"""Resnet model combined with Swish activation function"""
# Source: https://github.com/tzing/resnet-swish
import torch.nn as nn
import torch
import math
__all__ = ['ResNet_swish', 'ResNet18_swish', 'ResNet34_swish', 'ResNet50_swish', 'ResNet101_swish', 'ResNet152_swish']
class Swish(nn.Module):
def __init__(self, inplace=False):
super().__init__()
self.inplace = True
def forward(self, x):
if self.inplace:
x.mul_(torch.sigmoid(x))
return x
else:
return x * torch.sigmoid(x)
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.act = Swish(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.act(out)
out = self.conv2(out)
out = self.bn2(out)
if self.downsample is not None:
residual = self.downsample(x)
out += residual
out = self.act(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, bias=False)
self.bn1 = nn.BatchNorm2d(planes)
self.conv2 = nn.Conv2d(planes, planes, kernel_size=3, stride=stride,
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.act = Swish(inplace=True)
self.downsample = downsample
self.stride = stride
def forward(self, x):
residual = x
out = self.conv1(x)
out = self.bn1(out)
out = self.act(out)
out = self.conv2(out)
out = self.bn2(out)
out = self.act(out)
out = self.conv3(out)
out = self.bn3(out)
if self.downsample is not None:
residual = self.downsample(x)
out += residual
out = self.act(out)
return out
[docs]class ResNet_swish(nn.Module):
def __init__(self, block, layers, num_classes=1000):
self.inplanes = 64
super(ResNet_swish, self).__init__()
self.conv1 = nn.Conv2d(3, 64, kernel_size=7, stride=2, padding=3,
bias=False)
self.bn1 = nn.BatchNorm2d(64)
self.act = Swish(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.AvgPool2d(7)
self.last_linear = 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.act(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.last_linear(x)
return x
[docs]def ResNet18_swish(pretrained=False, **kwargs):
"""Constructs a ResNet-18 model. Not pretrained."""
model = ResNet_swish(BasicBlock, [2, 2, 2, 2], **kwargs)
if pretrained:
raise NotImplementedError()
return model
[docs]def ResNet34_swish(pretrained=False, **kwargs):
"""Constructs a ResNet-34 model. Not pretrained."""
model = ResNet_swish(BasicBlock, [3, 4, 6, 3], **kwargs)
if pretrained:
raise NotImplementedError()
return model
[docs]def ResNet50_swish(pretrained=False, **kwargs):
"""Constructs a ResNet-50 model. Not pretrained."""
model = ResNet_swish(Bottleneck, [3, 4, 6, 3], **kwargs)
if pretrained:
raise NotImplementedError()
return model
[docs]def ResNet101_swish(pretrained=False, **kwargs):
"""Constructs a ResNet-101 model. Not pretrained."""
model = ResNet_swish(Bottleneck, [3, 4, 23, 3], **kwargs)
if pretrained:
raise NotImplementedError()
return model
[docs]def ResNet152_swish(pretrained=False, **kwargs):
"""Constructs a ResNet-152 model. Not pretrained."""
model = ResNet_swish(Bottleneck, [3, 8, 36, 3], **kwargs)
if pretrained:
raise NotImplementedError()
return model