File size: 5,215 Bytes
475ac6e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
import torch
import torch.nn as nn
import math
from collections import OrderedDict

################## AlexNet ##################
def bn_relu(inplanes):
    return nn.Sequential(nn.BatchNorm2d(inplanes), nn.ReLU(inplace=True))

def bn_relu_pool(inplanes, kernel_size=3, stride=2):
    return nn.Sequential(nn.BatchNorm2d(inplanes), nn.ReLU(inplace=True), nn.MaxPool2d(kernel_size=kernel_size, stride=stride))

class AlexNet(nn.Module):
    def __init__(self, num_classes=1):
        super(AlexNet, self).__init__()
        self.conv1 = nn.Conv2d(3, 96, kernel_size=11, stride=4, bias=False)
        self.relu_pool1 = bn_relu_pool(inplanes=96)
        self.conv2 = nn.Conv2d(96, 192, kernel_size=5, padding=2, groups=2, bias=False)
        self.relu_pool2 = bn_relu_pool(inplanes=192)
        self.conv3 = nn.Conv2d(192, 384, kernel_size=3, padding=1, groups=2, bias=False)
        self.relu3 = bn_relu(inplanes=384)
        self.conv4 = nn.Conv2d(384, 384, kernel_size=3, padding=1, groups=2, bias=False)
        self.relu4 = bn_relu(inplanes=384)
        self.conv5 = nn.Conv2d(384, 256, kernel_size=3, padding=1, groups=2, bias=False)
        self.relu_pool5 = bn_relu_pool(inplanes=256)
        # classifier
        self.conv6 = nn.Conv2d(256, 256, kernel_size=5, groups=2, bias=False)
        self.relu6 = bn_relu(inplanes=256)
        self.conv7 = nn.Conv2d(256, num_classes, kernel_size=1, bias=False)

    def forward(self, x):
        x = self.conv1(x)
        x = self.relu_pool1(x)
        x = self.conv2(x)
        x = self.relu_pool2(x)
        x = self.conv3(x)
        x = self.relu3(x)
        x = self.conv4(x)
        x = self.relu4(x)
        x = self.conv5(x)
        x = self.relu_pool5(x)
        x = self.conv6(x)
        x = self.relu6(x)
        x = self.conv7(x)
        x = x.view(x.size(0), -1)
        return x



################## ResNet ##################
def conv3x3(in_planes, out_planes, stride=1):
    # 3x3 convolution with padding
    return nn.Conv2d(in_planes, out_planes, kernel_size=3, stride=stride, padding=1, bias=False)

class BasicBlock(nn.Module):
    expansion = 1
    def __init__(self, inplanes, planes, stride=1, downsample=None):
        super(BasicBlock, self).__init__()
        m = OrderedDict()
        m['conv1'] = conv3x3(inplanes, planes, stride)
        m['bn1'] = nn.BatchNorm2d(planes)
        m['relu1'] = nn.ReLU(inplace=True)
        m['conv2'] = conv3x3(planes, planes)
        m['bn2'] = nn.BatchNorm2d(planes)
        self.group1 = nn.Sequential(m)
        self.relu = nn.Sequential(nn.ReLU(inplace=True))
        self.downsample = downsample

    def forward(self, x):
        if self.downsample is not None:
            residual = self.downsample(x)
        else:
            residual = x
        out = self.group1(x) + residual
        out = self.relu(out)

        return out

class ResNet(nn.Module):
    def __init__(self, block, layers, num_classes=1000):
        self.inplanes = 64
        super(ResNet, self).__init__()

        m = OrderedDict()
        m['conv1'] = nn.Conv2d(3, 64, kernel_size=7, stride=2, padding=3, bias=False)
        m['bn1'] = nn.BatchNorm2d(64)
        m['relu1'] = nn.ReLU(inplace=True)
        m['maxpool'] = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
        self.group1= nn.Sequential(m)

        self.layer1 = self._make_layer(block, 64, layers[0])
        self.layer2 = self._make_layer(block, 128, layers[1], stride=2)
        self.layer3 = self._make_layer(block, 256, layers[2], stride=2)
        self.layer4 = self._make_layer(block, 512, layers[3], stride=2)

        self.avgpool = nn.Sequential(nn.AvgPool2d(7))
        self.group2 = nn.Sequential(
            OrderedDict([
                ('fullyconnected', nn.Linear(512 * block.expansion, num_classes))
            ])
        )

        for m in self.modules():
            if isinstance(m, nn.Conv2d):
                n = m.kernel_size[0] * m.kernel_size[1] * m.out_channels
                m.weight.data.normal_(0, math.sqrt(2. / n))
            elif isinstance(m, nn.BatchNorm2d):
                m.weight.data.fill_(1)
                m.bias.data.zero_()
            elif isinstance(m, nn.Linear):
                torch.nn.init.xavier_uniform_(m.weight.data)
                torch.nn.init.constant_(m.bias.data, 0)


    def _make_layer(self, block, planes, blocks, stride=1):
        downsample = None
        if stride != 1 or self.inplanes != planes * block.expansion:
            downsample = nn.Sequential(
                nn.Conv2d(self.inplanes, planes * block.expansion, kernel_size=1, stride=stride, bias=False),
                nn.BatchNorm2d(planes * block.expansion),
            )

        layers = []
        layers.append(block(self.inplanes, planes, stride, downsample))
        self.inplanes = planes * block.expansion
        for i in range(1, blocks):
            layers.append(block(self.inplanes, planes))

        return nn.Sequential(*layers)

    def forward(self, x):
        x = self.group1(x)
        x = self.layer1(x)
        x = self.layer2(x)
        x = self.layer3(x)
        x = self.layer4(x)
        x = self.avgpool(x)
        x = x.view(x.size(0), -1)
        x = self.group2(x)

        return x