2.5 yolov5的主干网络CSPDarknet的输出

1.主干网络输入的图片大小是640X640X3，reshape之后为1X3X640X640；

2.主干网络主要输出3个特征层，分别是torch.Size([1, 256, 80, 80]) torch.Size([1, 512, 40, 40]) torch.Size([1, 1024, 20, 20])。这3个特征将在yolo.py文件里对其分别求上采样和下采样以及求3个head。

代码解释及输出如下（注意：需要修改输入图片的路径）：

#主函数CSPDarknet
import torch
import torch.nn as nn
import cv2


#1.silu激活函数
class SiLU(nn.Module):
    @staticmethod
    def forward(x):
        return x * torch.sigmoid(x)


def autopad(k, p=None):
    if p is None:
        p = k // 2 if isinstance(k, int) else [x // 2 for x in k]
    return p


#2.构造卷积函数
class Conv(nn.Module):
    def __init__(self, c1, c2, k=1, s=1, p=None, g=1, act=True):
        super(Conv, self).__init__()
        # 卷积、标准化加激活函数
        self.conv=nn.Conv2d(c1,c2,k,s,autopad(k,p),groups=g, bias=False)
        self.bn=nn.BatchNorm2d(c2,eps=0.001,momentum=0.03)
        self.act=SiLU() if act is True else (act if isinstance(act,nn.Module) else nn.Identity())#激活函数

    def forward(self,x):
        return self.act(self.bn(self.conv(x)))#卷积->BatchNorm2d->激活函数->output

    def fuseforward(self, x):
        return self.act(self.conv(x))  # 这个forward函数不存在BN操作


#3.Focus函数:  对图片处理 640X640X3--->320X320X12------>320X320X64
class Focus(nn.Module):
    def __init__(self,c1, c2, k=1, s=1, p=None, g=1, act=True):
        super(Focus,self).__init__()
        # 通道数变为原来的4倍
        self.conv=Conv(c1*4,c2,k,s,p,g,act)

    def forward(self,x):
        return self.conv(

            # torch.cat:按照维数对数组拼接，1表示横着拼接，需要行数相同，以下拼接后通道数乘以4，行数减半.
            torch.cat(
                [
                    x[..., ::2, ::2],# 640, 640, 3 => 320, 320, 12
                    x[..., 1::2, ::2],
                    x[..., ::2, 1::2],
                    x[..., 1::2, 1::2]
                ], 1
            )
        )


# 4.CSPLayer中的残差结构的定义
class Bottleneck(nn.Module):
    # Standard bottleneck
    def __init__(self, c1, c2, shortcut=True, g=1, e=0.5):  # ch_in, ch_out, shortcut, groups, expansion
        super(Bottleneck, self).__init__()
        c_=int(c2*e)
        self.cv1=Conv(c1,c_,1,1)
        self.cv2=Conv(c_,c2,3,1,g=g)
        self.add=shortcut and c1==c2

    def forward(self,x):
        return x+self.cv2(self.cv1(x)) if self.add else self.cv2(self.cv1(x))

#5.csplayer结构,用残差结构进行特征提取
class C3(nn.Module):
    def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):
        super(C3,self).__init__()
        c_ = int(c2 * e)  # hidden channels
        self.cv1 = Conv(c1, c_, 1, 1)
        self.cv2 = Conv(c1, c_, 1, 1)
        self.cv3=Conv(2*c_,c2,1)
        self.m=nn.Sequential(*[Bottleneck(c_,c_,shortcut,g,e=1.0) for _ in range(n)])

    def forward(self,x):
        return self.cv3(torch.cat(
            (
            self.m(self.cv1(x)),
            self.cv2(x)
            )
        ,dim=1))


#6.SPP通过不同池化和大小的最大池化进行特征提取，提高网络的感受野
class SPP(nn.Module):
    # Spatial pyramid pooling layer used in YOLOv3-SPP
    def __init__(self, c1, c2, k=(5, 9, 13)):
        super(SPP, self).__init__()
        c_ = c1 // 2  # hidden channels
        self.cv1 = Conv(c1, c_, 1, 1)
        self.cv2 = Conv(c_ * (len(k) + 1), c2, 1, 1)
        self.m = nn.ModuleList([nn.MaxPool2d(kernel_size=x, stride=1, padding=x // 2) for x in k])

    def forward(self, x):
        x = self.cv1(x)
        return self.cv2(torch.cat([x] + [m(x) for m in self.m], 1))


class CSPDarknet(nn.Module):
    def __init__(self, base_channels=64, base_depth=1, phi="s", pretrained="ss"):
        super().__init__()
        # -----------------------------------------------#
        #   输入图片是640, 640, 3
        #   初始的基本通道base_channels是64
        # -----------------------------------------------#

