YoloX引入注意力机制，CIoU、DIoU，DW卷积

本文以Bubbliiing的YoloX代码进行注意力机制的增加，原博文参考以下。

https://blog.youkuaiyun.com/weixin_44791964/article/details/120476949?spm=1001.2014.3001.5502

在此感谢b导的视频，以及对我学习过程中的帮助。

在darknet中引入注意力机制

在darknet.py文件中加入以下代码。

'''注意力模块'''
class ChannelAttention(nn.Module):
    def __init__(self, in_planes, ratio=16):
        super(ChannelAttention, self).__init__()
        self.avg_pool = nn.AdaptiveAvgPool2d(1)
        self.max_pool = nn.AdaptiveMaxPool2d(1)
        self.f1 = nn.Conv2d(in_planes, in_planes // ratio, 1, bias=False)
        self.relu = nn.ReLU()
        self.f2 = nn.Conv2d(in_planes // ratio, in_planes, 1, bias=False)
        self.sigmoid = nn.Sigmoid()
    def forward(self, x):
        avg_out = self.f2(self.relu(self.f1(self.avg_pool(x))))
        max_out = self.f2(self.relu(self.f1(self.max_pool(x))))
        out = self.sigmoid(avg_out + max_out)
        return 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.conv = 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.conv(x)
        return self.sigmoid(x)
class CBAM(nn.Module):
    # CSP Bottleneck with 3 convolutions
    def __init__(self, c1, ratio=16, kernel_size=7):  # ch_in, ch_out, number, shortcut, groups, expansion
        super(CBAM, self).__init__()
        self.channel_attention = ChannelAttention(c1, ratio)
        self.spatial_attention = SpatialAttention(kernel_size)
    def forward(self, x):
        out = self.channel_attention(x) * x
        out = self.spatial_attention(out) * out
        return out

class SE(nn.Module):
    def __init__(self, c1, r=16):
        super(SE, self).__init__()
        self.avgpool = nn.AdaptiveAvgPool2d(1)
        self.l1 = nn.Linear(c1, c1 // r, bias=False)
        self.relu = nn.ReLU(inplace=True)
        self.l2 = nn.Linear(c1 // r, c1, bias=False)
        self.sig = nn.Sigmoid()
    def forward(self, x):
        b, c, _, _ = x.size()
        y = self.avgpool(x).view(b, c)
        y = self.l1(y)
        y = self.relu(y)
        y = self.l2(y)
        y = self.sig(y)
        y = y.view(b, c, 1, 1