File size: 5,730 Bytes
09481f3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
import torch
import torch.nn as nn
import torch.nn.functional as F
from torch.autograd import Variable
from collections import OrderedDict
from torch.nn import init
import math

import pdb

def conv_bn(inp, oup, stride):
    return nn.Sequential(
        nn.Conv2d(inp, oup, 3, stride, 1, bias=False),
        nn.BatchNorm2d(oup),
        nn.ReLU(inplace=True)
    )


def conv_1x1_bn(inp, oup):
    return nn.Sequential(
        nn.Conv2d(inp, oup, 1, 1, 0, bias=False),
        nn.BatchNorm2d(oup),
        nn.ReLU(inplace=True)
    )

def channel_shuffle(x, groups):
    batchsize, num_channels, height, width = x.data.size()

    channels_per_group = num_channels // groups
    
    # reshape
    x = x.view(batchsize, groups, 
        channels_per_group, height, width)

    x = torch.transpose(x, 1, 2).contiguous()

    # flatten
    x = x.view(batchsize, -1, height, width)

    return x
    
class InvertedResidual(nn.Module):
    def __init__(self, inp, oup, stride, benchmodel):
        super(InvertedResidual, self).__init__()
        self.benchmodel = benchmodel
        self.stride = stride
        assert stride in [1, 2]

        oup_inc = oup//2
        
        if self.benchmodel == 1:
            #assert inp == oup_inc
            self.banch2 = nn.Sequential(
                # pw
                nn.Conv2d(oup_inc, oup_inc, 1, 1, 0, bias=False),
                nn.BatchNorm2d(oup_inc),
                nn.ReLU(inplace=True),
                # dw
                nn.Conv2d(oup_inc, oup_inc, 3, stride, 1, groups=oup_inc, bias=False),
                nn.BatchNorm2d(oup_inc),
                # pw-linear
                nn.Conv2d(oup_inc, oup_inc, 1, 1, 0, bias=False),
                nn.BatchNorm2d(oup_inc),
                nn.ReLU(inplace=True),
            )                
        else:                  
            self.banch1 = nn.Sequential(
                # dw
                nn.Conv2d(inp, inp, 3, stride, 1, groups=inp, bias=False),
                nn.BatchNorm2d(inp),
                # pw-linear
                nn.Conv2d(inp, oup_inc, 1, 1, 0, bias=False),
                nn.BatchNorm2d(oup_inc),
                nn.ReLU(inplace=True),
            )        
    
            self.banch2 = nn.Sequential(
                # pw
                nn.Conv2d(inp, oup_inc, 1, 1, 0, bias=False),
                nn.BatchNorm2d(oup_inc),
                nn.ReLU(inplace=True),
                # dw
                nn.Conv2d(oup_inc, oup_inc, 3, stride, 1, groups=oup_inc, bias=False),
                nn.BatchNorm2d(oup_inc),
                # pw-linear
                nn.Conv2d(oup_inc, oup_inc, 1, 1, 0, bias=False),
                nn.BatchNorm2d(oup_inc),
                nn.ReLU(inplace=True),
            )
          
    @staticmethod
    def _concat(x, out):
        # concatenate along channel axis
        return torch.cat((x, out), 1)        

    def forward(self, x):
        if 1==self.benchmodel:
            x1 = x[:, :(x.shape[1]//2), :, :]
            x2 = x[:, (x.shape[1]//2):, :, :]
            out = self._concat(x1, self.banch2(x2))
        elif 2==self.benchmodel:
            out = self._concat(self.banch1(x), self.banch2(x))

        return channel_shuffle(out, 2)


class ShuffleNetV2(nn.Module):
    def __init__(self, n_class=1000, input_size=224, width_mult=2.):
        super(ShuffleNetV2, self).__init__()
        
        assert input_size % 32 == 0, "Input size needs to be divisible by 32"
        
        self.stage_repeats = [4, 8, 4]
        # index 0 is invalid and should never be called.
        # only used for indexing convenience.
        if width_mult == 0.5:
            self.stage_out_channels = [-1, 24,  48,  96, 192, 1024]
        elif width_mult == 1.0:
            self.stage_out_channels = [-1, 24, 116, 232, 464, 1024]
        elif width_mult == 1.5:
            self.stage_out_channels = [-1, 24, 176, 352, 704, 1024]
        elif width_mult == 2.0:
            self.stage_out_channels = [-1, 24, 244, 488, 976, 2048]
        else:
            raise ValueError(
                """Width multiplier should be in [0.5, 1.0, 1.5, 2.0]. Current value: {}""".format(width_mult))

        # building first layer
        input_channel = self.stage_out_channels[1]
        self.conv1 = conv_bn(3, input_channel, 2)    
        self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
        
        self.features = []
        # building inverted residual blocks
        for idxstage in range(len(self.stage_repeats)):
            numrepeat = self.stage_repeats[idxstage]
            output_channel = self.stage_out_channels[idxstage+2]
            for i in range(numrepeat):
                if i == 0:
                #inp, oup, stride, benchmodel):
                    self.features.append(InvertedResidual(input_channel, output_channel, 2, 2))
                else:
                    self.features.append(InvertedResidual(input_channel, output_channel, 1, 1))
                input_channel = output_channel
                
                
        # make it nn.Sequential
        self.features = nn.Sequential(*self.features)

        # building last several layers
        self.conv_last  = conv_1x1_bn(input_channel, self.stage_out_channels[-1])
        self.globalpool = nn.Sequential(nn.AvgPool2d(int(input_size/32)))              
        
        # building classifier
        self.classifier = nn.Sequential(nn.Linear(self.stage_out_channels[-1], n_class))

    def forward(self, x):
        x = self.conv1(x)
        x = self.maxpool(x)
        x = self.features(x)
        x = self.conv_last(x)
        x = self.globalpool(x)
        x = x.view(-1, self.stage_out_channels[-1])
        x = self.classifier(x)
        return x