-
Notifications
You must be signed in to change notification settings - Fork 1
/
resnet.py
executable file
·224 lines (180 loc) · 7.46 KB
/
resnet.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
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
221
222
223
224
import torch.nn as nn
import math
import torch
import torch.nn.functional as F
import torch.utils.model_zoo as model_zoo
from tqdm import tqdm
from utils import get_state_dict
from label_id_dict import label_to_category_id
from torch.autograd import Variable
from collections import defaultdict
model_urls = {
'resnet18': 'https://download.pytorch.org/models/resnet18-5c106cde.pth',
'resnet34': 'https://download.pytorch.org/models/resnet34-333f7ec4.pth',
'resnet50': 'https://download.pytorch.org/models/resnet50-19c8e357.pth',
'resnet101': 'https://download.pytorch.org/models/resnet101-5d3b4d8f.pth',
'resnet152': 'https://download.pytorch.org/models/resnet152-b121ed2d.pth',
}
def conv3x3(in_planes, out_planes, stride=1):
"3x3 convolution with padding"
return nn.Conv2d(in_planes, out_planes, kernel_size=3, stride=stride,
padding=1, bias=False)
class BasicBlock(nn.Module):
expansion = 1
def __init__(self, inplanes, planes, stride=1, downsample=None):
super(BasicBlock, self).__init__()
self.conv1 = conv3x3(inplanes, planes, stride)
self.bn1 = nn.BatchNorm2d(planes)
self.relu = nn.ReLU(inplace=True)
self.conv2 = conv3x3(planes, planes)
self.bn2 = nn.BatchNorm2d(planes)
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)
if self.downsample is not None:
residual = self.downsample(x)
out += residual
out = self.relu(out)
return out
class Bottleneck(nn.Module):
expansion = 4
def __init__(self, inplanes, planes, stride=1, downsample=None):
super(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,
padding=1, 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 ResNet(nn.Module):
def __init__(self, block, layers, num_classes=1000):
self.inplanes = 64
super(ResNet, self).__init__()
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])
self.layer2 = self._make_layer(block, 128, layers[1], stride=2)
self.layer3 = self._make_layer(block, 256, layers[2], stride=2)
self.layer4 = self._make_layer(block, 512, layers[3], stride=2)
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, stride, downsample))
self.inplanes = planes * block.expansion
for i in range(1, blocks):
layers.append(block(self.inplanes, planes))
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)
x = self.layer2(x)
x = self.layer3(x)
x = self.layer4(x)
x = F.adaptive_avg_pool2d(x, output_size=1)
x = x.view(x.size(0), -1)
x = self.fc(x)
return x
def load_pretrained_model(self, pretrained_model_file=None, skip=[]):
if pretrained_model_file:
pretrain_state_dict = get_state_dict(pretrained_model_file)
state_dict = self.state_dict()
keys = list(state_dict.keys())
for key in keys:
if any(s in key for s in skip):
continue
try:
state_dict[key] = pretrain_state_dict[key]
except KeyError:
print("KeyError: {} dosen't lie in pretrain state dict".format(key))
continue
else:
state_dict = model_zoo.load_url(model_urls[self.name])
self.load_state_dict(state_dict)
pass
def predict(self, data_loader, vote=False):
if not vote:
predicts = []
for data in tqdm(data_loader):
data = data.cuda() if self.use_cuda else data
data = Variable(data, volatile=True)
output = self.forward(data)
category_label = output.data.max(1)[1]
for i in range(len(category_label)):
predicts.append(label_to_category_id[category_label[i]])
else:
predicts = defaultdict(list)
for item_id, data in tqdm(data_loader):
data = data.cuda() if self.use_cuda else data
data = Variable(data, volatile=True)
output = self.forward(data)
category_label = output.data.max(1)[1]
for i in range(len(category_label)):
predicts[item_id[i]].append(label_to_category_id[category_label[i]])
return predicts
def save(self, file):
torch.save(self.state_dict(), file)
class ResNet18(ResNet):
def __init__(self, num_classes=1000):
super(ResNet18, self).__init__(BasicBlock, [2, 2, 2, 2], num_classes)
self.name = 'resnet18'
class ResNet34(ResNet):
def __init__(self, num_classes=1000):
super(ResNet34, self).__init__(BasicBlock, [3, 4, 6, 3], num_classes)
self.name = 'resnet34'
class ResNet50(ResNet):
def __init__(self, num_classes=1000):
super(ResNet50, self).__init__(Bottleneck, [3, 4, 6, 3], num_classes)
self.name = 'resnet50'
class ResNet101(ResNet):
def __init__(self, num_classes=1000):
super(ResNet101, self).__init__(Bottleneck, [3, 4, 23, 3], num_classes)
self.name = 'resnet101'
class ResNet152(ResNet):
def __init__(self, num_classes=1000):
super(ResNet152, self).__init__(Bottleneck, [3, 8, 36, 3], num_classes)
self.name = 'resnet152'