File size: 16,470 Bytes
c985ba4 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 |
import math
import torch.nn as nn
from .splat import SplAtConv2d, DropBlock2D
from utils.learning import freeze_params
__all__ = ['ResNet', 'Bottleneck']
_url_format = 'https://s3.us-west-1.wasabisys.com/resnest/torch/{}-{}.pth'
_model_sha256 = {name: checksum for checksum, name in []}
def short_hash(name):
if name not in _model_sha256:
raise ValueError(
'Pretrained model for {name} is not available.'.format(name=name))
return _model_sha256[name][:8]
resnest_model_urls = {
name: _url_format.format(name, short_hash(name))
for name in _model_sha256.keys()
}
class GlobalAvgPool2d(nn.Module):
def __init__(self):
"""Global average pooling over the input's spatial dimensions"""
super(GlobalAvgPool2d, self).__init__()
def forward(self, inputs):
return nn.functional.adaptive_avg_pool2d(inputs,
1).view(inputs.size(0), -1)
class Bottleneck(nn.Module):
"""ResNet Bottleneck
"""
# pylint: disable=unused-argument
expansion = 4
def __init__(self,
inplanes,
planes,
stride=1,
downsample=None,
radix=1,
cardinality=1,
bottleneck_width=64,
avd=False,
avd_first=False,
dilation=1,
is_first=False,
rectified_conv=False,
rectify_avg=False,
norm_layer=None,
dropblock_prob=0.0,
last_gamma=False):
super(Bottleneck, self).__init__()
group_width = int(planes * (bottleneck_width / 64.)) * cardinality
self.conv1 = nn.Conv2d(inplanes,
group_width,
kernel_size=1,
bias=False)
self.bn1 = norm_layer(group_width)
self.dropblock_prob = dropblock_prob
self.radix = radix
self.avd = avd and (stride > 1 or is_first)
self.avd_first = avd_first
if self.avd:
self.avd_layer = nn.AvgPool2d(3, stride, padding=1)
stride = 1
if dropblock_prob > 0.0:
self.dropblock1 = DropBlock2D(dropblock_prob, 3)
if radix == 1:
self.dropblock2 = DropBlock2D(dropblock_prob, 3)
self.dropblock3 = DropBlock2D(dropblock_prob, 3)
if radix >= 1:
self.conv2 = SplAtConv2d(group_width,
group_width,
kernel_size=3,
stride=stride,
padding=dilation,
dilation=dilation,
groups=cardinality,
bias=False,
radix=radix,
rectify=rectified_conv,
rectify_avg=rectify_avg,
norm_layer=norm_layer,
dropblock_prob=dropblock_prob)
elif rectified_conv:
from rfconv import RFConv2d
self.conv2 = RFConv2d(group_width,
group_width,
kernel_size=3,
stride=stride,
padding=dilation,
dilation=dilation,
groups=cardinality,
bias=False,
average_mode=rectify_avg)
self.bn2 = norm_layer(group_width)
else:
self.conv2 = nn.Conv2d(group_width,
group_width,
kernel_size=3,
stride=stride,
padding=dilation,
dilation=dilation,
groups=cardinality,
bias=False)
self.bn2 = norm_layer(group_width)
self.conv3 = nn.Conv2d(group_width,
planes * 4,
kernel_size=1,
bias=False)
self.bn3 = norm_layer(planes * 4)
if last_gamma:
from torch.nn.init import zeros_
zeros_(self.bn3.weight)
self.relu = nn.ReLU(inplace=True)
self.downsample = downsample
self.dilation = dilation
self.stride = stride
def forward(self, x):
residual = x
out = self.conv1(x)
out = self.bn1(out)
if self.dropblock_prob > 0.0:
out = self.dropblock1(out)
out = self.relu(out)
if self.avd and self.avd_first:
out = self.avd_layer(out)
out = self.conv2(out)
if self.radix == 0:
out = self.bn2(out)
if self.dropblock_prob > 0.0:
out = self.dropblock2(out)
out = self.relu(out)
if self.avd and not self.avd_first:
out = self.avd_layer(out)
out = self.conv3(out)
out = self.bn3(out)
if self.dropblock_prob > 0.0:
out = self.dropblock3(out)
if self.downsample is not None:
residual = self.downsample(x)
out += residual
out = self.relu(out)
return out
class ResNet(nn.Module):
"""ResNet Variants
Parameters
----------
block : Block
Class for the residual block. Options are BasicBlockV1, BottleneckV1.
layers : list of int
Numbers of layers in each block
classes : int, default 1000
Number of classification classes.
dilated : bool, default False
Applying dilation strategy to pretrained ResNet yielding a stride-8 model,
typically used in Semantic Segmentation.
norm_layer : object
Normalization layer used in backbone network (default: :class:`mxnet.gluon.nn.BatchNorm`;
for Synchronized Cross-GPU BachNormalization).
Reference:
- He, Kaiming, et al. "Deep residual learning for image recognition." Proceedings of the IEEE conference on computer vision and pattern recognition. 2016.
- Yu, Fisher, and Vladlen Koltun. "Multi-scale context aggregation by dilated convolutions."
