甘肃省酒泉市做网站公司,网络,有免费查企业的软件吗,wordpress 外贸主题一、SEBlock(通道注意力机制)
先在H*W维度进行压缩#xff0c;全局平均池化将每个通道平均为一个值。 #xff08;B, C, H, W#xff09;---- (B, C, 1, 1)
利用各channel维度的相关性计算权重 (B, C, 1, 1) --- (B, C//K, 1, 1) --- (B, C, 1, 1) --- sigmoid
与原特征相…一、SEBlock(通道注意力机制)
先在H*W维度进行压缩全局平均池化将每个通道平均为一个值。 B, C, H, W---- (B, C, 1, 1)
利用各channel维度的相关性计算权重 (B, C, 1, 1) --- (B, C//K, 1, 1) --- (B, C, 1, 1) --- sigmoid
与原特征相乘得到加权后的。
import torch
import torch.nn as nnclass SELayer(nn.Module):def __init__(self, channel, reduction 4):super(SELayer, self).__init__()self.avg_pool nn.AdaptiveAvgPool2d(1) //自适应全局池化只需要给出池化后特征图大小self.fc1 nn.Sequential(nn.Conv2d(channel, channel//reduction, 1, bias False),nn.ReLu(implace True),nn.Conv2d(channel//reduction, channel, 1, bias False),nn.sigmoid())def forward(self, x):y self.avg_pool(x)y_out self.fc1(y)return x * y
二、CBAM(通道注意力空间注意力机制)
CBAM里面既有通道注意力机制也有空间注意力机制。 通道注意力同SE的大致相同但额外加入了全局最大池化与全局平均池化并行。
空间注意力机制先在channel维度进行最大池化和均值池化然后在channel维度合并MLP进行特征交融。最终和原始特征相乘。
import torch
import torch.nn as nnclass ChannelAttention(nn.Module):def __init__(self, channel, rate 4):super(ChannelAttention, self).__init__()self.avg_pool nn.AdaptiveAvgPool2d(1)self.max_pool nn.AdaptiveMaxPool2d(1)self.fc1 nn.Sequential(nn.Conv2d(channel, channel//rate, 1, bias False)nn.ReLu(implace True)nn.Conv2d(channel//rate, channel, 1, bias False) )self.sig nn.sigmoid()def forward(self, x):avg sefl.avg_pool(x)avg_feature self.fc1(avg)max self.max_pool(x)max_feature self.fc1(max)out max_feature avg_featureout self.sig(out)return x * out import torch
import torch.nn as nnclass SpatialAttention(nn.Module):def __init__(self):super(SpatialAttention, self).__init__()//(B,C,H,W)---(B,1,H,W)---(B,2,H,W)---(B,1,H,W)self.conv1 nn.Conv2d(2, 1, kernel_size 3, padding 1, bias False)self.sigmoid nn.sigmoid()def forward(self, x):mean_f torch.mean(x, dim 1, keepdim True)max_f torch.max(x, dim 1, keepdim True)cat torch.cat([mean_f, max_f], dim 1)out self.conv1(cat)return x*self.sigmod(out) 三、transformer里的注意力机制
Scaled Dot-Product Attention
该注意力机制的输入是QKV。
1.先Q,K相乘。
2.scale
3.softmax
4.求output import torch
import torch.nn as nnclass ScaledDotProductAttention(nn.Module):def __init__(self, scale):super(ScaledDotProductAttention, self)self.scale scaleself.softmax nn.softmax(dim 2)def forward(self, q, k, v):u torch.bmm(q, k.transpose(1, 2))u u / scaleattn self.softmax(u)output torch.bmm(attn, v)return outputscale np.power(d_k, 0.5) //缩放系数为K维度的根号。
//Q (B, n_q, d_q) , K (B, n_k, d_k) V (B, n_v, d_v),Q与K的特征维度一定要一样。KV的个数一定要一样。 MultiHeadAttention
将QKVchannel维度转换为n*C的形式,相当于分成n份分别做注意力机制。
1.QKV单头变多头 channel ----- n * new_channel通过linear变换,然后把head和batch先合并
2.求单头注意力机制输出
3.维度拆分 将最终的head和channel合并。
4.linear得到最终输出维度 import torch
import torch.nn as nnclass MultiHeadAttention(nn.Module):def __init__(self, n_head, d_k, d_k_, d_v, d_v_, d_o):super(MultiHeadAttention, self)self.n_head n_headself.d_k d_kself.d_v d_vself.fc_k nn.Linear(d_k_, n_head * d_k)self.fc_v nn.Linear(d_v_, n_head * d_v)self.fc_q nn.Linear(d_k_, n_head * d_k)self.attention ScaledDotProductAttention(scalenp.power(d_k, 0.5))self.fc_o nn.Linear(n_head * d_v, d_0)def forward(self, q, k, v):batch, n_q, d_q_ q.size()batch, n_k, d_k_ k.size()batch, n_v, d_v_ v.size()q self.fc_q(q)k self.fc_k(k)v self.fc_v(v)q q.view(batch, n_q, n_head, d_q).permute(2, 0, 1, 3).contiguous().view(-1, n_q, d_q)k k.view(batch, n_k, n_head, d_k).permute(2, 0, 1, 3).contiguous().view(-1, n_k, d_k)v v.view(batch, n_v, n_head, d_v).permute(2, 0, 1, 3).contiguous().view(-1. n_v, d_v) output self.attention(q, k, v)output output.view(n_head, batch, n_q, d_v).permute(1, 2, 0, 3).contiguous().view(batch, n_q, -1)output self.fc_0(output)return output
