=True)
model = dict(
    type='CascadeEncoderDecoder',
    num_stages=2,
    pretrained='open-mmlab://msra/hrnetv2_w18',
    backbone=dict(
        type='HRNet',
        norm_cfg=norm_cfg,
        norm_eval=False,
        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=(18, 36)),
            stage3=dict(
                num_modules=4,
                num_branches=3,
                block='BASIC',
                num_blocks=(4, 4, 4),
                num_channels=(18, 36, 72)),
            stage4=dict(
                num_modules=3,
                num_branches=4,
                block='BASIC',
                num_blocks=(4, 4, 4, 4),
                num_channels=(18, 36, 72, 144)))),
    decode_head=[
        dict(
            type='FCNHead',
            in_channels=[18, 36, 72, 144],
            channels=sum([18, 36, 72, 144]),
            in_index=(0, 1, 2, 3),
            input_transform='resize_concat',
            kernel_size=1,
            num_convs=1,
            concat_input=False,
            dropout_ratio=-1,
            num_classes=19,
            norm_cfg=norm_cfg,
            align_corners=False,
            loss_decode=dict(
                type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.4)),
        dict(
            type='OCRHead',
            in_channels=[18, 36, 72, 144],
            in_index=(0, 1, 2, 3),
            input_transform='resize_concat',
            channels=512,
            ocr_channels=256,
            dropout_ratio=-1,
            num_classes=19,
            norm_cfg=norm_cfg,
            align_corners=False,
            loss_decode=dict(
                type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)),
    ],
    # model training and testing settings
    train_cfg=dict(),
    test_cfg=dict(mode='whole'))