-
Notifications
You must be signed in to change notification settings - Fork 16
/
Copy pathmodel.py
370 lines (292 loc) · 13.8 KB
/
model.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
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
"""
SpaceNet 6 baseline neural network architecture
Code adapted with minimal changes from these sources:
TernausNet:
Lines 31-196 of this file
https://github.com/ternaus/TernausNet/blob/master/unet_models.py
License in licenses/LICENSE_TernausNet.txt
VGG-11:
Lines 25-28 and 199-370 of this file
https://github.com/pytorch/vision/blob/master/torchvision/models/vgg.py
https://github.com/pytorch/vision/blob/master/torchvision/models/utils.py
License in licenses/LICENSE_Pytorch.txt
Note: The model weight URLs given here only work if there are three bands.
However, the current default (which is used for SpaceNet 6 SAR data) is 4
bands.
"""
import torch
import torch.nn as nn
from torch.nn import functional as F
try:
from torch.hub import load_state_dict_from_url
except ImportError:
from torch.utils.model_zoo import load_url as load_state_dict_from_url
def conv3x3(in_, out):
return nn.Conv2d(in_, out, 3, padding=1)
class ConvRelu(nn.Module):
def __init__(self, in_, out):
super().__init__()
self.conv = conv3x3(in_, out)
self.activation = nn.ReLU(inplace=True)
def forward(self, x):
x = self.conv(x)
x = self.activation(x)
return x
class DecoderBlock(nn.Module):
def __init__(self, in_channels, middle_channels, out_channels):
super().__init__()
self.block = nn.Sequential(
ConvRelu(in_channels, middle_channels),
nn.ConvTranspose2d(middle_channels, out_channels, kernel_size=3, stride=2, padding=1, output_padding=1),
nn.ReLU(inplace=True)
)
def forward(self, x):
return self.block(x)
class UNet11(nn.Module):
def __init__(self, num_filters=32, pretrained=False):
"""
:param num_classes:
:param num_filters:
:param pretrained:
False - no pre-trained network is used
True - encoder is pre-trained with VGG11
"""
super().__init__()
self.pool = nn.MaxPool2d(2, 2)
self.encoder = vgg11(pretrained=pretrained).features
self.relu = self.encoder[1]
self.conv1 = self.encoder[0]
self.conv2 = self.encoder[3]
self.conv3s = self.encoder[6]
self.conv3 = self.encoder[8]
self.conv4s = self.encoder[11]
self.conv4 = self.encoder[13]
self.conv5s = self.encoder[16]
self.conv5 = self.encoder[18]
self.center = DecoderBlock(num_filters * 8 * 2, num_filters * 8 * 2, num_filters * 8)
self.dec5 = DecoderBlock(num_filters * (16 + 8), num_filters * 8 * 2, num_filters * 8)
self.dec4 = DecoderBlock(num_filters * (16 + 8), num_filters * 8 * 2, num_filters * 4)
self.dec3 = DecoderBlock(num_filters * (8 + 4), num_filters * 4 * 2, num_filters * 2)
self.dec2 = DecoderBlock(num_filters * (4 + 2), num_filters * 2 * 2, num_filters)
self.dec1 = ConvRelu(num_filters * (2 + 1), num_filters)
self.final = nn.Conv2d(num_filters, 1, kernel_size=1)
def forward(self, x):
conv1 = self.relu(self.conv1(x))
conv2 = self.relu(self.conv2(self.pool(conv1)))
conv3s = self.relu(self.conv3s(self.pool(conv2)))
conv3 = self.relu(self.conv3(conv3s))
conv4s = self.relu(self.conv4s(self.pool(conv3)))
conv4 = self.relu(self.conv4(conv4s))
conv5s = self.relu(self.conv5s(self.pool(conv4)))
conv5 = self.relu(self.conv5(conv5s))
center = self.center(self.pool(conv5))
dec5 = self.dec5(torch.cat([center, conv5], 1))
dec4 = self.dec4(torch.cat([dec5, conv4], 1))
dec3 = self.dec3(torch.cat([dec4, conv3], 1))
dec2 = self.dec2(torch.cat([dec3, conv2], 1))
dec1 = self.dec1(torch.cat([dec2, conv1], 1))
return self.final(dec1)
class UNet16(nn.Module):
def __init__(self, num_classes=1, num_filters=32, pretrained=False, is_deconv=False):
"""
:param num_classes:
:param num_filters:
:param pretrained:
False - no pre-trained network used
True - encoder pre-trained with VGG16
:is_deconv:
False: bilinear interpolation is used in decoder
True: deconvolution is used in decoder
"""
super().__init__()
self.num_classes = num_classes
