-
Notifications
You must be signed in to change notification settings - Fork 215
/
res2next.py
179 lines (153 loc) · 6.07 KB
/
res2next.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
from __future__ import division
import math
import torch.nn as nn
import torch.nn.functional as F
from torch.nn import init
import torch
import torch.utils.model_zoo as model_zoo
__all__ = ['res2next50']
model_urls = {
'res2next50': 'https://shanghuagao.oss-cn-beijing.aliyuncs.com/res2net/res2next50_4s-6ef7e7bf.pth',
}
class Bottle2neckX(nn.Module):
expansion = 4
def __init__(self, inplanes, planes, baseWidth, cardinality, stride=1, downsample=None, scale = 4, stype='normal'):
""" Constructor
Args:
inplanes: input channel dimensionality
planes: output channel dimensionality
baseWidth: base width.
cardinality: num of convolution groups.
stride: conv stride. Replaces pooling layer.
scale: number of scale.
type: 'normal': normal set. 'stage': frist blokc of a new stage.
"""
super(Bottle2neckX, self).__init__()
D = int(math.floor(planes * (baseWidth/64.0)))
C = cardinality
self.conv1 = nn.Conv2d(inplanes, D*C*scale, kernel_size=1, stride=1, padding=0, bias=False)
self.bn1 = nn.BatchNorm2d(D*C*scale)
if scale == 1:
self.nums = 1
else:
self.nums = scale -1
if stype == 'stage':
self.pool = nn.AvgPool2d(kernel_size=3, stride = stride, padding=1)
convs = []
bns = []
for i in range(self.nums):
convs.append(nn.Conv2d(D*C, D*C, kernel_size=3, stride = stride, padding=1, groups=C, bias=False))
bns.append(nn.BatchNorm2d(D*C))
self.convs = nn.ModuleList(convs)
self.bns = nn.ModuleList(bns)
self.conv3 = nn.Conv2d(D*C*scale, planes * 4, kernel_size=1, stride=1, padding=0, bias=False)
self.bn3 = nn.BatchNorm2d(planes * 4)
self.relu = nn.ReLU(inplace=True)
self.downsample = downsample
self.width = D*C
self.stype = stype
self.scale = scale
def forward(self, x):
residual = x
out = self.conv1(x)
out = self.bn1(out)
out = self.relu(out)
spx = torch.split(out, self.width, 1)
for i in range(self.nums):
if i==0 or self.stype=='stage':
sp = spx[i]
else:
sp = sp + spx[i]
sp = self.convs[i](sp)
sp = self.relu(self.bns[i](sp))
if i==0:
out = sp
else:
out = torch.cat((out, sp), 1)
if self.scale != 1 and self.stype=='normal':
out = torch.cat((out, spx[self.nums]),1)
elif self.scale != 1 and self.stype=='stage':
out = torch.cat((out, self.pool(spx[self.nums])),1)
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 Res2NeXt(nn.Module):
def __init__(self, block, baseWidth, cardinality, layers, num_classes, scale=4):
""" Constructor
Args:
baseWidth: baseWidth for ResNeXt.
cardinality: number of convolution groups.
layers: config of layers, e.g., [3, 4, 6, 3]
num_classes: number of classes
scale: scale in res2net
"""
super(Res2NeXt, self).__init__()
self.cardinality = cardinality
self.baseWidth = baseWidth
self.num_classes = num_classes
self.inplanes = 64
self.output_size = 64
self.scale = scale
self.conv1 = nn.Conv2d(3, 64, 7, 2, 3, bias=False)
self.bn1 = nn.BatchNorm2d(64)
self.relu = nn.ReLU(inplace=True)
self.maxpool1 = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
self.layer1 = self._make_layer(block, 64, layers[0])
self.layer2 = self._make_layer(block, 128, layers[1], 2)
self.layer3 = self._make_layer(block, 256, layers[2], 2)
self.layer4 = self._make_layer(block, 512, layers[3], 2)
self.avgpool = nn.AdaptiveAvgPool2d(1)
self.fc = 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_()
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, self.baseWidth, self.cardinality, stride, downsample, scale=self.scale, stype='stage'))
self.inplanes = planes * block.expansion
for i in range(1, blocks):
layers.append(block(self.inplanes, planes, self.baseWidth, self.cardinality, scale=self.scale))
return nn.Sequential(*layers)
def forward(self, x):
x = self.conv1(x)
x = self.bn1(x)
x = self.relu(x)
x = self.maxpool1(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.fc(x)
return x
def res2next50(pretrained=False, **kwargs):
""" Construct Res2NeXt-50.
The default scale is 4.
Args:
pretrained (bool): If True, returns a model pre-trained on ImageNet
"""
model = Res2NeXt(Bottle2neckX, layers = [3, 4, 6, 3], baseWidth = 4, cardinality=8, scale = 4, num_classes=1000)
if pretrained:
model.load_state_dict(model_zoo.load_url(model_urls['res2next50']))
return model
if __name__ == '__main__':
images = torch.rand(1, 3, 224, 224).cuda(0)
model = res2next50(pretrained=True)
model = model.cuda(0)
print(model(images).size())