CoordAtt注意力网络结构

最新推荐文章于 2024-04-27 19:33:47 发布

一名CV界的小学生

最新推荐文章于 2024-04-27 19:33:47 发布

阅读量624

点赞数

文章标签：深度学习 pytorch 机器学习 YOLO

本文链接：https://blog.csdn.net/weixin_40132776/article/details/132322406

版权

源码：

import torch
import torch.nn as nn
import math
import torch.nn.functional as F

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()

        out = identity * a_w * a_h

        return out



def CA_onnx_gen():
    conv=CoordAtt(64,64)
    dummy_input = torch.randn(8,64, 128, 128)
    out=conv(dummy_input)
    print(out.shape)
 
    print(conv)
    # conv.load_state_dict(checkpoint)
    conv.eval()
    input_names = ["input"]
    output_names = ["output"]
    torch.onnx.export(conv, dummy_input, "CA.onnx", verbose=True, opset_version=13,input_names=input_names,
                      output_names=output_names)


if __name__=="__main__":
    CA_onnx_gen()

onnx结构：