| """
|
| Training recipe:
|
| https://github.com/NVIDIA/DeepLearningExamples/blob/master/PyTorch/Classification/ConvNets/se-resnext101-32x4d/README.md
|
|
|
| """
|
|
|
|
|
| import torch.nn as nn
|
| import math
|
| import torch.utils.model_zoo as model_zoo
|
|
|
| __all__ = ['SeResNeXt', 'se_resnext50', 'se_resnext101', 'se_resnext152', 'Selayer']
|
|
|
| model_urls = {
|
| 'se_resnext50': '',
|
| 'se_resnext101' : '',
|
| 'se_resnext152' : '',
|
| }
|
|
|
| class Selayer(nn.Module):
|
|
|
| def __init__(self, inplanes):
|
| super(Selayer, self).__init__()
|
| self.global_avgpool = nn.AdaptiveAvgPool2d(1)
|
| self.conv1 = nn.Conv2d(inplanes, inplanes / 16, kernel_size=1, stride=1)
|
| self.conv2 = nn.Conv2d(inplanes / 16, inplanes, kernel_size=1, stride=1)
|
| self.relu = nn.ReLU(inplace=True)
|
| self.sigmoid = nn.Sigmoid()
|
|
|
| def forward(self, x):
|
|
|
| out = self.global_avgpool(x)
|
|
|
| out = self.conv1(out)
|
| out = self.relu(out)
|
|
|
| out = self.conv2(out)
|
| out = self.sigmoid(out)
|
|
|
| return x * out
|
|
|
|
|
| class Bottleneck(nn.Module):
|
| expansion = 4
|
|
|
| def __init__(self, inplanes, planes, cardinality, stride=1, downsample=None):
|
| super(Bottleneck, self).__init__()
|
| self.conv1 = nn.Conv2d(inplanes, planes * 2, kernel_size=1, bias=False)
|
| self.bn1 = nn.BatchNorm2d(planes * 2)
|
|
|
| self.conv2 = nn.Conv2d(planes * 2, planes * 2, kernel_size=3, stride=stride,
|
| padding=1, groups=cardinality, bias=False)
|
| self.bn2 = nn.BatchNorm2d(planes * 2)
|
|
|
| self.conv3 = nn.Conv2d(planes * 2, planes * 4, kernel_size=1, bias=False)
|
| self.bn3 = nn.BatchNorm2d(planes * 4)
|
|
|
| self.selayer = Selayer(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)
|
|
|
| out = self.selayer(out)
|
|
|
| if self.downsample is not None:
|
| residual = self.downsample(x)
|
|
|
| out += residual
|
| out = self.relu(out)
|
|
|
| return out
|
|
|
|
|
| class SeResNeXt(nn.Module):
|
|
|
| def __init__(self, block, layers, cardinality=32, num_classes=1000):
|
| super(SeResNeXt, self).__init__()
|
| self.cardinality = cardinality
|
| self.inplanes = 64
|
|
|
| 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=1)
|
|
|
| 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=2)
|
|
|
| self.avgpool = nn.AdaptiveAvgPool2d(1)
|
| 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))
|
| if m.bias is not None:
|
| m.bias.data.zero_()
|
| 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, self.cardinality, stride, downsample))
|
| self.inplanes = planes * block.expansion
|
| for i in range(1, blocks):
|
| layers.append(block(self.inplanes, planes, self.cardinality))
|
|
|
| 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)
|
|
|
| return self.fc(x)
|
|
|
|
|
| def se_resnext50(pretrained=True, **kwargs):
|
| """Constructs a SeResNeXt-50 model.
|
|
|
| Args:
|
| pretrained (bool): If True, returns a model pre-trained on ImageNet
|
| """
|
| model = SeResNeXt(Bottleneck, [3, 4, 6, 3], **kwargs)
|
| if pretrained:
|
| model.load_state_dict(model_zoo.load_url(model_urls['se_resnext50']))
|
| return model
|
|
|
|
|
| def se_resnext101(pretrained = True, **kwargs):
|
| """Constructs a SeResNeXt-101 model.
|
|
|
| Args:
|
| pretrained (bool): If True, returns a model pre-trained on ImageNet
|
| """
|
| model = SeResNeXt(Bottleneck, [3, 4, 23, 3], **kwargs)
|
| if pretrained:
|
| model.load_state_dict(model_zoo.load_url(model_urls['se_resnext101']))
|
| return model
|
|
|
|
|
| def se_resnext152(pretrained=True, **kwargs):
|
| """Constructs a SeResNeXt-152 model.
|
|
|
| Args:
|
| pretrained (bool): If True, returns a model pre-trained on ImageNet
|
| """
|
| model = SeResNeXt(Bottleneck, [3, 8, 36, 3], **kwargs)
|
| if pretrained:
|
| model.load_state_dict(model_zoo.load_url(model_urls['se_resnext152']))
|
| return model |
