目錄
1. 前言
什么是注意力機制？
注意力機制（Attention Mechanism）是機器學習中的一種數據處理方法，廣泛應用在自然語言處理、圖像識別及語音識別等各種不同類型的機器學習任務中。
通俗來講：注意力機制就是希望網絡能夠自動學出來圖片或者文字序列中的需要注意的地方。比如人眼在看一幅畫的時候，不會將注意力平等地分配給畫中的所有像素，而是將更多注意力分配給人們關注的地方。
從實現的角度來講：注意力機制通過神經網絡的操作生成一個掩碼mask, mask上的值一個打分，評價當前需要關注的點的評分。
注意力機制可以分為：
通道注意力機制：對通道生成掩碼mask，進行打分，代表是senet, Channel Attention Module
空間注意力機制：對空間進行掩碼的生成，進行打分，代表是Spatial Attention Module
混合域注意力機制：同時對通道注意力和空間注意力進行評價打分，代表的有BAM, CBAM
2.論文摘要
ECCV2018論文地址： https://arxiv.org/abs/1807.06521
文章提出了卷積注意力模塊（CBAM -- Convolutional Block Attention Module ），這是一種用於前饋卷積神經網絡的簡單而有效的注意力模塊。 給定一個中間特征圖，CBAM模塊會沿着兩個獨立的維度（通道和空間）依次推斷注意力圖，然后將注意力圖與輸入特征圖相乘以進行自適應特征優化。 由於CBAM是輕量級的通用模塊，因此可以忽略的該模塊的開銷而將其無縫集成到任何CNN架構中，並且可以與基礎CNN一起進行端到端訓練。 本文通過在ImageNet-1K，MS COCO檢測和VOC 2007檢測數據集上進行的廣泛實驗來驗證CBAM。 實驗表明，使用該模塊在各種模型上，並在分類和檢測性能方面的持續改進，證明了CBAM的廣泛適用性。
在該論文中，作者研究了網絡架構中的注意力，注意力不僅要告訴我們重點關注哪里，還要提高關注點的表示。 目標是通過使用注意機制來增加表現力，關注重要特征並抑制不必要的特征。為了強調空間和通道這兩個維度上的有意義特征，作者依次應用通道和空間注意模塊，來分別在通道和空間維度上學習關注什么、在哪里關注。此外，通過了解要強調或抑制的信息也有助於網絡內的信息流動。
主要網絡架構也很簡單，一個是通道注意力模塊，另一個是空間注意力模塊，CBAM就是先后集成了通道注意力模塊和空間注意力模塊。
Convolutional Block Attention Module (CBAM) 表示卷積模塊的注意力機制模塊，是一種結合了空間（spatial）和通道（channel）的注意力機制模塊。相比於senet只關注通道（channel）的注意力機制可以取得更好的效果。
3.通道注意力機制（Channel Attention Module）
通道注意力機制是將特征圖在空間維度上進行壓縮，得到一個一維矢量后再進行操作。在空間維度上進行壓縮時，不僅考慮到了平均值池化（Average Pooling）還考慮了最大值池化（Max Pooling）。平均池化和最大池化可用來聚合特征映射的空間信息，送到一個共享網絡，壓縮輸入特征圖的空間維數，逐元素求和合並，以產生通道注意力圖。單就一張圖來說，通道注意力，關注的是這張圖上哪些內容是有重要作用的。平均值池化對特征圖上的每一個像素點都有反饋，而最大值池化在進行梯度反向傳播計算時，只有特征圖中響應最大的地方有梯度的反饋。通道注意力機制可以表達為：
代碼實現：
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)
self.fc = nn.Sequential(nn.Conv2d(in_planes, in_planes // 16, 1, bias=False),
nn.ReLU(),
nn.Conv2d(in_planes // 16, in_planes, 1, bias=False))
self.sigmoid = nn.Sigmoid()
def forward(self, x):
avg_out = self.fc(self.avg_pool(x))
max_out = self.fc(self.max_pool(x))
out = avg_out + max_out
return self.sigmoid(out)
應用代碼：
out = self.conv2(out)
out = self.bn2(out) #[1,64,56,56]
ca_tmp = self.ca(out) #[1,64,1,1]
out = self.ca(out) * out #[1,64,56,56]
4.空間注意力機制（Spatial Attention Module）
空間注意力機制是對通道進行壓縮，在通道維度分別進行了平均值池化和最大值池化。MaxPool的操作就是在通道上提取最大值，提取的次數是高乘以寬；AvgPool的操作就是在通道上提取平均值，提取的次數也是是高乘以寬；接着將前面所提取到的特征圖（通道數都為1）合並得到一個2通道的特征圖。
其中， 
為sigmoid操作，77表示卷積核的大小，77的卷積核比3*3的卷積核效果更好。
代碼實現：
class SpatialAttention(nn.Module):
def __init__(self, kernel_size=7):
super(SpatialAttention, self).__init__()
self.conv1 = nn.Conv2d(2, 1, kernel_size, padding=kernel_size//2, 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)
應用代碼：
out = self.conv2(out)
out = self.bn2(out) #[1,64,56,56]
sa_tmp = self.sa(out) #[1,1,56,56]
out = self.sa(out) * out #[1,64,56,56]
通道注意力和空間注意力這兩個模塊能夠以並行或者順序的方式組合在一塊兒，可是做者發現順序組合而且將通道注意力放在前面能夠取得更好的效果。
5.CBAM與ResNet網絡結構組合
6.可視化效果圖
最后，是使用Grad-cam進行了可視化，以來證明CBAM是真正地提取出了積極有效的特征。
7.代碼resnet_cbam.py
最關鍵的部分：
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) #[1,64,56,56]
ca_tmp = self.ca(out) #[1,64,1,1]
sa_tmp = self.sa(out) #[1,1,56,56]
out = self.ca(out) * out #[1,64,56,56]
out = self.sa(out) * out #[1,64,56,56]
if self.downsample is not None:
residual = self.downsample(x)
out += residual
out = self.relu(out)
return out
resnet_cbam.py
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 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)
self.fc = nn.Sequential(nn.Conv2d(in_planes, in_planes // 16, 1, bias=False),
nn.ReLU(),
nn.Conv2d(in_planes // 16, in_planes, 1, bias=False))
self.sigmoid = nn.Sigmoid()
def forward(self, x):
avg_out = self.fc(self.avg_pool(x))
max_out = self.fc(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__()
self.conv1 = nn.Conv2d(2, 1, kernel_size, padding=kernel_size//2, 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)
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) #[1,64,56,56]
ca_tmp = self.ca(out) #[1,64,1,1]
sa_tmp = self.sa(out) #[1,1,56,56]
out = self.ca(out) * out #[1,64,56,56]
out = self.sa(out) * out #[1,64,56,56]
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.AdaptiveAvgPool2d((1, 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
if __name__ == '__main__':
net = resnet18_cbam()
input = torch.randn(1,3,224,224)
out = net(input)
print(out.shape)
a = 0