This repository has been archived by the owner on Jul 2, 2023. It is now read-only.
-
-
Notifications
You must be signed in to change notification settings - Fork 482
/
Copy pathfcn32s.py
179 lines (151 loc) · 6.19 KB
/
fcn32s.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
import os.path as osp
import fcn
import numpy as np
import torch
import torch.nn as nn
# https://github.com/shelhamer/fcn.berkeleyvision.org/blob/master/surgery.py
def get_upsampling_weight(in_channels, out_channels, kernel_size):
"""Make a 2D bilinear kernel suitable for upsampling"""
factor = (kernel_size + 1) // 2
if kernel_size % 2 == 1:
center = factor - 1
else:
center = factor - 0.5
og = np.ogrid[:kernel_size, :kernel_size]
filt = (1 - abs(og[0] - center) / factor) * \
(1 - abs(og[1] - center) / factor)
weight = np.zeros((in_channels, out_channels, kernel_size, kernel_size),
dtype=np.float64)
weight[range(in_channels), range(out_channels), :, :] = filt
return torch.from_numpy(weight).float()
class FCN32s(nn.Module):
pretrained_model = \
osp.expanduser('~/data/models/pytorch/fcn32s_from_caffe.pth')
@classmethod
def download(cls):
return fcn.data.cached_download(
url='https://drive.google.com/uc?id=11k2Q0bvRQgQbT6-jYWeh6nmAsWlSCY3f', # NOQA
path=cls.pretrained_model,
md5='d3eb467a80e7da0468a20dfcbc13e6c8',
)
def __init__(self, n_class=21):
super(FCN32s, self).__init__()
# conv1
self.conv1_1 = nn.Conv2d(3, 64, 3, padding=100)
self.relu1_1 = nn.ReLU(inplace=True)
self.conv1_2 = nn.Conv2d(64, 64, 3, padding=1)
self.relu1_2 = nn.ReLU(inplace=True)
self.pool1 = nn.MaxPool2d(2, stride=2, ceil_mode=True) # 1/2
# conv2
self.conv2_1 = nn.Conv2d(64, 128, 3, padding=1)
self.relu2_1 = nn.ReLU(inplace=True)
self.conv2_2 = nn.Conv2d(128, 128, 3, padding=1)
self.relu2_2 = nn.ReLU(inplace=True)
self.pool2 = nn.MaxPool2d(2, stride=2, ceil_mode=True) # 1/4
# conv3
self.conv3_1 = nn.Conv2d(128, 256, 3, padding=1)
self.relu3_1 = nn.ReLU(inplace=True)
self.conv3_2 = nn.Conv2d(256, 256, 3, padding=1)
self.relu3_2 = nn.ReLU(inplace=True)
self.conv3_3 = nn.Conv2d(256, 256, 3, padding=1)
self.relu3_3 = nn.ReLU(inplace=True)
self.pool3 = nn.MaxPool2d(2, stride=2, ceil_mode=True) # 1/8
# conv4
self.conv4_1 = nn.Conv2d(256, 512, 3, padding=1)
self.relu4_1 = nn.ReLU(inplace=True)
self.conv4_2 = nn.Conv2d(512, 512, 3, padding=1)
self.relu4_2 = nn.ReLU(inplace=True)
self.conv4_3 = nn.Conv2d(512, 512, 3, padding=1)
self.relu4_3 = nn.ReLU(inplace=True)
self.pool4 = nn.MaxPool2d(2, stride=2, ceil_mode=True) # 1/16
# conv5
self.conv5_1 = nn.Conv2d(512, 512, 3, padding=1)
self.relu5_1 = nn.ReLU(inplace=True)
self.conv5_2 = nn.Conv2d(512, 512, 3, padding=1)
self.relu5_2 = nn.ReLU(inplace=True)
self.conv5_3 = nn.Conv2d(512, 512, 3, padding=1)
self.relu5_3 = nn.ReLU(inplace=True)
self.pool5 = nn.MaxPool2d(2, stride=2, ceil_mode=True) # 1/32
# fc6
self.fc6 = nn.Conv2d(512, 4096, 7)
self.relu6 = nn.ReLU(inplace=True)
self.drop6 = nn.Dropout2d()
# fc7
self.fc7 = nn.Conv2d(4096, 4096, 1)
self.relu7 = nn.ReLU(inplace=True)
self.drop7 = nn.Dropout2d()
self.score_fr = nn.Conv2d(4096, n_class, 1)
self.upscore = nn.ConvTranspose2d(n_class, n_class, 64, stride=32,
bias=False)
self._initialize_weights()
def _initialize_weights(self):
for m in self.modules():
if isinstance(m, nn.Conv2d):
m.weight.data.zero_()
if m.bias is not None:
m.bias.data.zero_()
if isinstance(m, nn.ConvTranspose2d):
assert m.kernel_size[0] == m.kernel_size[1]
initial_weight = get_upsampling_weight(
m.in_channels, m.out_channels, m.kernel_size[0])
m.weight.data.copy_(initial_weight)
def forward(self, x):
h = x
h = self.relu1_1(self.conv1_1(h))
h = self.relu1_2(self.conv1_2(h))
h = self.pool1(h)
h = self.relu2_1(self.conv2_1(h))
h = self.relu2_2(self.conv2_2(h))
h = self.pool2(h)
h = self.relu3_1(self.conv3_1(h))
h = self.relu3_2(self.conv3_2(h))
h = self.relu3_3(self.conv3_3(h))
h = self.pool3(h)
h = self.relu4_1(self.conv4_1(h))
h = self.relu4_2(self.conv4_2(h))
h = self.relu4_3(self.conv4_3(h))
h = self.pool4(h)
h = self.relu5_1(self.conv5_1(h))
h = self.relu5_2(self.conv5_2(h))
h = self.relu5_3(self.conv5_3(h))
h = self.pool5(h)
h = self.relu6(self.fc6(h))
h = self.drop6(h)
h = self.relu7(self.fc7(h))
h = self.drop7(h)
h = self.score_fr(h)
h = self.upscore(h)
h = h[:, :, 19:19 + x.size()[2], 19:19 + x.size()[3]].contiguous()
return h
def copy_params_from_vgg16(self, vgg16):
features = [
self.conv1_1, self.relu1_1,
self.conv1_2, self.relu1_2,
self.pool1,
self.conv2_1, self.relu2_1,
self.conv2_2, self.relu2_2,
self.pool2,
self.conv3_1, self.relu3_1,
self.conv3_2, self.relu3_2,
self.conv3_3, self.relu3_3,
self.pool3,
self.conv4_1, self.relu4_1,
self.conv4_2, self.relu4_2,
self.conv4_3, self.relu4_3,
self.pool4,
self.conv5_1, self.relu5_1,
self.conv5_2, self.relu5_2,
self.conv5_3, self.relu5_3,
self.pool5,
]
for l1, l2 in zip(vgg16.features, features):
if isinstance(l1, nn.Conv2d) and isinstance(l2, nn.Conv2d):
assert l1.weight.size() == l2.weight.size()
assert l1.bias.size() == l2.bias.size()
l2.weight.data = l1.weight.data
l2.bias.data = l1.bias.data
for i, name in zip([0, 3], ['fc6', 'fc7']):
l1 = vgg16.classifier[i]
l2 = getattr(self, name)
l2.weight.data = l1.weight.data.view(l2.weight.size())
l2.bias.data = l1.bias.data.view(l2.bias.size())