Pytorch图像处理注意力机制解析及代码详解

import torch
import torch.nn as nn
import math
class se_block(nn.Module):
    def __init__(self, channel, ratio=16):
        super(se_block, self).__init__()
        self.avg_pool = nn.AdaptiveAvgPool2d(1)
        self.fc = nn.Sequential(
                nn.Linear(channel, channel // ratio, bias=False),
                nn.ReLU(inplace=True),
                nn.Linear(channel // ratio, 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

class ChannelAttention(nn.Module):
    def __init__(self, in_planes, ratio=8):
        super(ChannelAttention, self).__init__()
        self.avg_pool = nn.AdaptiveAvgPool2d(1)
        self.max_pool = nn.AdaptiveMaxPool2d(1)
        # 利用1x1卷积代替全连接
        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)
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)
class cbam_block(nn.Module):
    def __init__(self, channel, ratio=8, kernel_size=7):
        super(cbam_block, self).__init__()
        self.channelattention = ChannelAttention(channel, ratio=ratio)
        self.spatialattention = SpatialAttention(kernel_size=kernel_size)
    def forward(self, x):
        x = x * self.channelattention(x)
        x = x * self.spatialattention(x)
        return x

class eca_block(nn.Module):
    def __init__(self, channel, b=1, gamma=2):
        super(eca_block, self).__init__()
        kernel_size = int(abs((math.log(channel, 2) + b) / gamma))
        kernel_size = kernel_size if kernel_size % 2 else kernel_size + 1
        self.avg_pool = nn.AdaptiveAvgPool2d(1)
        self.conv = nn.Conv1d(1, 1, kernel_size=kernel_size, padding=(kernel_size - 1) // 2, bias=False) 
        self.sigmoid = nn.Sigmoid()
    def forward(self, x):
        y = self.avg_pool(x)
        y = self.conv(y.squeeze(-1).transpose(-1, -2)).transpose(-1, -2).unsqueeze(-1)
        y = self.sigmoid(y)
        return x * y.expand_as(x)

attention_block = [se_block, cbam_block, eca_block]
#---------------------------------------------------#
#   特征层->最后的输出
#---------------------------------------------------#
class YoloBody(nn.Module):
    def __init__(self, anchors_mask, num_classes, phi=0):
        super(YoloBody, self).__init__()
        self.phi            = phi
        self.backbone       = darknet53_tiny(None)
        self.conv_for_P5    = BasicConv(512,256,1)
        self.yolo_headP5    = yolo_head([512, len(anchors_mask[0]) * (5 + num_classes)],256)
        self.upsample       = Upsample(256,128)
        self.yolo_headP4    = yolo_head([256, len(anchors_mask[1]) * (5 + num_classes)],384)
        if 1 <= self.phi and self.phi <= 3:
            self.feat1_att      = attention_block[self.phi - 1](256)
            self.feat2_att      = attention_block[self.phi - 1](512)
            self.upsample_att   = attention_block[self.phi - 1](128)
    def forward(self, x):
        #---------------------------------------------------#
        #   生成CSPdarknet53_tiny的主干模型
        #   feat1的shape为26,26,256
        #   feat2的shape为13,13,512
        #---------------------------------------------------#
        feat1, feat2 = self.backbone(x)
        if 1 <= self.phi and self.phi <= 3:
            feat1 = self.feat1_att(feat1)
            feat2 = self.feat2_att(feat2)
        # 13,13,512 -> 13,13,256
        P5 = self.conv_for_P5(feat2)
        # 13,13,256 -> 13,13,512 -> 13,13,255
        out0 = self.yolo_headP5(P5) 
        # 13,13,256 -> 13,13,128 -> 26,26,128
        P5_Upsample = self.upsample(P5)
        # 26,26,256 + 26,26,128 -> 26,26,384
        if 1 <= self.phi and self.phi <= 3:
            P5_Upsample = self.upsample_att(P5_Upsample)
        P4 = torch.cat([P5_Upsample,feat1],axis=1)
        # 26,26,384 -> 26,26,256 -> 26,26,255
        out1 = self.yolo_headP4(P4)
        return out0, out1