-
Notifications
You must be signed in to change notification settings - Fork 219
/
resnet.py
328 lines (261 loc) · 10.1 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
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
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
from model.utils.config import cfg
from model.fpn.fpn import _FPN
import torch
import torch.nn as nn
import torch.nn.functional as F
from torch.autograd import Variable
import math
import torch.utils.model_zoo as model_zoo
import pdb
__all__ = ['ResNet', 'resnet18', 'resnet34', 'resnet50', 'resnet101',
'resnet152']
model_urls = {
'resnet18': 'https://s3.amazonaws.com/pytorch/models/resnet18-5c106cde.pth',
'resnet34': 'https://s3.amazonaws.com/pytorch/models/resnet34-333f7ec4.pth',
'resnet50': 'https://s3.amazonaws.com/pytorch/models/resnet50-19c8e357.pth',
'resnet101': 'https://s3.amazonaws.com/pytorch/models/resnet101-5d3b4d8f.pth',
'resnet152': 'https://s3.amazonaws.com/pytorch/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, stride=stride, bias=False) # change
self.bn1 = nn.BatchNorm2d(planes)
self.conv2 = nn.Conv2d(planes, planes, kernel_size=3, stride=1, # change
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=0, ceil_mode=True) # change
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=1)
self.avgpool = nn.AvgPool2d(7)
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 = self.avgpool(x)
x = x.view(x.size(0), -1)
x = self.fc(x)
return x
def resnet18(pretrained=False):
"""Constructs a ResNet-18 model.
Args:
pretrained (bool): If True, returns a model pre-trained on ImageNet
"""
model = ResNet(BasicBlock, [2, 2, 2, 2])
if pretrained:
model.load_state_dict(model_zoo.load_url(model_urls['resnet18']))
return model
def resnet34(pretrained=False):
"""Constructs a ResNet-34 model.
Args:
pretrained (bool): If True, returns a model pre-trained on ImageNet
"""
model = ResNet(BasicBlock, [3, 4, 6, 3])
if pretrained:
model.load_state_dict(model_zoo.load_url(model_urls['resnet34']))
return model
def resnet50(pretrained=False):
"""Constructs a ResNet-50 model.
Args:
pretrained (bool): If True, returns a model pre-trained on ImageNet
"""
model = ResNet(Bottleneck, [3, 4, 6, 3])
if pretrained:
model.load_state_dict(model_zoo.load_url(model_urls['resnet50']))
return model
def resnet101(pretrained=False):
"""Constructs a ResNet-101 model.
Args:
pretrained (bool): If True, returns a model pre-trained on ImageNet
"""
model = ResNet(Bottleneck, [3, 4, 23, 3])
if pretrained:
model.load_state_dict(model_zoo.load_url(model_urls['resnet101']))
return model
def resnet152(pretrained=False):
"""Constructs a ResNet-152 model.
