File size: 10,692 Bytes
6fc43ab |
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 |
"""
Created on Sat Nov 21 10:49:39 2021
@author: cxue2
"""
import torch.nn as nn
__all__ = ['r3d_18', 'mc3_18', 'r2plus1d_18']
class Conv3DSimple(nn.Conv3d):
def __init__(self,
in_planes,
out_planes,
midplanes=None,
stride=1,
padding=1):
super(Conv3DSimple, self).__init__(
in_channels=in_planes,
out_channels=out_planes,
kernel_size=(3, 3, 3),
stride=stride,
padding=padding,
bias=False)
@staticmethod
def get_downsample_stride(stride):
return stride, stride, stride
class Conv2Plus1D(nn.Sequential):
def __init__(self,
in_planes,
out_planes,
midplanes,
stride=1,
padding=1):
super(Conv2Plus1D, self).__init__(
nn.Conv3d(in_planes, midplanes, kernel_size=(1, 3, 3),
stride=(1, stride, stride), padding=(0, padding, padding),
bias=False),
nn.BatchNorm3d(midplanes),
nn.ReLU(inplace=True),
nn.Conv3d(midplanes, out_planes, kernel_size=(3, 1, 1),
stride=(stride, 1, 1), padding=(padding, 0, 0),
bias=False))
@staticmethod
def get_downsample_stride(stride):
return stride, stride, stride
class Conv3DNoTemporal(nn.Conv3d):
def __init__(self,
in_planes,
out_planes,
midplanes=None,
stride=1,
padding=1):
super(Conv3DNoTemporal, self).__init__(
in_channels=in_planes,
out_channels=out_planes,
kernel_size=(1, 3, 3),
stride=(1, stride, stride),
padding=(0, padding, padding),
bias=False)
@staticmethod
def get_downsample_stride(stride):
return 1, stride, stride
class BasicBlock(nn.Module):
expansion = 1
def __init__(self, inplanes, planes, conv_builder, stride=1, downsample=None):
midplanes = (inplanes * planes * 3 * 3 * 3) // (inplanes * 3 * 3 + 3 * planes)
super(BasicBlock, self).__init__()
self.conv1 = nn.Sequential(
conv_builder(inplanes, planes, midplanes, stride),
nn.BatchNorm3d(planes),
nn.ReLU(inplace=True)
)
self.conv2 = nn.Sequential(
conv_builder(planes, planes, midplanes),
nn.BatchNorm3d(planes)
)
self.relu = nn.ReLU(inplace=True)
self.downsample = downsample
self.stride = stride
def forward(self, x):
residual = x
out = self.conv1(x)
out = self.conv2(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, conv_builder, stride=1, downsample=None):
super(Bottleneck, self).__init__()
midplanes = (inplanes * planes * 3 * 3 * 3) // (inplanes * 3 * 3 + 3 * planes)
# 1x1x1
self.conv1 = nn.Sequential(
nn.Conv3d(inplanes, planes, kernel_size=1, bias=False),
nn.BatchNorm3d(planes),
nn.ReLU(inplace=True)
)
# Second kernel
self.conv2 = nn.Sequential(
conv_builder(planes, planes, midplanes, stride),
nn.BatchNorm3d(planes),
nn.ReLU(inplace=True)
)
# 1x1x1
self.conv3 = nn.Sequential(
nn.Conv3d(planes, planes * self.expansion, kernel_size=1, bias=False),
nn.BatchNorm3d(planes * self.expansion)
)
self.relu = nn.ReLU(inplace=True)
self.downsample = downsample
self.stride = stride
def forward(self, x):
residual = x
out = self.conv1(x)
out = self.conv2(out)
out = self.conv3(out)
if self.downsample is not None:
residual = self.downsample(x)
out += residual
out = self.relu(out)
return out
class BasicStem(nn.Sequential):
"""The default conv-batchnorm-relu stem
"""
def __init__(self):
super(BasicStem, self).__init__(
nn.Conv3d(1, 64, kernel_size=(7, 7, 7), stride=(2, 2, 2),
padding=(3, 3, 3), bias=False),
nn.BatchNorm3d(64),
nn.ReLU(inplace=True))
class R2Plus1dStem(nn.Sequential):
"""R(2+1)D stem is different than the default one as it uses separated 3D convolution
"""
def __init__(self):
super(R2Plus1dStem, self).__init__(
nn.Conv3d(3, 45, kernel_size=(1, 7, 7),
stride=(1, 2, 2), padding=(0, 3, 3),
bias=False),
nn.BatchNorm3d(45),
nn.ReLU(inplace=True),
nn.Conv3d(45, 64, kernel_size=(3, 1, 1),
stride=(1, 1, 1), padding=(1, 0, 0),
bias=False),
nn.BatchNorm3d(64),
nn.ReLU(inplace=True))
class VideoResNet(nn.Module):
def __init__(self, block, conv_makers, layers,
stem, num_classes=16,
zero_init_residual=False):
"""Generic resnet video generator.
