CBAM非官方代码及官方代码
非官方代码
两大模块:
class ChannelAttention(nn.Module):
def __init__(self, in_planes, ratio=16):
super(ChannelAttention, self).__init__()
self.avg_pool = nn.AdaptiveAvgPool2d(1)
self.max_pool = nn.AdaptiveMaxPool2d(1)
# 共享权重的MLP
self.fc1 = nn.Conv2d(in_planes, in_planes // 16, 1, bias=False)
self.relu1 = nn.ReLU()
self.fc2 = nn.Conv2d(in_planes // 16, in_planes, 1, bias=False)
self.sigmoid = nn.Sigmoid()
def forward(self, x):
avg_out = self.fc2(self.relu1(self.fc1(self.avg_pool(x))))
max_out = self.fc2(self.relu1(self.fc1(self.max_pool(x))))
out = avg_out + max_out
return self.sigmoid(out)
class SpatialAttention(nn.Module):
def __init__(self, kernel_size=7):
super(SpatialAttention, self).__init__()
assert kernel_size in (3, 7), 'kernel size must be 3 or 7'
padding = 3 if kernel_size == 7 else 1
self.conv1 = nn.Conv2d(2, 1, kernel_size, padding=padding, bias=False)
self.sigmoid = nn.Sigmoid()
def forward(self, x):
avg_out = torch.mean(x, dim=1, keepdim=True)
max_out, _ = torch.max(x, dim=1, keepdim=True)
x = torch.cat([avg_out, max_out], dim=1)
x = self.conv1(x)
return self.sigmoid(x)
应用于resnet中:
import torch
import torch.nn as nn
import math
import torch.utils.model_zoo as model_zoo
__all__ = ['ResNet', 'resnet18_cbam', 'resnet34_cbam', 'resnet50_cbam', 'resnet101_cbam',
'resnet152_cbam']
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.ca = ChannelAttention(planes)
self.sa = SpatialAttention()
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.ca(out) * out
out = self.sa(out) * 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, 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.relu = nn.ReLU(inplace=True)
self.ca = ChannelAttention(planes * 4)
self.sa = SpatialAttention()
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.ca(out) * out
out = self.sa(out) * out
if self.downsample is not None:
residual = self.downsample(x)
out += residual
out = self.relu(out)
return out
class ResNet(nn.Module):
def __init__(self, block, layers, num_classes=1000):
self.inplanes = 64
super(ResNet, self).__init__()
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.AvgPool2d(7, stride=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))
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.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)
x = self.fc(x)
return x
def resnet18_cbam(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:
pretrained_state_dict = model_zoo.load_url(model_urls['resnet18'])
now_state_dict = model.state_dict()
now_state_dict.update(pretrained_state_dict)
model.load_state_dict(now_state_dict)
return model
def resnet34_cbam(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:
pretrained_state_dict = model_zoo.load_url(model_urls['resnet34'])
now_state_dict = model.state_dict()
now_state_dict.update(pretrained_state_dict)
model.load_state_dict(now_state_dict)
return model
def resnet50_cbam(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:
pretrained_state_dict = model_zoo.load_url(model_urls['resnet50'])
now_state_dict = model.state_dict()
now_state_dict.update(pretrained_state_dict)
model.load_state_dict(now_state_dict)
return model
def resnet101_cbam(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:
pretrained_state_dict = model_zoo.load_url(model_urls['resnet101'])
now_state_dict = model.state_dict()
now_state_dict.update(pretrained_state_dict)
model.load_state_dict(now_state_dict)
return model
def resnet152_cbam(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:
pretrained_state_dict = model_zoo.load_url(model_urls['resnet152'])
