yolov5（ODConv改进）

最新推荐文章于 2024-12-27 22:39:54 发布

「已注销」

最新推荐文章于 2024-12-27 22:39:54 发布

阅读量3.2k

点赞数 21

文章标签：算法

本文链接：https://blog.youkuaiyun.com/qq_53198408/article/details/130196390

版权


import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.autograd

class ODConv(nn.Sequential):
    def __init__(self, in_planes, out_planes, kernel_size=3, stride=1, groups=1, norm_layer=nn.BatchNorm2d,
                 reduction=0.0625, kernel_num=1):
        padding = (kernel_size - 1) // 2
        super(ODConv, self).__init__(
            ODConv2d(in_planes, out_planes, kernel_size, stride, padding, groups=groups,
                     reduction=reduction, kernel_num=kernel_num),
            norm_layer(out_planes),
            nn.SiLU()
        )

class Attention(nn.Module):
    def __init__(self, in_planes, out_planes, kernel_size, 
    groups=1, 
    reduction=0.0625, 
    kernel_num=4, 
    min_channel=16):
        super(Attention, self).__init__()
        attention_channel = max(int(in_planes * reduction), min_channel)
        self.kernel_size = kernel_size
        self.kernel_num = kernel_num
        self.temperature = 1.0

        self.avgpool = nn.AdaptiveAvgPool2d(1)
        self.fc = nn.Conv2d(in_planes, attention_channel, 1, bias=False)
        self.bn = nn.BatchNorm2d(attention_channel)
        self.relu = nn.ReLU(inplace=True)

        self.channel_fc = nn.Conv2d(attention_channel, in_planes, 1, bias=True)
        self.func_channel = self.get_channel_attention

        if in_planes == groups and in_planes == out_planes:  # depth-wise convolution
            self.func_filter = self.skip
        else:
            self.filter_fc = nn.Conv2d(attention_channel, out_planes, 1, bias=True)
            self.func_filter = self.get_filter_attention

        if kernel_size == 1:  # point-wise convolution
            self.func_spatial = self.skip
        else:
            self.spatial_fc = nn.Conv2d(attention_channel, kernel_size * kernel_size, 1, bias=True)
            self.func_spatial = self.get_spatial_attention

        if kernel_num == 1:
            self.func_kernel = self.skip
        else:
            self.kernel_fc = nn.Conv2d(attention_channel, kernel_num, 1, bias=True)
            self.func_kernel = self.get_kernel_attention
        self.bn_1 = nn.LayerNorm(