FCN-32/16/8/1s(2014)

注.Backbone: VGG

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
import torch
import torch.nn as nn
from torchvision import models
from torchvision.models.vgg import VGG


class FCN32s(nn.Module):

    def __init__(self, pretrained_net, n_class=1):
        super().__init__()
        self.n_class = n_class
        self.pretrained_net = pretrained_net
        self.relu    = nn.ReLU(inplace=True)
        self.deconv1 = nn.ConvTranspose2d(512, 512, kernel_size=3, stride=2, padding=1, dilation=1, output_padding=1)
        self.bn1     = nn.BatchNorm2d(512)
        self.deconv2 = nn.ConvTranspose2d(512, 256, kernel_size=3, stride=2, padding=1, dilation=1, output_padding=1)
        self.bn2     = nn.BatchNorm2d(256)
        self.deconv3 = nn.ConvTranspose2d(256, 128, kernel_size=3, stride=2, padding=1, dilation=1, output_padding=1)
        self.bn3     = nn.BatchNorm2d(128)
        self.deconv4 = nn.ConvTranspose2d(128, 64, kernel_size=3, stride=2, padding=1, dilation=1, output_padding=1)
        self.bn4     = nn.BatchNorm2d(64)
        self.deconv5 = nn.ConvTranspose2d(64, 32, kernel_size=3, stride=2, padding=1, dilation=1, output_padding=1)
        self.bn5     = nn.BatchNorm2d(32)
        self.classifier = nn.Conv2d(32, n_class, kernel_size=1)

    def forward(self, x):
        output = self.pretrained_net(x)
        x5 = output['x5']

        score = self.bn1(self.relu(self.deconv1(x5)))     
        score = self.bn2(self.relu(self.deconv2(score)))  
        score = self.bn3(self.relu(self.deconv3(score)))  
        score = self.bn4(self.relu(self.deconv4(score)))  
        score = self.bn5(self.relu(self.deconv5(score)))  
        score = self.classifier(score)                    

        score = nn.Sigmoid()(score)
        return score 


class FCN16s(nn.Module):

    def __init__(self, pretrained_net, n_class=1):
        super().__init__()
        self.n_class = n_class
        self.pretrained_net = pretrained_net
        self.relu    = nn.ReLU(inplace=True)
        self.deconv1 = nn.ConvTranspose2d(512, 512, kernel_size=3, stride=2, padding=1, dilation=1, output_padding=1)
        self.bn1     = nn.BatchNorm2d(512)
        self.deconv2 = nn.ConvTranspose2d(512, 256, kernel_size=3, stride=2, padding=1, dilation=1, output_padding=1)
        self.bn2     = nn.BatchNorm2d(256)
        self.deconv3 = nn.ConvTranspose2d(256, 128, kernel_size=3, stride=2, padding=1, dilation=1, output_padding=1)
        self.bn3     = nn.BatchNorm2d(128)
        self.deconv4 = nn.ConvTranspose2d(128, 64, kernel_size=3, stride=2, padding=1, dilation=1, output_padding=1)
        self.bn4     = nn.BatchNorm2d(64)
        self.deconv5 = nn.ConvTranspose2d(64, 32, kernel_size=3, stride=2, padding=1, dilation=1, output_padding=1)
        self.bn5     = nn.BatchNorm2d(32)
        self.classifier = nn.Conv2d(32, n_class, kernel_size=1)

    def forward(self, x):
        output = self.pretrained_net(x)
        x5 = output['x5']  
        x4 = output['x4']  

        score = self.relu(self.deconv1(x5))               
        score = self.bn1(score + x4)                      
        score = self.bn2(self.relu(self.deconv2(score)))  
        score = self.bn3(self.relu(self.deconv3(score)))  
        score = self.bn4(self.relu(self.deconv4(score)))  
        score = self.bn5(self.relu(self.deconv5(score)))  
        score = self.classifier(score)                   
        
        score = nn.Sigmoid()(score)
        return score  


class FCN8s(nn.Module):

    def __init__(self, pretrained_net, n_class=1):
        super().__init__()
        self.n_class = n_class
        self.pretrained_net = pretrained_net
        self.relu    = nn.ReLU(inplace=True)
        self.deconv1 = nn.ConvTranspose2d(512, 512, kernel_size=3, stride=2, padding=1, dilation=1, output_padding=1)
        self.bn1     = nn.BatchNorm2d(512)
        self.deconv2 = nn.ConvTranspose2d(512, 256, kernel_size=3, stride=2, padding=1, dilation=1, output_padding=1)
        self.bn2     = nn.BatchNorm2d(256)
        self.deconv3 = nn.ConvTranspose2d(256, 128, kernel_size=3, stride=2, padding=1, dilation=1, output_padding=1)
        self.bn3     = nn.BatchNorm2d(128)
        self.deconv4 = nn.ConvTranspose2d(128, 64, kernel_size=3, stride=2, padding=1, dilation=1, output_padding=1)
        self.bn4     = nn.BatchNorm2d(64)
        self.deconv5 = nn.ConvTranspose2d(64, 32, kernel_size=3, stride=2, padding=1, dilation=1, output_padding=1)
        self.bn5     = nn.BatchNorm2d(32)
        self.classifier = nn.Conv2d(32, n_class, kernel_size=1)