self.pool = nn.MaxPool2d(2, 2)
self.encoder = vgg16(pretrained=pretrained).features
self.relu = nn.ReLU(inplace=True)
self.conv1 = nn.Sequential(self.encoder[0],
self.relu,
self.encoder[2],
self.relu)
self.conv2 = nn.Sequential(self.encoder[5],
self.relu,
self.encoder[7],
self.relu)
self.conv3 = nn.Sequential(self.encoder[10],
self.relu,
self.encoder[12],
self.relu,
self.encoder[14],
self.relu)
self.conv4 = nn.Sequential(self.encoder[17],
self.relu,
self.encoder[19],
self.relu,
self.encoder[21],
self.relu)
self.conv5 = nn.Sequential(self.encoder[24],
self.relu,
self.encoder[26],
self.relu,
self.encoder[28],
self.relu)
self.center = DecoderBlockV2(512, num_filters * 8 * 2, num_filters * 8, is_deconv)
self.dec5 = DecoderBlockV2(512 + num_filters * 8, num_filters * 8 * 2, num_filters * 8, is_deconv)
self.dec4 = DecoderBlockV2(512 + num_filters * 8, num_filters * 8 * 2, num_filters * 8, is_deconv)
self.dec3 = DecoderBlockV2(256 + num_filters * 8, num_filters * 4 * 2, num_filters * 2, is_deconv)
self.dec2 = DecoderBlockV2(128 + num_filters * 2, num_filters * 2 * 2, num_filters, is_deconv)
self.dec1 = ConvRelu(64 + num_filters, num_filters)
self.final = nn.Conv2d(num_filters, num_classes, kernel_size=1)
def forward(self, x):
conv1 = self.conv1(x)
conv2 = self.conv2(self.pool(conv1))
conv3 = self.conv3(self.pool(conv2))
conv4 = self.conv4(self.pool(conv3))
conv5 = self.conv5(self.pool(conv4))
center = self.center(self.pool(conv5))
dec5 = self.dec5(torch.cat([center, conv5], 1))
dec4 = self.dec4(torch.cat([dec5, conv4], 1))
dec3 = self.dec3(torch.cat([dec4, conv3], 1))
dec2 = self.dec2(torch.cat([dec3, conv2], 1))
dec1 = self.dec1(torch.cat([dec2, conv1], 1))
if self.num_classes > 1:
x_out = F.log_softmax(self.final(dec1), dim=1)
else:
x_out = self.final(dec1)
return x_out
model_urls = {
'vgg11': 'https://download.pytorch.org/models/vgg11-bbd30ac9.pth',
'vgg13': 'https://download.pytorch.org/models/vgg13-c768596a.pth',
'vgg16': 'https://download.pytorch.org/models/vgg16-397923af.pth',
'vgg19': 'https://download.pytorch.org/models/vgg19-dcbb9e9d.pth',
'vgg11_bn': 'https://download.pytorch.org/models/vgg11_bn-6002323d.pth',
'vgg13_bn': 'https://download.pytorch.org/models/vgg13_bn-abd245e5.pth',
'vgg16_bn': 'https://download.pytorch.org/models/vgg16_bn-6c64b313.pth',
'vgg19_bn': 'https://download.pytorch.org/models/vgg19_bn-c79401a0.pth',
}
class VGG(nn.Module):
def __init__(self, features, num_classes=1000, init_weights=True):
super(VGG, self).__init__()
self.features = features
self.avgpool = nn.AdaptiveAvgPool2d((7, 7))
self.classifier = nn.Sequential(
nn.Linear(512 * 7 * 7, 4096),
nn.ReLU(True),
nn.Dropout(),
nn.Linear(4096, 4096),
nn.ReLU(True),
nn.Dropout(),
nn.Linear(4096, num_classes),
)
if init_weights:
self._initialize_weights()
def forward(self, x):
x = self.features(x)
x = self.avgpool(x)
x = torch.flatten(x, 1)
x = self.classifier(x)
return x
def _initialize_weights(self):
for m in self.modules():
if isinstance(m, nn.Conv2d):
nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu')
if m.bias is not None:
nn.init.constant_(m.bias, 0)
elif isinstance(m, nn.BatchNorm2d):
nn.init.constant_(m.weight, 1)
nn.init.constant_(m.bias, 0)
elif isinstance(m, nn.Linear):
nn.init.normal_(m.weight, 0, 0.01)
nn.init.constant_(m.bias, 0)
def make_layers(cfg, batch_norm=False, bands=4):
layers = []
in_channels = bands
for v in cfg:
if v == 'M':
layers += [nn.MaxPool2d(kernel_size=2, stride=2)]
else:
conv2d = nn.Conv2d(in_channels, v, kernel_size=3, padding=1)
if batch_norm:
layers += [conv2d, nn.BatchNorm2d(v), nn.ReLU(inplace=True)]
else:
layers += [conv2d, nn.ReLU(inplace=True)]
in_channels = v
return nn.Sequential(*layers)
cfgs = {
'A': [64, 'M', 128, 'M', 256, 256, 'M', 512, 512, 'M', 512, 512, 'M'],
'B': [64, 64, 'M', 128, 128, 'M', 256, 256, 'M', 512, 512, 'M', 512, 512, 'M'],
'D': [64, 64, 'M', 128, 128, 'M', 256, 256, 256, 'M', 512, 512, 512, 'M', 512, 512, 512, 'M'],