Args:
pretrained (bool): If True, returns a model pre-trained on ImageNet
"""
model = ResNet(Bottleneck, [3, 8, 36, 3])
if pretrained:
model.load_state_dict(model_zoo.load_url(model_urls['resnet152']))
return model
class resnet(_FPN):
def __init__(self, classes, num_layers=101, pretrained=False, class_agnostic=False):
self.model_path = 'data/pretrained_model/resnet101_caffe.pth'
self.dout_base_model = 256
self.pretrained = pretrained
self.class_agnostic = class_agnostic
_FPN.__init__(self, classes, class_agnostic)
def _init_modules(self):
resnet = resnet101()
if self.pretrained == True:
print("Loading pretrained weights from %s" %(self.model_path))
state_dict = torch.load(self.model_path)
resnet.load_state_dict({k:v for k,v in state_dict.items() if k in resnet.state_dict()})
self.RCNN_layer0 = nn.Sequential(resnet.conv1, resnet.bn1, resnet.relu, resnet.maxpool)
self.RCNN_layer1 = nn.Sequential(resnet.layer1)
self.RCNN_layer2 = nn.Sequential(resnet.layer2)
self.RCNN_layer3 = nn.Sequential(resnet.layer3)
self.RCNN_layer4 = nn.Sequential(resnet.layer4)
# Top layer
self.RCNN_toplayer = nn.Conv2d(2048, 256, kernel_size=1, stride=1, padding=0) # reduce channel
# Smooth layers
self.RCNN_smooth1 = nn.Conv2d(256, 256, kernel_size=3, stride=1, padding=1)
self.RCNN_smooth2 = nn.Conv2d(256, 256, kernel_size=3, stride=1, padding=1)
self.RCNN_smooth3 = nn.Conv2d(256, 256, kernel_size=3, stride=1, padding=1)
# Lateral layers
self.RCNN_latlayer1 = nn.Conv2d(1024, 256, kernel_size=1, stride=1, padding=0)
self.RCNN_latlayer2 = nn.Conv2d( 512, 256, kernel_size=1, stride=1, padding=0)
self.RCNN_latlayer3 = nn.Conv2d( 256, 256, kernel_size=1, stride=1, padding=0)
# ROI Pool feature downsampling
self.RCNN_roi_feat_ds = nn.Conv2d(256, 256, kernel_size=3, stride=2, padding=1)
self.RCNN_top = nn.Sequential(
nn.Conv2d(256, 1024, kernel_size=cfg.POOLING_SIZE, stride=cfg.POOLING_SIZE, padding=0),
nn.ReLU(True),
nn.Conv2d(1024, 1024, kernel_size=1, stride=1, padding=0),
nn.ReLU(True)
)
self.RCNN_cls_score = nn.Linear(1024, self.n_classes)
if self.class_agnostic:
self.RCNN_bbox_pred = nn.Linear(1024, 4)
else:
self.RCNN_bbox_pred = nn.Linear(1024, 4 * self.n_classes)
# Fix blocks
for p in self.RCNN_layer0[0].parameters(): p.requires_grad=False
for p in self.RCNN_layer0[1].parameters(): p.requires_grad=False
assert (0 <= cfg.RESNET.FIXED_BLOCKS < 4)
if cfg.RESNET.FIXED_BLOCKS >= 3:
for p in self.RCNN_layer3.parameters(): p.requires_grad=False
if cfg.RESNET.FIXED_BLOCKS >= 2:
for p in self.RCNN_layer2.parameters(): p.requires_grad=False
if cfg.RESNET.FIXED_BLOCKS >= 1:
for p in self.RCNN_layer1.parameters(): p.requires_grad=False
def set_bn_fix(m):
classname = m.__class__.__name__
if classname.find('BatchNorm') != -1:
for p in m.parameters(): p.requires_grad=False
self.RCNN_layer0.apply(set_bn_fix)
self.RCNN_layer1.apply(set_bn_fix)
self.RCNN_layer2.apply(set_bn_fix)
self.RCNN_layer3.apply(set_bn_fix)
self.RCNN_layer4.apply(set_bn_fix)
def train(self, mode=True):
# Override train so that the training mode is set as we want
nn.Module.train(self, mode)
if mode:
# Set fixed blocks to be in eval mode
self.RCNN_layer0.eval()
self.RCNN_layer1.eval()
self.RCNN_layer2.train()
self.RCNN_layer3.train()
self.RCNN_layer4.train()
self.RCNN_smooth1.train()
self.RCNN_smooth2.train()
self.RCNN_smooth3.train()
self.RCNN_latlayer1.train()
self.RCNN_latlayer2.train()
self.RCNN_latlayer3.train()
self.RCNN_toplayer.train()
def set_bn_eval(m):
classname = m.__class__.__name__
if classname.find('BatchNorm') != -1:
m.eval()
self.RCNN_layer0.apply(set_bn_eval)
self.RCNN_layer1.apply(set_bn_eval)
self.RCNN_layer2.apply(set_bn_eval)
self.RCNN_layer3.apply(set_bn_eval)
self.RCNN_layer4.apply(set_bn_eval)
def _head_to_tail(self, pool5):
block5 = self.RCNN_top(pool5)
fc7 = block5.mean(3).mean(2)
return fc7