Coordinate Attention +resnet+pytorch实现

# CA (coordinate attention)

import torch
import torch.nn as nn
import math
import torch.nn.functional as F
from torchsummary import summary
import torch.utils.model_zoo as model_zoo

__all__ = ['ResNet', 'resnet18', 'resnet34', 'resnet50', 'resnet101',
           'resnet152']

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',
}
import torch
import torch.nn as nn


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 CoordAttention(nn.Module):

    def __init__(self, in_channels, out_channels, reduction=32):
        super(CoordAttention, self).__init__()
        self.pool_w, self.pool_h = nn.AdaptiveAvgPool2d((1, None)), nn.AdaptiveAvgPool2d((None, 1))
        temp_c = max(8, in_channels // reduction)
        self.conv1 = nn.Conv2d(in_channels, temp_c, kernel_size=1, stride=1, padding=0)

        self.bn1 = nn.BatchNorm2d(temp_c)
        self.act1 = h_swish()

        self.conv2 = nn.Conv2d(temp_c, out_channels, kernel_size=1, stride=