'E': [64, 64, 'M', 128, 128, 'M', 256, 256, 256, 256, 'M', 512, 512, 512, 512, 'M', 512, 512, 512, 512, 'M'],
}
def _vgg(arch, cfg, batch_norm, pretrained, progress, **kwargs):
if pretrained:
kwargs['init_weights'] = False
model = VGG(make_layers(cfgs[cfg], batch_norm=batch_norm), **kwargs)
if pretrained:
state_dict = load_state_dict_from_url(model_urls[arch],
progress=progress)
model.load_state_dict(state_dict)
return model
def vgg11(pretrained=False, progress=True, **kwargs):
r"""VGG 11-layer model (configuration "A") from
`"Very Deep Convolutional Networks For Large-Scale Image Recognition" <https://arxiv.org/pdf/1409.1556.pdf>`_
Args:
pretrained (bool): If True, returns a model pre-trained on ImageNet
progress (bool): If True, displays a progress bar of the download to stderr
"""
return _vgg('vgg11', 'A', False, pretrained, progress, **kwargs)
def vgg11_bn(pretrained=False, progress=True, **kwargs):
r"""VGG 11-layer model (configuration "A") with batch normalization
`"Very Deep Convolutional Networks For Large-Scale Image Recognition" <https://arxiv.org/pdf/1409.1556.pdf>`_
Args:
pretrained (bool): If True, returns a model pre-trained on ImageNet
progress (bool): If True, displays a progress bar of the download to stderr
"""
return _vgg('vgg11_bn', 'A', True, pretrained, progress, **kwargs)
def vgg13(pretrained=False, progress=True, **kwargs):
r"""VGG 13-layer model (configuration "B")
`"Very Deep Convolutional Networks For Large-Scale Image Recognition" <https://arxiv.org/pdf/1409.1556.pdf>`_
Args:
pretrained (bool): If True, returns a model pre-trained on ImageNet
progress (bool): If True, displays a progress bar of the download to stderr
"""
return _vgg('vgg13', 'B', False, pretrained, progress, **kwargs)
def vgg13_bn(pretrained=False, progress=True, **kwargs):
r"""VGG 13-layer model (configuration "B") with batch normalization
`"Very Deep Convolutional Networks For Large-Scale Image Recognition" <https://arxiv.org/pdf/1409.1556.pdf>`_
Args:
pretrained (bool): If True, returns a model pre-trained on ImageNet
progress (bool): If True, displays a progress bar of the download to stderr
"""
return _vgg('vgg13_bn', 'B', True, pretrained, progress, **kwargs)
def vgg16(pretrained=False, progress=True, **kwargs):
r"""VGG 16-layer model (configuration "D")
`"Very Deep Convolutional Networks For Large-Scale Image Recognition" <https://arxiv.org/pdf/1409.1556.pdf>`_
Args:
pretrained (bool): If True, returns a model pre-trained on ImageNet
progress (bool): If True, displays a progress bar of the download to stderr
"""
return _vgg('vgg16', 'D', False, pretrained, progress, **kwargs)
def vgg16_bn(pretrained=False, progress=True, **kwargs):
r"""VGG 16-layer model (configuration "D") with batch normalization
`"Very Deep Convolutional Networks For Large-Scale Image Recognition" <https://arxiv.org/pdf/1409.1556.pdf>`_
Args:
pretrained (bool): If True, returns a model pre-trained on ImageNet
progress (bool): If True, displays a progress bar of the download to stderr
"""
return _vgg('vgg16_bn', 'D', True, pretrained, progress, **kwargs)
def vgg19(pretrained=False, progress=True, **kwargs):
r"""VGG 19-layer model (configuration "E")
`"Very Deep Convolutional Networks For Large-Scale Image Recognition" <https://arxiv.org/pdf/1409.1556.pdf>`_
Args:
pretrained (bool): If True, returns a model pre-trained on ImageNet
progress (bool): If True, displays a progress bar of the download to stderr
"""
return _vgg('vgg19', 'E', False, pretrained, progress, **kwargs)
def vgg19_bn(pretrained=False, progress=True, **kwargs):
r"""VGG 19-layer model (configuration 'E') with batch normalization
`"Very Deep Convolutional Networks For Large-Scale Image Recognition" <https://arxiv.org/pdf/1409.1556.pdf>`_
Args:
pretrained (bool): If True, returns a model pre-trained on ImageNet
progress (bool): If True, displays a progress bar of the download to stderr
"""
return _vgg('vgg19_bn', 'E', True, pretrained, progress, **kwargs)