This repository was archived by the owner on Sep 7, 2025. It is now read-only.
-
Notifications
You must be signed in to change notification settings - Fork 4
Expand file tree
/
Copy pathmodels.py
More file actions
132 lines (105 loc) · 5.76 KB
/
Copy pathmodels.py
File metadata and controls
132 lines (105 loc) · 5.76 KB
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
import torch
from torch import nn
from torchvision.models.vgg import VGG
from torchvision.models.vgg import vgg16
from torchvision.models.resnet import resnet50
import torch.nn.functional as F
class ResNet50(nn.Module):
def __init__(self):
super(ResNet50, self).__init__()
self.model = resnet50(pretrained=True)
self.model = torch.nn.Sequential(*list(self.model.children())[:-1])
self.disable_training()
def forward(self,x):
return self.model(x)
def disable_training(self):
for parameter in self.parameters():
parameter.requires_grad = False
'''Models based on https://github.com/pochih/FCN-pytorch'''
class FCN32s(nn.Module):
def __init__(self, n_class = 1):
super().__init__()
self.n_class = n_class
self.pretrained_net = VGGNet()
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=7, padding = 3)
def forward(self, x):
output = self.pretrained_net(x)
x5 = output['x5'] # size=(N, 512, x.H/32, x.W/32)
score = self.bn1(self.relu(self.deconv1(x5))) # size=(N, 512, x.H/16, x.W/16)
score = self.bn2(self.relu(self.deconv2(score))) # size=(N, 256, x.H/8, x.W/8)
score = self.bn3(self.relu(self.deconv3(score))) # size=(N, 128, x.H/4, x.W/4)
score = self.bn4(self.relu(self.deconv4(score))) # size=(N, 64, x.H/2, x.W/2)
score = self.bn5(self.relu(self.deconv5(score))) # size=(N, 32, x.H, x.W)
score = torch.sigmoid(self.classifier(score)) # size=(N, n_class, x.H/1, x.W/1)
return score # size=(N, n_class, x.H/1, x.W/1)
class FCN8s(nn.Module):
def __init__(self):
super().__init__()
self.n_class = 1
self.pretrained_net = VGGNet()
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, self.n_class, kernel_size=1)
def forward(self, x):
output = self.pretrained_net(x)
x5 = output['x5'] # size=(N, 512, x.H/32, x.W/32)
x4 = output['x4'] # size=(N, 512, x.H/16, x.W/16)
x3 = output['x3'] # size=(N, 256, x.H/8, x.W/8)
score = self.relu(self.deconv1(x5)) # size=(N, 512, x.H/16, x.W/16)
score = self.bn1(score + x4) # element-wise add, size=(N, 512, x.H/16, x.W/16)
score = self.relu(self.deconv2(score)) # size=(N, 256, x.H/8, x.W/8)
score = self.bn2(score + x3) # element-wise add, size=(N, 256, x.H/8, x.W/8)
score = self.bn3(self.relu(self.deconv3(score))) # size=(N, 128, x.H/4, x.W/4)
score = self.bn4(self.relu(self.deconv4(score))) # size=(N, 64, x.H/2, x.W/2)
score = self.bn5(self.relu(self.deconv5(score))) # size=(N, 32, x.H, x.W)
score = torch.sigmoid(self.classifier(score)) # size=(N, n_class, x.H/1, x.W/1)
return score # size=(N, n_class, x.H/1, x.W/1)
class VGGNet(VGG):
def __init__(self):
super().__init__(self.make_layers())
self.ranges = ((0, 5), (5, 10), (10, 17), (17, 24), (24, 31))
self.load_state_dict(vgg16(pretrained=True).state_dict())
del self.classifier
def forward(self, x):
output = {}
# get the output of each maxpooling layer (5 maxpool in VGG net)
for idx in range(len(self.ranges)):
for layer in range(self.ranges[idx][0], self.ranges[idx][1]):
x = self.features[layer](x)
output["x%d"%(idx+1)] = x
return output
def make_layers(self, batch_norm=False):
cfg = [64, 64, 'M', 128, 128, 'M', 256, 256, 256, 'M', 512, 512, 512, 'M', 512, 512, 512, 'M']
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)