now_state_dict = model.state_dict()
now_state_dict.update(pretrained_state_dict)
model.load_state_dict(now_state_dict)
return model
官方代码
import torch
import math
import torch.nn as nn
import torch.nn.functional as F
# 基础卷积套餐：conv+bn+relu
class BasicConv(nn.Module):
def __init__(self, in_planes, out_planes, kernel_size, stride=1, padding=0, dilation=1, groups=1, relu=True, bn=True, bias=False):
super(BasicConv, self).__init__()
self.out_channels = out_planes
self.conv = nn.Conv2d(in_planes, out_planes, kernel_size=kernel_size, stride=stride, padding=padding, dilation=dilation, groups=groups, bias=bias)
self.bn = nn.BatchNorm2d(out_planes,eps=1e-5, momentum=0.01, affine=True) if bn else None
self.relu = nn.ReLU() if relu else None
def forward(self, x):
x = self.conv(x)
if self.bn is not None:
x = self.bn(x)
if self.relu is not None:
x = self.relu(x)
return x
# 平铺
class Flatten(nn.Module):
def forward(self, x):
return x.view(x.size(0), -1)
class ChannelGate(nn.Module):
def __init__(self, gate_channels, reduction_ratio=16, pool_types=['avg', 'max']):
super(ChannelGate, self).__init__()
self.gate_channels = gate_channels
# shared MLP 多层感知机
self.mlp = nn.Sequential(
Flatten(),
nn.Linear(gate_channels, gate_channels // reduction_ratio),
nn.ReLU(),
nn.Linear(gate_channels // reduction_ratio, gate_channels)
)
self.pool_types = pool_types
def forward(self, x):
channel_att_sum = None
for pool_type in self.pool_types:
if pool_type=='avg':
avg_pool = F.avg_pool2d( x, (x.size(2), x.size(3)), stride=(x.size(2), x.size(3)))
# avg_pool size: [bs, gate_channels, 1, 1]
channel_att_raw = self.mlp( avg_pool )
elif pool_type=='max':
max_pool = F.max_pool2d( x, (x.size(2), x.size(3)), stride=(x.size(2), x.size(3)))
channel_att_raw = self.mlp( max_pool )
elif pool_type=='lp':
lp_pool = F.lp_pool2d( x, 2, (x.size(2), x.size(3)), stride=(x.size(2), x.size(3)))
channel_att_raw = self.mlp( lp_pool )
elif pool_type=='lse':
# LSE pool only
lse_pool = logsumexp_2d(x)
channel_att_raw = self.mlp( lse_pool )
if channel_att_sum is None:
channel_att_sum = channel_att_raw
else:
# avg_pool + max_pool
channel_att_sum = channel_att_sum + channel_att_raw
scale = F.sigmoid( channel_att_sum ).unsqueeze(2).unsqueeze(3).expand_as(x)
return x * scale
def logsumexp_2d(tensor):
tensor_flatten = tensor.view(tensor.size(0), tensor.size(1), -1)
# [bs, channel, w, h] to [bs, channel, w*h]
s, _ = torch.max(tensor_flatten, dim=2, keepdim=True)
outputs = s + (tensor_flatten - s).exp().sum(dim=2, keepdim=True).log()
return outputs
class ChannelPool(nn.Module):
def forward(self, x):
# 沿着原feature的channel分别做max_pool和avg_pool，然后将两者concat
return torch.cat( (torch.max(x,1)[0].unsqueeze(1), torch.mean(x,1).unsqueeze(1)), dim=1 )
class SpatialGate(nn.Module):
def __init__(self):
super(SpatialGate, self).__init__()
kernel_size = 7
self.compress = ChannelPool()
self.spatial = BasicConv(2, 1, kernel_size, stride=1, padding=(kernel_size-1) // 2, relu=False)
def forward(self, x):
x_compress = self.compress(x)
x_out = self.spatial(x_compress)
scale = F.sigmoid(x_out) # broadcasting
return x * scale
class CBAM(nn.Module):
def __init__(self, gate_channels, reduction_ratio=16, pool_types=['avg', 'max'], no_spatial=False):
super(CBAM, self).__init__()
self.ChannelGate = ChannelGate(gate_channels, reduction_ratio, pool_types)
self.no_spatial=no_spatial
if not no_spatial:
self.SpatialGate = SpatialGate()
def forward(self, x):
x_out = self.ChannelGate(x)
if not self.no_spatial:
x_out = self.SpatialGate(x_out)
return x_out