forked from zhangyongshun/BagofTricks-LT
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy patholtr_resnet.py
executable file
·199 lines (160 loc) · 6.98 KB
/
oltr_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
import math
import torch.nn as nn
import torch.nn.functional as F
import torch
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, use_modulatedatt=False, use_fc=False, dropout=None):
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.avgpool = nn.AvgPool2d(7, stride=1)
self.use_fc = use_fc
self.use_dropout = True if dropout else False
if self.use_fc:
print('Using fc.')
self.fc_add = nn.Linear(512 * block.expansion, 512)
if self.use_dropout:
print('Using dropout.')
self.dropout = nn.Dropout(p=dropout)
self.use_modulatedatt = use_modulatedatt
if self.use_modulatedatt:
print('Using self attention.')
self.modulatedatt = ModulatedAttLayer(in_channels=512 * block.expansion)
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, **kwargs):
out = self.conv1(x)
out = self.bn1(out)
out = self.relu(out)
out = self.maxpool(out)
out = self.layer1(out)
if 'layer' in kwargs and kwargs['layer'] == 'layer1':
out = kwargs['coef']*out + (1-kwargs['coef'])*out[kwargs['index']]
out = self.layer2(out)
if 'layer' in kwargs and kwargs['layer'] == 'layer2':
out = kwargs['coef']*out+(1-kwargs['coef'])*out[kwargs['index']]
out = self.layer3(out)
if 'layer' in kwargs and kwargs['layer'] == 'layer3':
out = kwargs['coef']*out+(1-kwargs['coef'])*out[kwargs['index']]
out = self.layer4(out)
if 'layer' in kwargs and kwargs['layer'] == 'layer4':
out = kwargs['coef']*out+(1-kwargs['coef'])*out[kwargs['index']]
return out
def init_weights(model, weights_path, caffe=False, classifier=False):
"""Initialize weights"""
print('Pretrained %s weights path: %s' % ('classifier' if classifier else 'feature model',
weights_path))
weights = torch.load(weights_path)
if not classifier:
if caffe:
weights = {k: weights[k] if k in weights else model.state_dict()[k]
for k in model.state_dict()}
else:
weights = weights['state_dict_best']['feat_model']
weights = {k: weights['module.' + k] if 'module.' + k in weights else model.state_dict()[k]
for k in model.state_dict()}
else:
weights = weights['state_dict_best']['classifier']
weights = {k: weights['module.fc.' + k] if 'module.fc.' + k in weights else model.state_dict()[k]
for k in model.state_dict()}
model.load_state_dict(weights)
return model
def res10(cfg, use_selfatt=False, use_fc=False, dropout=None, stage1_weights=False, dataset=None, test=False,
pretrain=False,
pretrained_model = None,
last_layer_stride = None,
flag=None):
print('Loading Scratch ResNet 10 Feature Model.')
resnet10 = ResNet(BasicBlock, [1, 1, 1, 1], use_modulatedatt=use_selfatt, use_fc=use_fc, dropout=None)
if not test:
if stage1_weights:
assert(dataset)
print('Loading %s Stage 1 ResNet 10 Weights.' % dataset)
resnet10 = init_weights(model=resnet10,
weights_path='./logs/%s/stage1/final_model_checkpoint.pth' % dataset)
else:
print('No Pretrained Weights For Feature Model.')
return resnet10