Spaces:
Running
on
T4
Running
on
T4
File size: 11,277 Bytes
d4b77ac |
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 |
import torch.nn as nn
import torch
from torch.autograd import Variable
import math
import torch.utils.model_zoo as model_zoo
from models.features import Features
from utils.log_helper import log_once
__all__ = ['ResNet', 'resnet18', 'resnet34', 'resnet50', 'resnet101',
'resnet152']
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(Features):
expansion = 4
def __init__(self, inplanes, planes, stride=1, downsample=None, dilation=1):
super(Bottleneck, self).__init__()
self.conv1 = nn.Conv2d(inplanes, planes, kernel_size=1, bias=False)
self.bn1 = nn.BatchNorm2d(planes)
# padding = (2 - stride) + (dilation // 2 - 1)
padding = 2 - stride
assert stride==1 or dilation==1, "stride and dilation must have one equals to zero at least"
if dilation > 1:
padding = dilation
self.conv2 = nn.Conv2d(planes, planes, kernel_size=3, stride=stride,
padding=padding, bias=False, dilation=dilation)
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)
if out.size() != residual.size():
print(out.size(), residual.size())
out += residual
out = self.relu(out)
return out
class Bottleneck_nop(nn.Module):
expansion = 4
def __init__(self, inplanes, planes, stride=1, downsample=None):
super(Bottleneck_nop, 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=0, 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)
s = residual.size(3)
residual = residual[:, :, 1:s-1, 1:s-1]
out += residual
out = self.relu(out)
return out
class ResNet(nn.Module):
def __init__(self, block, layers, layer4=False, layer3=False):
self.inplanes = 64
super(ResNet, self).__init__()
self.conv1 = nn.Conv2d(3, 64, kernel_size=7, stride=2, padding=0, # 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) # 31x31, 15x15
self.feature_size = 128 * block.expansion
if layer3:
self.layer3 = self._make_layer(block, 256, layers[2], stride=1, dilation=2) # 15x15, 7x7
self.feature_size = (256 + 128) * block.expansion
else:
self.layer3 = lambda x:x # identity
if layer4:
self.layer4 = self._make_layer(block, 512, layers[3], stride=1, dilation=4) # 7x7, 3x3
self.feature_size = 512 * block.expansion
else:
self.layer4 = lambda x:x # identity
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, dilation=1):
downsample = None
dd = dilation
if stride != 1 or self.inplanes != planes * block.expansion:
if stride == 1 and dilation == 1:
downsample = nn.Sequential(
nn.Conv2d(self.inplanes, planes * block.expansion,
kernel_size=1, stride=stride, bias=False),
nn.BatchNorm2d(planes * block.expansion),
)
else:
if dilation > 1:
dd = dilation // 2
padding = dd
else:
dd = 1
padding = 0
downsample = nn.Sequential(
nn.Conv2d(self.inplanes, planes * block.expansion,
kernel_size=3, stride=stride, bias=False,
padding=padding, dilation=dd),
nn.BatchNorm2d(planes * block.expansion),
)
layers = []
# layers.append(block(self.inplanes, planes, stride, downsample, dilation=dilation))
layers.append(block(self.inplanes, planes, stride, downsample, dilation=dd))
self.inplanes = planes * block.expansion
for i in range(1, blocks):
layers.append(block(self.inplanes, planes, dilation=dilation))
return nn.Sequential(*layers)
def forward(self, x):
x = self.conv1(x)
x = self.bn1(x)
x = self.relu(x)
# print x.size()
x = self.maxpool(x)
# print x.size()
p1 = self.layer1(x)
p2 = self.layer2(p1)
p3 = self.layer3(p2)
# p3 = torch.cat([p2, p3], 1)
log_once("p3 {}".format(p3.size()))
p4 = self.layer4(p3)
return p2, p3, p4
class ResAdjust(nn.Module):
def __init__(self,
block=Bottleneck,
out_channels=256,
adjust_number=1,
fuse_layers=[2,3,4]):
super(ResAdjust, self).__init__()
self.fuse_layers = set(fuse_layers)
if 2 in self.fuse_layers:
self.layer2 = self._make_layer(block, 128, 1, out_channels, adjust_number)
if 3 in self.fuse_layers:
self.layer3 = self._make_layer(block, 256, 2, out_channels, adjust_number)
if 4 in self.fuse_layers:
self.layer4 = self._make_layer(block, 512, 4, out_channels, adjust_number)
self.feature_size = out_channels * len(self.fuse_layers)
def _make_layer(self, block, plances, dilation, out, number=1):
layers = []
for _ in range(number):
layer = block(plances * block.expansion, plances, dilation=dilation)
layers.append(layer)
downsample = nn.Sequential(
nn.Conv2d(plances * block.expansion, out, kernel_size=3, padding=1, bias=False),
nn.BatchNorm2d(out)
)
layers.append(downsample)
return nn.Sequential(*layers)
def forward(self, p2, p3, p4):
outputs = []
if 2 in self.fuse_layers:
outputs.append(self.layer2(p2))
if 3 in self.fuse_layers:
outputs.append(self.layer3(p3))
if 4 in self.fuse_layers:
outputs.append(self.layer4(p4))
# return torch.cat(outputs, 1)
return outputs
def resnet18(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:
model.load_state_dict(model_zoo.load_url(model_urls['resnet18']))
return model
def resnet34(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:
model.load_state_dict(model_zoo.load_url(model_urls['resnet34']))
return model
def resnet50(pretrained=False, **kwargs):
"""Constructs a ResNet-50 model.
Args:
pretrained (bool): If True, returns a model pre-trained on ImageNet
"""
model = ResNet(Bottleneck, [3, 4, 6, 3], **kwargs)
if pretrained:
model.load_state_dict(model_zoo.load_url(model_urls['resnet50']))
return model
def resnet101(pretrained=False, **kwargs):
"""Constructs a ResNet-101 model.
Args:
pretrained (bool): If True, returns a model pre-trained on ImageNet
"""
model = ResNet(Bottleneck, [3, 4, 23, 3], **kwargs)
if pretrained:
model.load_state_dict(model_zoo.load_url(model_urls['resnet101']))
return model
def resnet152(pretrained=False, **kwargs):
"""Constructs a ResNet-152 model.
Args:
pretrained (bool): If True, returns a model pre-trained on ImageNet
"""
model = ResNet(Bottleneck, [3, 8, 36, 3], **kwargs)
if pretrained:
model.load_state_dict(model_zoo.load_url(model_urls['resnet152']))
return model
if __name__ == '__main__':
net = resnet50()
print(net)
net = net.cuda()
var = torch.FloatTensor(1,3,127,127).cuda()
var = Variable(var)
template = net(var)
print('Examplar Size: {}'.format(template.shape))
var = torch.FloatTensor(1,3,255,255).cuda()
var = Variable(var)
net(var)
|