    def forward(self, x):
        output = self.pretrained_net(x)
        x5 = output['x5']  
        x4 = output['x4']  
        x3 = output['x3']  

        score = self.relu(self.deconv1(x5))              
        score = self.bn1(score + x4)                      
        score = self.relu(self.deconv2(score))            
        score = self.bn2(score + x3)                      
        score = self.bn3(self.relu(self.deconv3(score)))  
        score = self.bn4(self.relu(self.deconv4(score)))  
        score = self.bn5(self.relu(self.deconv5(score)))  
        score = self.classifier(score)                    

        score = nn.Sigmoid()(score)
        return score  


class FCNs(nn.Module):

    def __init__(self, pretrained_net, n_class=1):
        super().__init__()
        self.n_class = n_class
        self.pretrained_net = pretrained_net
        self.relu    = nn.ReLU(inplace=True)
        self.deconv1 = nn.ConvTranspose2d(512, 512, kernel_size=3, stride=2, padding=1, dilation=1, output_padding=1)
        self.bn1     = nn.BatchNorm2d(512)
        self.deconv2 = nn.ConvTranspose2d(512, 256, kernel_size=3, stride=2, padding=1, dilation=1, output_padding=1)
        self.bn2     = nn.BatchNorm2d(256)
        self.deconv3 = nn.ConvTranspose2d(256, 128, kernel_size=3, stride=2, padding=1, dilation=1, output_padding=1)
        self.bn3     = nn.BatchNorm2d(128)
        self.deconv4 = nn.ConvTranspose2d(128, 64, kernel_size=3, stride=2, padding=1, dilation=1, output_padding=1)
        self.bn4     = nn.BatchNorm2d(64)
        self.deconv5 = nn.ConvTranspose2d(64, 32, kernel_size=3, stride=2, padding=1, dilation=1, output_padding=1)
        self.bn5     = nn.BatchNorm2d(32)
        self.classifier = nn.Conv2d(32, n_class, kernel_size=1) 
        # classifier is 1x1 conv, to reduce channels from 32 to n_class

    def forward(self, x):
        output = self.pretrained_net(x)
        x5 = output['x5']  
        x4 = output['x4']  
        x3 = output['x3']  
        x2 = output['x2']  
        x1 = output['x1']  

        score = self.bn1(self.relu(self.deconv1(x5)))     
        score = score + x4                                
        score = self.bn2(self.relu(self.deconv2(score)))  
        score = score + x3                                
        score = self.bn3(self.relu(self.deconv3(score)))  
        score = score + x2                                
        score = self.bn4(self.relu(self.deconv4(score)))  
        score = score + x1                                
        score = self.bn5(self.relu(self.deconv5(score)))  
        score = self.classifier(score)                    

        score = nn.Sigmoid()(score)
        return score  


class VGGNet(VGG):

    def __init__(self, pretrained=True, model='vgg16', requires_grad=True, remove_fc=True, show_params=False):
        super().__init__(make_layers(cfg[model]))
        self.ranges = ranges[model]

        if pretrained:
            exec("self.load_state_dict(models.%s(pretrained=True).state_dict())" % model)

        if not requires_grad:
            for param in super().parameters():
                param.requires_grad = False

        # delete redundant fully-connected layers
        if remove_fc:  
            del self.classifier

        if show_params:
            for name, param in self.named_parameters():
                print(name, param.size())

    def forward(self, x):
        output = {}
        # get the output of each maxpooling layer (5 maxpool in VGG net)
        for idx, (begin, end) in enumerate(self.ranges):
        #self.ranges = ((0, 5), (5, 10), (10, 17), (17, 24), (24, 31)) (vgg16 examples)
            for layer in range(begin, end):
                x = self.features[layer](x)
            output["x%d"%(idx+1)] = x

        return output


ranges = {
    'vgg11': ((0, 3), (3, 6),  (6, 11),  (11, 16), (16, 21)),
    'vgg13': ((0, 5), (5, 10), (10, 15), (15, 20), (20, 25)),
    'vgg16': ((0, 5), (5, 10), (10, 17), (17, 24), (24, 31)),
    'vgg19': ((0, 5), (5, 10), (10, 19), (19, 28), (28, 37))
}

