attention注意力机制的一些整理
未完待续。。。
临时想整理一下，原理还未整理。
1通道注意力 channel attention
SE模块
class SELayer(nn.Module):
def __init__(self, channel, reduction=16):
super(SELayer, self).__init__()
self.avg_pool = nn.AdaptiveAvgPool2d(1)
self.fc = nn.Sequential(
nn.Linear(channel, channel // reduction, bias=False),
nn.ReLU(inplace=True),
nn.Linear(channel // reduction, channel, bias=False),
nn.Sigmoid()
)
def forward(self, x):
b, c, _, _ = x.size()
y = self.avg_pool(x).view(b, c)
y = self.fc(y).view(b, c, 1, 1)
return x * y.expand_as(x)
SEResNet-SEBottleneck模块
class SEBottleneck(nn.Module):
expansion = 4
def __init__(self, inplanes, planes, stride=1, downsample=None, reduction=16):
super(SEBottleneck, 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.se = SELayer(planes * 4, reduction)
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.se(out)
if self.downsample is not None:
residual = self.downsample(x)
out += residual
out = self.relu(out)
return out
全连接替换为全卷积的通道注意力
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.fc1 = nn.Conv2d(in_planes, in_planes // ratio, 1, bias=False)
self.relu1 = nn.ReLU()
self.fc2 = nn.Conv2d(in_planes // ratio, 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)
2空间注意力 Spatial attention
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) # 7,3 3,1
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)
3坐标注意力 Coordinate attention
class h_sigmoid(nn.Module):
def __init__(self, inplace=True):
super(h_sigmoid, self).__init__()
self.relu = nn.ReLU6(inplace=inplace)
def forward(self, x):
return self.relu(x + 3) / 6
class h_swish(nn.Module):
def __init__(self, inplace=True):
super(h_swish, self).__init__()
self.sigmoid = h_sigmoid(inplace=inplace)
def forward(self, x):
return x * self.sigmoid(x)
class CoordAtt(nn.Module):
def __init__(self, inp, oup, reduction=32):
super(CoordAtt, self).__init__()
self.pool_h = nn.AdaptiveAvgPool2d((None, 1))
self.pool_w = nn.AdaptiveAvgPool2d((1, None))
mip = max(8, inp // reduction)
self.conv1 = nn.Conv2d(inp, mip, kernel_size=1, stride=1, padding=0)
self.bn1 = nn.BatchNorm2d(mip)
self.act = h_swish()
self.conv_h = nn.Conv2d(mip, oup, kernel_size=1, stride=1, padding=0)
self.conv_w = nn.Conv2d(mip, oup, kernel_size=1, stride=1, padding=0)
def forward(self, x):
identity = x
n, c, h, w = x.size()
x_h = self.pool_h(x)
x_w = self.pool_w(x).permute(0, 1, 3, 2)
y = torch.cat([x_h, x_w], dim=2)
y = self.conv1(y)
y = self.bn1(y)
y = self.act(y)
x_h, x_w = torch.split(y, [h, w], dim=2)
x_w = x_w.permute(0, 1, 3, 2)
a_h = self.conv_h(x_h).sigmoid()
a_w = self.conv_w(x_w).sigmoid()
# 如果下面这个原论文代码用不了的话，可以换成另一个试试
out = identity * a_w * a_h
# out = a_h.expand_as(x) * a_w.expand_as(x) * identity
return out
4自注意力 self attention
Non -Local
class _NonLocalBlockND(nn.Module):
def __init__(self, in_channels, inter_channels=None, dimension=3, sub_sample=True, bn_layer=True):
"""
:param in_channels:
:param inter_channels:
:param dimension:
:param sub_sample:
:param bn_layer:
"""
super(_NonLocalBlockND, self).__init__()
assert dimension in [1, 2, 3]
self.dimension = dimension
self.sub_sample = sub_sample
self.in_channels = in_channels
self.inter_channels = inter_channels
if self.inter_channels is None:
self.inter_channels = in_channels // 2
if self.inter_channels == 0:
self.inter_channels = 1
if dimension == 3:
conv_nd = nn.Conv3d
max_pool_layer = nn.MaxPool3d(kernel_size=(1, 2, 2))
bn = nn.BatchNorm3d
elif dimension == 2:
conv_nd = nn.Conv2d
max_pool_layer = nn.MaxPool2d(kernel_size=(2, 2))
bn = nn.BatchNorm2d
else:
conv_nd = nn.Conv1d
max_pool_layer = nn.MaxPool1d(kernel_size=(2))
bn = nn.BatchNorm1d
self.g = conv_nd(in_channels=self.in_channels, out_channels=self.inter_channels,
kernel_size=1, stride=1, padding=0)
if bn_layer:
self.W = nn.Sequential(
conv_nd(in_channels=self.inter_channels, out_channels=self.in_channels,
kernel_size=1, stride=1, padding=0),
bn(self.in_channels)
)
nn.init.constant_(self.W[1].weight, 0)
nn.init.constant_(self.W[1].bias, 0)
else:
self.W = conv_nd(in_channels=self.inter_channels, out_channels=self.in_channels,
kernel_size=1, stride=1, padding=0)
nn.init.constant_(self.W.weight, 0)
nn.init.constant_(self.W.bias, 0)
self.theta = conv_nd(in_channels=self.in_channels, out_channels=self.inter_channels,
kernel_size=1, stride=1, padding=0)
self.phi = conv_nd(in_channels=self.in_channels, out_channels=self.inter_channels,
kernel_size=1, stride=1, padding=0)
if sub_sample:
self.g = nn.Sequential(self.g, max_pool_layer)
self.phi = nn.Sequential(self.phi, max_pool_layer)
def forward(self, x, return_nl_map=False):
"""
:param x: (b, c, t, h, w)
:param return_nl_map: if True return z, nl_map, else only return z.
:return:
"""
batch_size = x.size(0)
g_x = self.g(x).view(batch_size, self.inter_channels, -1)
g_x = g_x.permute(0, 2, 1)
# 相比于gaussian ,embedded gaussian增加了1*1卷积层，将输入的通道转为inter_channels
theta_x = self.theta(x).view(batch_size, self.inter_channels, -1)
theta_x = theta_x.permute(0, 2, 1)
phi_x = self.phi(x).view(batch_size, self.inter_channels, -1)
f = torch.matmul(theta_x, phi_x)
f_div_C = F.softmax(f, dim=-1)
y = torch.matmul(f_div_C, g_x)
y = y.permute(0, 2, 1).contiguous()
y = y.view(batch_size, self.inter_channels, *x.size()[2:])
W_y = self.W(y)
z = W_y + x
if return_nl_map:
return z, f_div_C
return z
像素注意力
pass
5组合
CBAM
class CBAM(nn.Module):
def __init__(self, in_planes, ratio=16, kernel_size=7):
super(CBAM, self).__init__()
self.ca = ChannelAttention(in_planes, ratio)
self.sa = SpatialAttention(kernel_size)
def forward(self, x):
out = x * self.ca(x)
result = out * self.sa(out)
return result