"""
# pylint: disable=unused-variable
def __init__(self,
block,
layers,
radix=1,
groups=1,
bottleneck_width=64,
num_classes=1000,
dilated=False,
dilation=1,
deep_stem=False,
stem_width=64,
avg_down=False,
rectified_conv=False,
rectify_avg=False,
avd=False,
avd_first=False,
final_drop=0.0,
dropblock_prob=0,
last_gamma=False,
norm_layer=nn.BatchNorm2d,
freeze_at=0):
self.cardinality = groups
self.bottleneck_width = bottleneck_width
# ResNet-D params
self.inplanes = stem_width * 2 if deep_stem else 64
self.avg_down = avg_down
self.last_gamma = last_gamma
# ResNeSt params
self.radix = radix
self.avd = avd
self.avd_first = avd_first
super(ResNet, self).__init__()
self.rectified_conv = rectified_conv
self.rectify_avg = rectify_avg
if rectified_conv:
from rfconv import RFConv2d
conv_layer = RFConv2d
else:
conv_layer = nn.Conv2d
conv_kwargs = {'average_mode': rectify_avg} if rectified_conv else {}
if deep_stem:
self.conv1 = nn.Sequential(
conv_layer(3,
stem_width,
kernel_size=3,
stride=2,
padding=1,
bias=False,
**conv_kwargs),
norm_layer(stem_width),
nn.ReLU(inplace=True),
conv_layer(stem_width,
stem_width,
kernel_size=3,
stride=1,
padding=1,
bias=False,
**conv_kwargs),
norm_layer(stem_width),
nn.ReLU(inplace=True),
conv_layer(stem_width,
stem_width * 2,
kernel_size=3,
stride=1,
padding=1,
bias=False,
**conv_kwargs),
)
else:
self.conv1 = conv_layer(3,
64,
kernel_size=7,
stride=2,
padding=3,
bias=False,
**conv_kwargs)
self.bn1 = norm_layer(self.inplanes)
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],
norm_layer=norm_layer,
is_first=False)
self.layer2 = self._make_layer(block,
128,
layers[1],
stride=2,
norm_layer=norm_layer)
if dilated or dilation == 4:
self.layer3 = self._make_layer(block,
256,
layers[2],
stride=1,
dilation=2,
norm_layer=norm_layer,
dropblock_prob=dropblock_prob)
elif dilation == 2:
self.layer3 = self._make_layer(block,
256,
layers[2],
stride=2,
dilation=1,
norm_layer=norm_layer,
dropblock_prob=dropblock_prob)
else:
self.layer3 = self._make_layer(block,
256,
layers[2],
stride=2,
norm_layer=norm_layer,
dropblock_prob=dropblock_prob)
self.stem = [self.conv1, self.bn1]
self.stages = [self.layer1, self.layer2, self.layer3]
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, norm_layer):
m.weight.data.fill_(1)
m.bias.data.zero_()
self.freeze(freeze_at)
def _make_layer(self,
block,
planes,
blocks,
stride=1,
dilation=1,
norm_layer=None,
dropblock_prob=0.0,
is_first=True):
downsample = None
if stride != 1 or self.inplanes != planes * block.expansion:
down_layers = []
if self.avg_down:
if dilation == 1:
down_layers.append(
nn.AvgPool2d(kernel_size=stride,
stride=stride,
ceil_mode=True,
count_include_pad=False))
else:
down_layers.append(
nn.AvgPool2d(kernel_size=1,
stride=1,
ceil_mode=True,
count_include_pad=False))
down_layers.append(
nn.Conv2d(self.inplanes,
planes * block.expansion,
kernel_size=1,
stride=1,
bias=False))
else:
down_layers.append(
nn.Conv2d(self.inplanes,
planes * block.expansion,
kernel_size=1,
stride=stride,
bias=False))
down_layers.append(norm_layer(planes * block.expansion))
downsample = nn.Sequential(*down_layers)
layers = []
if dilation == 1 or dilation == 2:
layers.append(
block(self.inplanes,
planes,
stride,
downsample=downsample,
radix=self.radix,
cardinality=self.cardinality,
bottleneck_width=self.bottleneck_width,
avd=self.avd,
avd_first=self.avd_first,
dilation=1,
is_first=is_first,
rectified_conv=self.rectified_conv,
rectify_avg=self.rectify_avg,
norm_layer=norm_layer,
dropblock_prob=dropblock_prob,
last_gamma=self.last_gamma))
elif dilation == 4:
layers.append(
block(self.inplanes,
planes,
stride,
downsample=downsample,
radix=self.radix,
cardinality=self.cardinality,
bottleneck_width=self.bottleneck_width,
avd=self.avd,
avd_first=self.avd_first,
dilation=2,
is_first=is_first,
rectified_conv=self.rectified_conv,
rectify_avg=self.rectify_avg,
norm_layer=norm_layer,
dropblock_prob=dropblock_prob,
last_gamma=self.last_gamma))
else:
raise RuntimeError("=> unknown dilation size: {}".format(dilation))
self.inplanes = planes * block.expansion
for i in range(1, blocks):
layers.append(
block(self.inplanes,
planes,
radix=self.radix,
cardinality=self.cardinality,
bottleneck_width=self.bottleneck_width,
avd=self.avd,
avd_first=self.avd_first,
dilation=dilation,
rectified_conv=self.rectified_conv,
rectify_avg=self.rectify_avg,
norm_layer=norm_layer,
dropblock_prob=dropblock_prob,
last_gamma=self.last_gamma))
return nn.Sequential(*layers)
def forward(self, x):
x = self.conv1(x)
x = self.bn1(x)
x = self.relu(x)
x = self.maxpool(x)
xs = []
x = self.layer1(x)
xs.append(x) # 4X
x = self.layer2(x)
xs.append(x) # 8X
x = self.layer3(x)
xs.append(x) # 16X
# Following STMVOS, we drop stage 5.
xs.append(x) # 16X
return xs
def freeze(self, freeze_at):
if freeze_at >= 1:
for m in self.stem:
freeze_params(m)
for idx, stage in enumerate(self.stages, start=2):
if freeze_at >= idx:
freeze_params(stage)
|