pytorch实现yolov4CSPDarknet53主干网络

```python
import torch
import torch.nn.functional as F
import torch.nn as nn
import math
from collections import OrderedDict

#-------------------------------------------------#
#   MISH激活函数
#-------------------------------------------------#
class Mish(nn.Module):
    def __init__(self):
        super(Mish, self).__init__()

    def forward(self, x):
        return x * torch.tanh(F.softplus(x))

#-------------------------------------------------#
#   卷积块
#   CONV+BATCHNORM+MISH
#-------------------------------------------------#
class BasicConv(nn.Module):
    def __init__(self, in_channels, out_channels, kernel_size, stride=1):
        super(BasicConv, self).__init__()

        self.conv = nn.Conv2d(in_channels, out_channels, kernel_size, stride, kernel_size//2, bias=False)
        self.bn = nn.BatchNorm2d(out_channels)
        self.activation = Mish()

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

#---------------------------------------------------#
#   CSPdarknet的结构块的组成部分
#   内部堆叠的残差块
#---------------------------------------------------#
class Resblock(nn.Module):
    def __init__(self, channels, hidden_channels=None, residual_activation=nn.Identity()):
        super(Resblock, self).__init__()

        if hidden_channels is None:
            hidden_channels = channels

        self.block = nn.Sequential(
            BasicConv(channels, hidden_channels, 1),
            BasicConv(hidden_channels, channels, 3)
        )

    def forward(self, x):
        return x + self.block(x)

#---------------------------------------------------#
#   CSPdarknet的结构块
#   存在一个大残差边
#   这个大残差边绕过了很多的残差结构
#---------------------------------------------------#
class Resblock_body(nn.Module):
    def __init__(self, in_channels, out_channels, num_blocks, first):
        super(Resblock_body, self).__init__()

        self.downsample_conv = BasicConv(in_channels, out_channels, 3, stride=2)

        if first:
            self.split_conv0 = BasicConv(out_channels, out_channels, 1) #csp net part1
            self.split_conv1 = BasicConv(out_channels, out_channels, 1)  #csp net part2
            self.blocks_conv = nn.Sequential(#csp net part2
                Resblock(channels=out_channels, hidden_channels=out_channels//2),
                BasicConv(out_channels, out_channels, 1)
            )
            self.concat_conv = BasicConv(out_channels*2, out_channels, 1) #csp net 拼接
        else:
            self.split_conv0 = BasicConv(out_channels, out_channels//2, 1)
            self.split_conv1 = BasicConv(out_channels, out_channels//2, 1)

            self.blocks_conv = nn.Sequential(
                *[Resblock(out_channels//2) for _ in range(num_blocks)], #多个resblock循环叠加
                BasicConv(out_channels//2, out_channels//2, 1)
            )
            self.concat_conv = BasicConv(out_channels, out_channels, 1)

    def forward(self, x):
        x = self.downsample_conv(x)
        # csp net part1
        x0 = self.split_conv0(x)
        # csp net part2
        x1 = self.split_conv1(x)
        x1 = self.blocks_conv(x1)
        #csp 通道拼接
        x = torch.cat([x1, x0], dim=1)
        #卷积
        x = self.concat_conv(x)

        return x

class CSPDarkNet(nn.Module):
    def __init__(self, layers):#layers :[1,2,8,8,4] 每个Resblock_body的重复个数
        super(CSPDarkNet, self).__init__()
        self.inplanes = 32
        self.conv1 = BasicConv(3, self.inplanes, kernel_size=3, stride=1)
        self.feature_channels = [64, 128, 256, 512, 1024]

        self.stages = nn.ModuleList([
            Resblock_body(self.inplanes, self.feature_channels[0], layers[0], first=True),
            Resblock_body(self.feature_channels[0], self.feature_channels[1], layers[1], first=False),#输入64维，输出128维，层数2层，
            Resblock_body(self.feature_channels[1], self.feature_channels[2], layers[2], first=False),
            Resblock_body(self.feature_channels[2], self.feature_channels[3], layers[3], first=False),
            Resblock_body(self.feature_channels[3], self.feature_channels[4], layers[4], first=False)
        ])

        self.num_features = 1
        # 进行权值初始化
        for m in self.modules():
            if isinstance(m, nn.Conv2d):
                n = m.kernel_size[0] * m.kernel_size[1] * m.out_channels
                m.weight.data.normal_(0, math.sqrt(2. / n))
            elif isinstance(m, nn.BatchNorm2d):
                m.weight.data.fill_(1)
                m.bias.data.zero_()


    def forward(self, x):
        x = self.conv1(x)

        x = self.stages[0](x)
        x = self.stages[1](x)
        out3 = self.stages[2](x) #8倍采样
        out4 = self.stages[3](out3) #16背下采样
        out5 = self.stages[4](out4) #32倍下采样

        return out3, out4, out5

def darknet53(pretrained, **kwargs):
    model = CSPDarkNet([1, 2, 8, 8, 4])
    if pretrained:
        if isinstance(pretrained, str):
            model.load_state_dict(torch.load(pretrained))
        else:
            raise Exception("darknet request a pretrained path. got [{}]".format(pretrained))
    return model