File size: 8,185 Bytes
51da11a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
# BSD 3-Clause License

# Copyright (c) Soumith Chintala 2016,
# All rights reserved.

# Redistribution and use in source and binary forms, with or without
# modification, are permitted provided that the following conditions are met:

# * Redistributions of source code must retain the above copyright notice, this
#  list of conditions and the following disclaimer.

# * Redistributions in binary form must reproduce the above copyright notice,
#  this list of conditions and the following disclaimer in the documentation
#  and/or other materials provided with the distribution.

# * Neither the name of the copyright holder nor the names of its
#  contributors may be used to endorse or promote products derived from
#  this software without specific prior written permission.

# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
# AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
# DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE
# FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
# DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
# SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
# CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
# OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
# OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

# Adaptation of the PyTorch torchvision MobileNetV2 without a classifier.
# See source here: https://pytorch.org/vision/0.8/_modules/torchvision/models/mobilenet.html#mobilenet_v2
from torch import nn


def _make_divisible(v, divisor, min_value=None):
    """
    This function is taken from the original tf repo.
    It ensures that all layers have a channel number that is divisible by 8
    It can be seen here:
    https://github.com/tensorflow/models/blob/master/research/slim/nets/mobilenet/mobilenet.py
    :param v:
    :param divisor:
    :param min_value:
    :return:
    """
    if min_value is None:
        min_value = divisor
    new_v = max(min_value, int(v + divisor / 2) // divisor * divisor)
    # Make sure that round down does not go down by more than 10%.
    if new_v < 0.9 * v:
        new_v += divisor
    return new_v


class ConvBNReLU(nn.Sequential):
    def __init__(
        self, in_planes, out_planes, kernel_size=3, stride=1, groups=1, norm_layer=None
    ):
        padding = (kernel_size - 1) // 2
        if norm_layer is None:
            norm_layer = nn.BatchNorm2d
        super(ConvBNReLU, self).__init__(
            nn.Conv2d(
                in_planes,
                out_planes,
                kernel_size,
                stride,
                padding,
                groups=groups,
                bias=False,
            ),
            norm_layer(out_planes),
            nn.ReLU6(inplace=True),
        )


class InvertedResidual(nn.Module):
    def __init__(self, inp, oup, stride, expand_ratio, norm_layer=None):
        super(InvertedResidual, self).__init__()
        self.stride = stride
        assert stride in [1, 2]

        if norm_layer is None:
            norm_layer = nn.BatchNorm2d

        hidden_dim = int(round(inp * expand_ratio))
        self.use_res_connect = self.stride == 1 and inp == oup

        layers = []
        if expand_ratio != 1:
            # pw
            layers.append(
                ConvBNReLU(inp, hidden_dim, kernel_size=1, norm_layer=norm_layer)
            )
        layers.extend(
            [
                # dw
                ConvBNReLU(
                    hidden_dim,
                    hidden_dim,
                    stride=stride,
                    groups=hidden_dim,
                    norm_layer=norm_layer,
                ),
                # pw-linear
                nn.Conv2d(hidden_dim, oup, 1, 1, 0, bias=False),
                norm_layer(oup),
            ]
        )
        self.conv = nn.Sequential(*layers)

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


class MobileNetV2(nn.Module):
    def __init__(
        self,
        embed_dim=1028,
        width_mult=1.0,
        inverted_residual_setting=None,
        round_nearest=8,
        block=None,
        norm_layer=None,
    ):
        """
        MobileNet V2 main class

        Args:
            embed_dim (int): Number of channels in the final output.
            width_mult (float): Width multiplier - adjusts number of channels in each layer by this amount
            inverted_residual_setting: Network structure
            round_nearest (int): Round the number of channels in each layer to be a multiple of this number
            Set to 1 to turn off rounding
            block: Module specifying inverted residual building block for mobilenet
            norm_layer: Module specifying the normalization layer to use

        """
        super(MobileNetV2, self).__init__()

        if block is None:
            block = InvertedResidual

        if norm_layer is None:
            norm_layer = nn.BatchNorm2d

        input_channel = 32
        last_channel = embed_dim / width_mult

        if inverted_residual_setting is None:
            inverted_residual_setting = [
                # t, c, n, s
                [1, 16, 1, 1],
                [6, 24, 2, 2],
                [6, 32, 3, 2],
                [6, 64, 4, 2],
                [6, 96, 3, 1],
                [6, 160, 3, 2],
                [6, 320, 1, 1],
            ]

        # only check the first element, assuming user knows t,c,n,s are required
        if (
            len(inverted_residual_setting) == 0
            or len(inverted_residual_setting[0]) != 4
        ):
            raise ValueError(
                "inverted_residual_setting should be non-empty "
                "or a 4-element list, got {}".format(inverted_residual_setting)
            )

        # building first layer
        input_channel = _make_divisible(input_channel * width_mult, round_nearest)
        self.last_channel = _make_divisible(
            last_channel * max(1.0, width_mult), round_nearest
        )
        features = [ConvBNReLU(3, input_channel, stride=2, norm_layer=norm_layer)]
        # building inverted residual blocks
        for t, c, n, s in inverted_residual_setting:
            output_channel = _make_divisible(c * width_mult, round_nearest)
            for i in range(n):
                stride = s if i == 0 else 1
                features.append(
                    block(
                        input_channel,
                        output_channel,
                        stride,
                        expand_ratio=t,
                        norm_layer=norm_layer,
                    )
                )
                input_channel = output_channel
        # building last several layers
        features.append(
            ConvBNReLU(
                input_channel, self.last_channel, kernel_size=1, norm_layer=norm_layer
            )
        )
        # make it nn.Sequential
        self.features = nn.Sequential(*features)

        # weight initialization
        for m in self.modules():
            if isinstance(m, nn.Conv2d):
                nn.init.kaiming_normal_(m.weight, mode="fan_out")
                if m.bias is not None:
                    nn.init.zeros_(m.bias)
            elif isinstance(m, (nn.BatchNorm2d, nn.GroupNorm)):
                nn.init.ones_(m.weight)
                nn.init.zeros_(m.bias)
            elif isinstance(m, nn.Linear):
                nn.init.normal_(m.weight, 0, 0.01)
                nn.init.zeros_(m.bias)

    def _forward_impl(self, x):
        # This exists since TorchScript doesn't support inheritance, so the superclass method
        # (this one) needs to have a name other than `forward` that can be accessed in a subclass
        return self.features(x)
        # return the features directly, no classifier or pooling

    def forward(self, x):
        return self._forward_impl(x)