# Vgg-Net config 
cfg = {
    'vgg11': [64, 'M', 128, 'M', 256, 256, 'M', 512, 512, 'M', 512, 512, 'M'],
    'vgg13': [64, 64, 'M', 128, 128, 'M', 256, 256, 'M', 512, 512, 'M', 512, 512, 'M'],
    'vgg16': [64, 64, 'M', 128, 128, 'M', 256, 256, 256, 'M', 512, 512, 512, 'M', 512, 512, 512, 'M'],
    'vgg19': [64, 64, 'M', 128, 128, 'M', 256, 256, 256, 256, 'M', 512, 512, 512, 512, 'M', 512, 512, 512, 512, 'M'],
}

# make layers using Vgg-Net config(cfg)
def make_layers(cfg, batch_norm=False):
    layers = []
    in_channels = 3
    for v in cfg:
        if v == 'M':
            layers += [nn.MaxPool2d(kernel_size=2, stride=2)]
        else:
            conv2d = nn.Conv2d(in_channels, v, kernel_size=3, padding=1)
            if batch_norm:
                layers += [conv2d, nn.BatchNorm2d(v), nn.ReLU(inplace=True)]
            else:
                layers += [conv2d, nn.ReLU(inplace=True)]
            in_channels = v
    return nn.Sequential(*layers)


UNet(2015)

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
import torch.nn as nn
import torch
 
class DoubleConv(nn.Module):

    def __init__(self, in_channels, out_channels):
        super(DoubleConv, self).__init__()
        self.conv = nn.Sequential(
                nn.Conv2d(in_channels, out_channels, kernel_size=3, padding=1), 
                nn.BatchNorm2d(out_channels),
                nn.ReLU(inplace = True),
                nn.Conv2d(out_channels, out_channels, kernel_size=3, padding=1),
                nn.BatchNorm2d(out_channels),
                nn.ReLU(inplace = True)  
            )

    def forward(self, x):
        return self.conv(x)
 
 
class UNet(nn.Module):

    def __init__(self, in_channels=3, out_channels=1):
        super(UNet,self).__init__()
        # Conv
        self.conv1 = DoubleConv(in_channels, 64)
        self.pool1 = nn.MaxPool2d(2) 

        self.conv2 = DoubleConv(64, 128)
        self.pool2 = nn.MaxPool2d(2)

        self.conv3 = DoubleConv(128, 256)
        self.pool3 = nn.MaxPool2d(2)

        self.conv4 = DoubleConv(256, 512)
        self.pool4 = nn.MaxPool2d(2)

        self.conv5 = DoubleConv(512, 1024)

        # DeConv
        self.up_conv6 = nn.ConvTranspose2d(1024, 512, 2, stride=2)
        self.conv6 = DoubleConv(1024, 512)

        self.up_conv7 = nn.ConvTranspose2d(512, 256, 2, stride=2)
        self.conv7 = DoubleConv(512, 256)

        self.up_conv8 = nn.ConvTranspose2d(256, 128, 2, stride=2)
        self.conv8 = DoubleConv(256, 128)

        self.up_conv9 = nn.ConvTranspose2d(128, 64, 2, stride=2)
        self.conv9 = DoubleConv(128, 64)
        
        self.conv10 = nn.Conv2d(64, out_channels, 1)
        
    def forward(self,x):
        conv_out_1 = self.conv1(x)
        pool_out_1 = self.pool1(conv_out_1)
        conv_out_2 = self.conv2(pool_out_1)
        pool_out_2 = self.pool2(conv_out_2)
        conv_out_3 = self.conv3(pool_out_2)
        pool_out_3 = self.pool3(conv_out_3)
        conv_out_4 = self.conv4(pool_out_3)
        pool_out_4 = self.pool4(conv_out_4)
        conv_out_5 = self.conv5(pool_out_4)
        up_conv_out_6 = self.up_conv6(conv_out_5)
        concate_6 = torch.cat([up_conv_out_6, conv_out_4], dim=1) 

        conv_out_6 = self.conv6(concate_6)
        up_conv_out_7 = self.up_conv7(conv_out_6)
        concate_7 = torch.cat([up_conv_out_7, conv_out_3], dim=1)

        conv_out_7 = self.conv7(concate_7)
        up_conv_out_8 = self.up_conv8(conv_out_7)
        concate_8 = torch.cat([up_conv_out_8, conv_out_2], dim=1)

        conv_out_8 = self.conv8(concate_8)
        up_conv_out_9 = self.up_conv9(conv_out_8)
        concate_9 = torch.cat([up_conv_out_9, conv_out_1], dim=1)

        conv_out_9 = self.conv9(concate_9)
        conv_out_10 = self.conv10(conv_out_9)
        out = nn.Sigmoid()(conv_out_10) 
        return out