ASPP改进——结合频率注意力机制，附上代码

import torch
import torch.nn.modules
import torch.nn as nn
from torch.nn import functional as F
from models.Attention_mechanism import FCANet

class FCANetASPP(nn.Module):                       
    def __init__(self, dim_in, dim_out, rate=1, bn_mom=0.1):
        super(CBAM_ASPP, self).__init__()
        self.branch1 = nn.Sequential(
            nn.Conv2d(dim_in, dim_out, 1, 1, padding=0, dilation=rate, bias=True),
            nn.BatchNorm2d(dim_out, momentum=bn_mom),
            nn.ReLU(inplace=True),
        )
        self.branch2 = nn.Sequential(
            nn.Conv2d(dim_in, dim_out, 3, 1, padding=6 * rate, dilation=6 * rate, bias=True),
            nn.BatchNorm2d(dim_out, momentum=bn_mom),
            nn.ReLU(inplace=True),
        )
        self.branch3 = nn.Sequential(
            nn.Conv2d(dim_in, dim_out, 3, 1, padding=12 * rate, dilation=12 * rate, bias=True),
            nn.BatchNorm2d(dim_out, momentum=bn_mom),
            nn.ReLU(inplace=True),
        )
        self.branch4 = nn.Sequential(
            nn.Conv2d(dim_in, dim_out, 3, 1, padding=18 * rate, dilation=18 * rate, bias=True),
            nn.BatchNorm2d(dim_out, momentum=bn_mom),
            nn.ReLU(inplace=True),
        )
        self.branch5_conv = nn.Conv2d(dim_in, dim_out, 1, 1, 0, bias=True)
        self.branch5_bn = nn.BatchNorm2d(dim_out, momentum=bn_mom)
        self.branch5_relu = nn.ReLU(inplace=True)

        self.conv_cat = nn.Sequential(
            nn.Conv2d(dim_out * 5, dim_out, 1, 1, padding=0, bias=True),
            nn.BatchNorm2d(dim_out, momentum=bn_mom),
            nn.ReLU(inplace=True),
        )

        self.FCANet = FCANet(channel=dim_out * 5, dct_h=42, dct_w=80)

    def forward(self, x):
        [b, c, row, col] = x.size()
        conv1x1 = self.branch1(x)
        conv3x3_1 = self.branch2(x)
        conv3x3_2 = self.branch3(x)
        conv3x3_3 = self.branch4(x)
        global_feature = torch.mean(x, 2, True)
        global_feature = torch.mean(global_feature, 3, True)
        global_feature = self.branch5_conv(global_feature)
        global_feature = self.branch5_bn(global_feature)
        global_feature = self.branch5_relu(global_feature)
        global_feature = F.interpolate(global_feature, (row, col), None, 'bilinear', True)

        feature_cat = torch.cat([conv1x1, conv3x3_1, conv3x3_2, conv3x3_3, global_feature], dim=1)
        # 加入频率注意力机制
        fcanet=self.FCANet(feature_cat)
        result=self.conv_cat(fcanet)
        return result

空洞空间卷积池化金字塔（atrous spatial pyramid pooling (ASPP)）通过对于输入的特征以不同的采样率进行采样，即从不同尺度提取输入特征，然后将所获取的特征进行融合，得到最终的特征提取结果，这样不仅可以节约参数和计算力，而且保证了其能够做为即插即用的模块集成到现有的网络架构中去。