Args:
block (nn.Module): resnet building block
conv_makers (list(functions)): generator function for each layer
layers (List[int]): number of blocks per layer
stem (nn.Module, optional): Resnet stem, if None, defaults to conv-bn-relu. Defaults to None.
num_classes (int, optional): Dimension of the final FC layer. Defaults to 400.
zero_init_residual (bool, optional): Zero init bottleneck residual BN. Defaults to False.
"""
super(VideoResNet, self).__init__()
self.inplanes = 64
self.stem = stem()
self.layer1 = self._make_layer(block, conv_makers[0], 64, layers[0], stride=1)
self.layer2 = self._make_layer(block, conv_makers[1], 128, layers[1], stride=2)
self.layer3 = self._make_layer(block, conv_makers[2], 192, layers[2], stride=2)
self.layer4 = self._make_layer(block, conv_makers[3], 256, layers[3], stride=2)
self.avgpool = nn.AdaptiveAvgPool3d((1, 1, 1))
self.fc = nn.Linear(256 * block.expansion, num_classes)
# init weights
self._initialize_weights()
if zero_init_residual:
for m in self.modules():
if isinstance(m, Bottleneck):
nn.init.constant_(m.bn3.weight, 0)
def forward(self, x):
x = self.stem(x)
x = self.layer1(x)
x = self.layer2(x)
x = self.layer3(x)
x = self.layer4(x)
x = self.avgpool(x)
# Flatten the layer to fc
x = x.flatten(1)
x = self.fc(x)
return x
def _make_layer(self, block, conv_builder, planes, blocks, stride=1):
downsample = None
if stride != 1 or self.inplanes != planes * block.expansion:
ds_stride = conv_builder.get_downsample_stride(stride)
downsample = nn.Sequential(
nn.Conv3d(self.inplanes, planes * block.expansion,
kernel_size=1, stride=ds_stride, bias=False),
nn.BatchNorm3d(planes * block.expansion)
)
layers = []
layers.append(block(self.inplanes, planes, conv_builder, stride, downsample))
self.inplanes = planes * block.expansion
for i in range(1, blocks):
layers.append(block(self.inplanes, planes, conv_builder))
return nn.Sequential(*layers)
def _initialize_weights(self):
for m in self.modules():
if isinstance(m, nn.Conv3d):
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.BatchNorm3d):
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 _video_resnet(arch, pretrained=False, progress=True, **kwargs):
model = VideoResNet(**kwargs)
return model
def r3d_18(pretrained=False, progress=True, **kwargs):
"""Construct 18 layer Resnet3D model as in
https://arxiv.org/abs/1711.11248
Args:
pretrained (bool): If True, returns a model pre-trained on Kinetics-400
progress (bool): If True, displays a progress bar of the download to stderr
Returns:
nn.Module: R3D-18 network
"""
return _video_resnet('r3d_18',
pretrained, progress,
block=BasicBlock,
conv_makers=[Conv3DSimple] * 4,
layers=[2, 2, 2, 2],
stem=BasicStem, **kwargs)
def mc3_18(pretrained=False, progress=True, **kwargs):
"""Constructor for 18 layer Mixed Convolution network as in
https://arxiv.org/abs/1711.11248
Args:
pretrained (bool): If True, returns a model pre-trained on Kinetics-400
progress (bool): If True, displays a progress bar of the download to stderr
Returns:
nn.Module: MC3 Network definition
"""
return _video_resnet('mc3_18',
pretrained, progress,
block=BasicBlock,
conv_makers=[Conv3DSimple] + [Conv3DNoTemporal] * 3,
layers=[2, 2, 2, 2],
stem=BasicStem, **kwargs)
def r2plus1d_18(pretrained=False, progress=True, **kwargs):
"""Constructor for the 18 layer deep R(2+1)D network as in
https://arxiv.org/abs/1711.11248
Args:
pretrained (bool): If True, returns a model pre-trained on Kinetics-400
progress (bool): If True, displays a progress bar of the download to stderr
Returns:
nn.Module: R(2+1)D-18 network
"""
return _video_resnet('r2plus1d_18',
pretrained, progress,
block=BasicBlock,
conv_makers=[Conv2Plus1D] * 4,
layers=[2, 2, 2, 2],
stem=R2Plus1dStem, **kwargs)
if __name__ == '__main__':
import torch
net = r3d_18().to(0)
x = torch.zeros(3, 1, 182, 218, 182).to(0)
print(net(x).shape)
print(net) |