yolov5cbs和cbl

根据提供的引用内容，yolov5cbs和cbl是YOLOv5中的两个模块。

yolov5cbs是YOLOv5中的一个模块，它是由Conv、BN和SiLU三个基本模块组成的。其中，Conv是卷积层，BN是批量归一化层，SiLU是激活函数。yolov5cbs模块的作用是对输入数据进行特征提取和处理。

cbl是YOLOv5中的另一个模块，它是由Conv、BN和LeakyReLU三个基本模块组成的。其中，Conv是卷积层，BN是批量归一化层，LeakyReLU是激活函数。cbl模块的作用是对输入数据进行特征提取和处理。

下面是一个yolov5cbs和cbl的示例代码：

import torch.nn as nn

# yolov5cbs模块
class YOLOv5CSPBlock(nn.Module):
    def __init__(self, in_channels, out_channels, hidden_channels=None, residual_activation=nn.Identity()):
        super().__init__()
        if hidden_channels is None:
            hidden_channels = out_channels
        self.conv1 = nn.Conv2d(in_channels, hidden_channels, 1, bias=False)
        self.bn1 = nn.BatchNorm2d(hidden_channels)
        self.act = nn.SiLU(inplace=True)
        self.conv2 = nn.Conv2d(hidden_channels, out_channels, 3, padding=1, bias=False)
        self.bn2 = nn.BatchNorm2d(out_channels)
        self.res_conv = nn.Conv2d(in_channels, out_channels, 1)
        self.res_bn = nn.BatchNorm2d(out_channels)
        self.res_act = residual_activation

    def forward(self, x):
        y = self.conv1(x)
        y = self.bn1(y)
        y = self.act(y)
        y = self.conv2(y)
        y = self.bn2(y)
        res = self.res_conv(x)
        res = self.res_bn(res)
        res = self.res_act(res)
        return self.act(res + y)

# cbl模块
class CBL(nn.Module):
    def __init__(self, in_channels, out_channels, kernel_size, stride, padding, groups=1):
        super().__init__()
        self.conv = nn.Conv2d(in_channels, out_channels, kernel_size, stride, padding, groups=groups, bias=False)
        self.bn = nn.BatchNorm2d(out_channels)
        self.act = nn.LeakyReLU(0.1, inplace=True)

    def forward(self, x):
        x = self.conv(x)
        x = self.bn(x)
        x = self.act(x)
        return x