-
Notifications
You must be signed in to change notification settings - Fork 13
/
DeepLab_v3_plus.py
187 lines (150 loc) · 6.81 KB
/
DeepLab_v3_plus.py
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
import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.utils.model_zoo as model_zoo
import torchvision.models as models
import numpy as np
import math
model_url = 'https://download.pytorch.org/models/resnet101-5d3b4d8f.pth'
class Atrous_Bottleneck(nn.Module):
expansion = 4
def __init__(self, inplanes, planes, stride=1, rate=1, downsample=None):
super(Atrous_Bottleneck, self).__init__()
self.conv1 = nn.Conv2d(inplanes, planes, kernel_size=1, bias=False)
self.bn1 = nn.BatchNorm2d(planes)
self.conv2 = nn.Conv2d(planes, planes, kernel_size=3, stride=stride,
dilation=rate, padding=rate, bias=False)
self.bn2 = nn.BatchNorm2d(planes)
self.conv3 = nn.Conv2d(planes, planes * 4, kernel_size=1, bias=False)
self.bn3 = nn.BatchNorm2d(planes * 4)
self.relu = nn.ReLU(inplace=True)
self.downsample = downsample
self.stride = stride
def forward(self, x):
residual = x
out = self.conv1(x)
out = self.bn1(out)
out = self.relu(out)
out = self.conv2(out)
out = self.bn2(out)
out = self.relu(out)
out = self.conv3(out)
out = self.bn3(out)
if self.downsample is not None:
residual = self.downsample(x)
out += residual
out = self.relu(out)
return out
class Atrous_ResNet_features(nn.Module):
def __init__(self, block, layers, pretrained=False):
super(Atrous_ResNet_features, self).__init__()
self.inplanes = 64
self.conv1 = nn.Conv2d(3, 64, kernel_size=7, stride=2, padding=3,
bias=False)
self.bn1 = nn.BatchNorm2d(64)
self.relu = nn.ReLU(inplace=True)
self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
self.layer1 = self._make_layer(block, 64, layers[0], stride=1, rate=1)
self.layer2 = self._make_layer(block, 128, layers[1], stride=2, rate=1)
self.layer3 = self._make_layer(block, 256, layers[2], stride=2, rate=1)
self.layer4 = self._make_MG_unit(block, 512, stride=1, rate=2)
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_()
if pretrained:
print('load the pre-trained model.')
resnet = models.resnet101(pretrained)
self.conv1 = resnet.conv1
self.bn1 = resnet.bn1
self.layer1 = resnet.layer1
self.layer2 = resnet.layer2
def _make_layer(self, block, planes, blocks, stride=1, rate=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, rate, downsample))
self.inplanes = planes * block.expansion
for i in range(1, blocks):
layers.append(block(self.inplanes, planes))
return nn.Sequential(*layers)
def _make_MG_unit(self, block, planes, blocks=[1,2,4], stride=1, rate=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, rate=blocks[0]*rate, downsample=downsample))
self.inplanes = planes * block.expansion
for i in range(1, len(blocks)):
layers.append(block(self.inplanes, planes, stride=1, rate=blocks[i]*rate))
return nn.Sequential(*layers)
def forward(self, x):
x = self.conv1(x)
x = self.bn1(x)
x = self.relu(x)
x = self.maxpool(x)
x = self.layer1(x)
conv2 = x
x = self.layer2(x)
x = self.layer3(x)
x = self.layer4(x)
return x, conv2
class Atrous_module(nn.Module):
def __init__(self, inplanes, planes, rate):
super(Atrous_module, self).__init__()
self.atrous_convolution = nn.Conv2d(inplanes, planes, kernel_size=3,
stride=1, padding=rate, dilation=rate)
self.batch_norm = nn.BatchNorm2d(planes)
def forward(self, x):
x = self.atrous_convolution(x)
x = self.batch_norm(x)
return x
class DeepLabv3_plus(nn.Module):
def __init__(self, num_classes, small=True, pretrained=False):
super(DeepLabv3_plus, self).__init__()
block = Atrous_Bottleneck
self.resnet_features = Atrous_ResNet_features(block, [3, 4, 23], pretrained)
rates = [1, 6, 12, 18]
self.aspp1 = Atrous_module(2048 , 256, rate=rates[0])
self.aspp2 = Atrous_module(2048 , 256, rate=rates[1])
self.aspp3 = Atrous_module(2048 , 256, rate=rates[2])
self.aspp4 = Atrous_module(2048 , 256, rate=rates[3])
self.image_pool = nn.Sequential(nn.AdaptiveMaxPool2d(1),
nn.Conv2d(2048, 256, kernel_size=1))
self.fc1 = nn.Sequential(nn.Conv2d(1280, 256, kernel_size=1),
nn.BatchNorm2d(256))
self.reduce_conv2 = nn.Sequential(nn.Conv2d(256, 48, kernel_size=1),
nn.BatchNorm2d(48))
self.last_conv = nn.Sequential(nn.Conv2d(304, 256, kernel_size=3, stride=1, padding=1),
nn.BatchNorm2d(256),
nn.Conv2d(256, 256, kernel_size=3, stride=1, padding=1),
nn.BatchNorm2d(256),
nn.Conv2d(256, num_classes, kernel_size=1, stride=1))
def forward(self, x):
x, conv2 = self.resnet_features(x)
x1 = self.aspp1(x)
x2 = self.aspp2(x)
x3 = self.aspp3(x)
x4 = self.aspp4(x)
x5 = self.image_pool(x)
x5 = F.upsample(x5, size=x4.size()[2:], mode='nearest')
x = torch.cat((x1, x2, x3, x4, x5), dim=1)
x = self.fc1(x)
x = F.upsample(x, scale_factor=(4,4), mode='bilinear')
low_lebel_features = self.reduce_conv2(conv2)
x = torch.cat((x, low_lebel_features), dim=1)
x = self.last_conv(x)
x = F.upsample(x, scale_factor=(4, 4), mode='bilinear')
return x