Image Segmentation
Transformers
PyTorch
upernet
Inference Endpoints
File size: 7,010 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
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
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
from mmcv.cnn import ConvModule
from torch import nn as nn
from torch.utils import checkpoint as cp

from .se_layer import SELayer


class InvertedResidual(nn.Module):
    """InvertedResidual block for MobileNetV2.

    Args:
        in_channels (int): The input channels of the InvertedResidual block.
        out_channels (int): The output channels of the InvertedResidual block.
        stride (int): Stride of the middle (first) 3x3 convolution.
        expand_ratio (int): Adjusts number of channels of the hidden layer
            in InvertedResidual by this amount.
        dilation (int): Dilation rate of depthwise conv. Default: 1
        conv_cfg (dict): Config dict for convolution layer.
            Default: None, which means using conv2d.
        norm_cfg (dict): Config dict for normalization layer.
            Default: dict(type='BN').
        act_cfg (dict): Config dict for activation layer.
            Default: dict(type='ReLU6').
        with_cp (bool): Use checkpoint or not. Using checkpoint will save some
            memory while slowing down the training speed. Default: False.

    Returns:
        Tensor: The output tensor.
    """

    def __init__(self,
                 in_channels,
                 out_channels,
                 stride,
                 expand_ratio,
                 dilation=1,
                 conv_cfg=None,
                 norm_cfg=dict(type='BN'),
                 act_cfg=dict(type='ReLU6'),
                 with_cp=False):
        super(InvertedResidual, self).__init__()
        self.stride = stride
        assert stride in [1, 2], f'stride must in [1, 2]. ' \
            f'But received {stride}.'
        self.with_cp = with_cp
        self.use_res_connect = self.stride == 1 and in_channels == out_channels
        hidden_dim = int(round(in_channels * expand_ratio))

        layers = []
        if expand_ratio != 1:
            layers.append(
                ConvModule(
                    in_channels=in_channels,
                    out_channels=hidden_dim,
                    kernel_size=1,
                    conv_cfg=conv_cfg,
                    norm_cfg=norm_cfg,
                    act_cfg=act_cfg))
        layers.extend([
            ConvModule(
                in_channels=hidden_dim,
                out_channels=hidden_dim,
                kernel_size=3,
                stride=stride,
                padding=dilation,
                dilation=dilation,
                groups=hidden_dim,
                conv_cfg=conv_cfg,
                norm_cfg=norm_cfg,
                act_cfg=act_cfg),
            ConvModule(
                in_channels=hidden_dim,
                out_channels=out_channels,
                kernel_size=1,
                conv_cfg=conv_cfg,
                norm_cfg=norm_cfg,
                act_cfg=None)
        ])
        self.conv = nn.Sequential(*layers)

    def forward(self, x):

        def _inner_forward(x):
            if self.use_res_connect:
                return x + self.conv(x)
            else:
                return self.conv(x)

        if self.with_cp and x.requires_grad:
            out = cp.checkpoint(_inner_forward, x)
        else:
            out = _inner_forward(x)

        return out


class InvertedResidualV3(nn.Module):
    """Inverted Residual Block for MobileNetV3.

    Args:
        in_channels (int): The input channels of this Module.
        out_channels (int): The output channels of this Module.
        mid_channels (int): The input channels of the depthwise convolution.
        kernel_size (int): The kernal size of the depthwise convolution.
            Default: 3.
        stride (int): The stride of the depthwise convolution. Default: 1.
        se_cfg (dict): Config dict for se layer. Defaul: None, which means no
            se layer.
        with_expand_conv (bool): Use expand conv or not. If set False,
            mid_channels must be the same with in_channels. Default: True.
        conv_cfg (dict): Config dict for convolution layer. Default: None,
            which means using conv2d.
        norm_cfg (dict): Config dict for normalization layer.
            Default: dict(type='BN').
        act_cfg (dict): Config dict for activation layer.
            Default: dict(type='ReLU').
        with_cp (bool): Use checkpoint or not. Using checkpoint will save some
            memory while slowing down the training speed. Default: False.

    Returns:
        Tensor: The output tensor.
    """

    def __init__(self,
                 in_channels,
                 out_channels,
                 mid_channels,
                 kernel_size=3,
                 stride=1,
                 se_cfg=None,
                 with_expand_conv=True,
                 conv_cfg=None,
                 norm_cfg=dict(type='BN'),
                 act_cfg=dict(type='ReLU'),
                 with_cp=False):
        super(InvertedResidualV3, self).__init__()
        self.with_res_shortcut = (stride == 1 and in_channels == out_channels)
        assert stride in [1, 2]
        self.with_cp = with_cp
        self.with_se = se_cfg is not None
        self.with_expand_conv = with_expand_conv

        if self.with_se:
            assert isinstance(se_cfg, dict)
        if not self.with_expand_conv:
            assert mid_channels == in_channels

        if self.with_expand_conv:
            self.expand_conv = ConvModule(
                in_channels=in_channels,
                out_channels=mid_channels,
                kernel_size=1,
                stride=1,
                padding=0,
                conv_cfg=conv_cfg,
                norm_cfg=norm_cfg,
                act_cfg=act_cfg)
        self.depthwise_conv = ConvModule(
            in_channels=mid_channels,
            out_channels=mid_channels,
            kernel_size=kernel_size,
            stride=stride,
            padding=kernel_size // 2,
            groups=mid_channels,
            conv_cfg=dict(
                type='Conv2dAdaptivePadding') if stride == 2 else conv_cfg,
            norm_cfg=norm_cfg,
            act_cfg=act_cfg)

        if self.with_se:
            self.se = SELayer(**se_cfg)

        self.linear_conv = ConvModule(
            in_channels=mid_channels,
            out_channels=out_channels,
            kernel_size=1,
            stride=1,
            padding=0,
            conv_cfg=conv_cfg,
            norm_cfg=norm_cfg,
            act_cfg=None)

    def forward(self, x):

        def _inner_forward(x):
            out = x

            if self.with_expand_conv:
                out = self.expand_conv(out)

            out = self.depthwise_conv(out)

            if self.with_se:
                out = self.se(out)

            out = self.linear_conv(out)

            if self.with_res_shortcut:
                return x + out
            else:
                return out

        if self.with_cp and x.requires_grad:
            out = cp.checkpoint(_inner_forward, x)
        else:
            out = _inner_forward(x)

        return out