-
Notifications
You must be signed in to change notification settings - Fork 18
/
auxi_net_v0_noBAN.py
347 lines (277 loc) · 11.5 KB
/
auxi_net_v0_noBAN.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
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
import torch
import torch.nn as nn
import math
import torch.utils.model_zoo as model_zoo
import copy
__all__ = ['ResNet', 'resnet18_carla', 'resnet34_carla', 'resnet50_carla']
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',
}
model_paths = {
'resnet34': 'resnet34-333f7ec4.pth',
}
'''
in_planes: input channels
out_planes: output channels
'''
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 ChannelAttention(nn.Module):
def __init__(self, in_planes, ratio=16):
super(ChannelAttention, self).__init__()
# AdaptiveAvgPooling2d는 Batch, Channel은 유지.
# 원하는 output W, H를 입력하면 kernal_size, stride등을 자동으로 설정하여 연산.
self.avg_pool = nn.AdaptiveAvgPool2d(1)
self.max_pool = nn.AdaptiveMaxPool2d(1)
self.fc1 = nn.Conv2d(in_planes, in_planes // 16, 1, bias=False)
self.relu1 = nn.ReLU()
self.fc2 = nn.Conv2d(in_planes // 16, in_planes, 1, bias=False)
self.sigmoid = nn.Sigmoid()
def forward(self, x):
avg_out = self.fc2(self.relu1(self.fc1(self.avg_pool(x))))
max_out = self.fc2(self.relu1(self.fc1(self.max_pool(x))))
out = avg_out + max_out
return self.sigmoid(out)
class SpatialAttention(nn.Module):
def __init__(self, kernel_size=7):
super(SpatialAttention, self).__init__()
assert kernel_size in (3, 7), 'kernel size must be 3 or 7'
padding = 3 if kernel_size == 7 else 1
self.conv1 = nn.Conv2d(2, 1, kernel_size, padding=padding, bias=False)
self.sigmoid = nn.Sigmoid()
def forward(self, x):
avg_out = torch.mean(x, dim=1, keepdim=True)
max_out, _ = torch.max(x, dim=1, keepdim=True)
x = torch.cat([avg_out, max_out], dim=1)
x = self.conv1(x)
return self.sigmoid(x)
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.ca = ChannelAttention(planes)
self.sa = SpatialAttention()
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.ca(out) * out
# out = self.sa(out) * 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.ca = ChannelAttention(planes * 4)
self.sa = SpatialAttention()
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)
# out = self.ca(out) * out
# out = self.sa(out) * 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
self.inplanes_2 = self.inplanes
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.fc = nn.Linear(512 * block.expansion, num_classes)
# fc layers
self.img_fc = nn.Sequential(
nn.Linear(10752, 512),
nn.Dropout(0.3),
nn.ReLU(),
nn.Linear(512, 512),
nn.Dropout(0.3),
nn.ReLU(),
)
self.speed_fc = nn.Sequential(
nn.Linear(1, 128),
nn.Dropout(0.5),
nn.ReLU(),
nn.Linear(128, 128),
nn.Dropout(0.5),
nn.ReLU(),
)
self.emb_fc = nn.Sequential(
nn.Linear(512 + 128, 512),
nn.Dropout(0.5),
nn.ReLU(),
)
self.branches = nn.ModuleList([
nn.Sequential(
nn.Linear(512, 256),
nn.Dropout(0.5),
nn.ReLU(),
nn.Linear(256, 256),
# nn.Dropout(self.dropout_vec[i*2+14]),
nn.ReLU(),
nn.Linear(256, 1),
) for i in range(4)
])
self.speed_branch = nn.Sequential(
nn.Linear(512, 256),
nn.Dropout(0.5),
nn.ReLU(),
nn.Linear(256, 256),
# nn.Dropout(self.dropout_vec[1]),
nn.ReLU(),
nn.Linear(256, 1),
)
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_()
elif isinstance(m, nn.Linear):
nn.init.xavier_uniform_(
m.weight)
m.bias.data.fill_(0.01)
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_2 = self.inplanes # 동일한 형태의 layer branch를 만들기 위해 변경 전의 self.inplanes를 저장
self.inplanes = planes * block.expansion
for i in range(1, blocks):
layers.append(block(self.inplanes, planes))
return nn.Sequential(*layers)
def _make_layer_2(self, block, planes, blocks, stride=1):
downsample = None
if stride != 1 or self.inplanes_2 != planes * block.expansion:
downsample = nn.Sequential(
nn.Conv2d(self.inplanes_2, planes * block.expansion,
kernel_size=1, stride=stride, bias=False),
nn.BatchNorm2d(planes * block.expansion),
)
layers = []
layers.append(block(self.inplanes_2, planes, stride, downsample))
self.inplanes_2 = planes * block.expansion
for i in range(1, blocks):
layers.append(block(self.inplanes_2, planes))
return nn.Sequential(*layers)
def forward(self, x, speed):
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 = x.view(x.size(0), -1)
x = self.img_fc(x)
speed = self.speed_fc(speed)
emb = torch.cat([x, speed], dim=1)
emb = self.emb_fc(emb)
output = torch.cat([out(emb) for out in self.branches],
dim=1)
pred_speed = self.speed_branch(x)
return output, pred_speed
def resnet18_carla(pretrained=False, **kwargs):
"""Constructs a ResNet-18 model.
Args:
pretrained (bool): If True, returns a model pre-trained on ImageNet
"""
model = ResNet(BasicBlock, [2, 2, 2, 2], **kwargs)
if pretrained:
pretrained_state_dict = model_zoo.load_url(model_urls['resnet18'])
now_state_dict = model.state_dict()
now_state_dict.update(pretrained_state_dict)
model.load_state_dict(now_state_dict)
return model
def resnet34_carla(pretrained=False, **kwargs):
"""Constructs a ResNet-34 model.
Args:
pretrained (bool): If True, returns a model pre-trained on ImageNet
"""
model = ResNet(BasicBlock, [3, 4, 6, 3], **kwargs)
if pretrained:
now_state_dict = model.state_dict()
# pretrained_state_dict = model_zoo.load_url(model_urls['resnet34'])
pretrained_state_dict = torch.load(model_paths['resnet34'])
# model_paths
# 1. filter out unnecessary keys
pretrained_state_dict = {k: v for k, v in pretrained_state_dict.items() if k in now_state_dict}
# 2. overwrite entries in the existing state dict
now_state_dict.update(pretrained_state_dict)
# 3. load the new state dict
model.load_state_dict(now_state_dict)
return model
def resnet50_carla(pretrained=False, **kwargs):
"""Constructs a ResNet-50 model.
Args:
pretrained (bool): If True, returns a model pre-trained on ImageNet
"""
model = ResNet(BasicBlock, [3, 4, 6, 3], **kwargs)
if pretrained:
now_state_dict = model.state_dict()
# pretrained_state_dict = model_zoo.load_url(model_urls['resnet34'])
pretrained_state_dict = torch.load(model_paths['resnet34'])
# model_paths
# 1. filter out unnecessary keys
pretrained_state_dict = {k: v for k, v in pretrained_state_dict.items() if k in now_state_dict}
# 2. overwrite entries in the existing state dict
now_state_dict.update(pretrained_state_dict)
# 3. load the new state dict
model.load_state_dict(now_state_dict)
return model