        # -----------------------------------------------#
        #   利用focus网络结构进行特征提取
        #   640, 640, 3 -> 320, 320, 12 -> 320, 320, 64
        # -----------------------------------------------#
        self.stem = Focus(3, base_channels, k=3)

        # -----------------------------------------------#
        #   完成卷积之后，320, 320, 64 -> 160, 160, 128
        #   完成CSPlayer之后，160, 160, 128 -> 160, 160, 128
        # -----------------------------------------------#
        self.dark2 = nn.Sequential(
            # 320, 320, 64 -> 160, 160, 128
            Conv(base_channels, base_channels * 2, 3, 2),
            # 160, 160, 128 -> 160, 160, 128
            C3(base_channels * 2, base_channels * 2, base_depth),
        )

        # -----------------------------------------------#
        #   完成卷积之后，160, 160, 128 -> 80, 80, 256
        #   完成CSPlayer之后，80, 80, 256 -> 80, 80, 256
        #                   在这里引出有效特征层80, 80, 256
        #                   进行加强特征提取网络FPN的构建
        # -----------------------------------------------#
        self.dark3 = nn.Sequential(
            Conv(base_channels * 2, base_channels * 4, 3, 2),
            C3(base_channels * 4, base_channels * 4, base_depth * 3),
        )

        # -----------------------------------------------#
        #   完成卷积之后，80, 80, 256 -> 40, 40, 512
        #   完成CSPlayer之后，40, 40, 512 -> 40, 40, 512
        #                   在这里引出有效特征层40, 40, 512
        #                   进行加强特征提取网络FPN的构建
        # -----------------------------------------------#
        self.dark4 = nn.Sequential(
            Conv(base_channels * 4, base_channels * 8, 3, 2),
            C3(base_channels * 8, base_channels * 8, base_depth * 3),
        )

        # -----------------------------------------------#
        #   完成卷积之后，40, 40, 512 -> 20, 20, 1024
        #   完成SPP之后，20, 20, 1024 -> 20, 20, 1024
        #   完成CSPlayer之后，20, 20, 1024 -> 20, 20, 1024
        # -----------------------------------------------#
        self.dark5 = nn.Sequential(
            Conv(base_channels * 8, base_channels * 16, 3, 2),
            SPP(base_channels * 16, base_channels * 16),
            C3(base_channels * 16, base_channels * 16, base_depth, shortcut=False),
        )
        # if pretrained:
        #     url = {
        #         's': 'https://github.com/bubbliiiing/yolov5-pytorch/releases/download/v1.0/cspdarknet_s_backbone.pth',
        #         'm': 'https://github.com/bubbliiiing/yolov5-pytorch/releases/download/v1.0/cspdarknet_m_backbone.pth',
        #         'l': 'https://github.com/bubbliiiing/yolov5-pytorch/releases/download/v1.0/cspdarknet_l_backbone.pth',
        #         'x': 'https://github.com/bubbliiiing/yolov5-pytorch/releases/download/v1.0/cspdarknet_x_backbone.pth',
        #     }[phi]
        #     checkpoint = torch.hub.load_state_dict_from_url(url=url, map_location="cpu", model_dir="./model_data")
        #     self.load_state_dict(checkpoint, strict=False)
        #     print("Load weights from ", url.split('/')[-1])

    def forward(self, x):
        x = self.stem(x)
        x = self.dark2(x)
        # -----------------------------------------------#
        #   dark3的输出为80, 80, 256，是一个有效特征层
        # -----------------------------------------------#
        x = self.dark3(x)
        feat1 = x
        # -----------------------------------------------#
        #   dark4的输出为40, 40, 512，是一个有效特征层
        # -----------------------------------------------#
        x = self.dark4(x)
        feat2 = x
        # -----------------------------------------------#
        #   dark5的输出为20, 20, 1024，是一个有效特征层
        # -----------------------------------------------#
        x = self.dark5(x)
        feat3 = x
        return feat1, feat2, feat3


if __name__ == "__main__":
    #输入图片路径
    image=cv2.imread(r"D:\AI\data\red_green_light\4.jpg")

    image=cv2.resize(image,(640,640))
    print(image.shape)

    images=image.reshape(1,3,640, 640)

    data=torch.tensor(images)
    datas=torch.tensor(images,dtype=torch.float32)

    ss=CSPDarknet()
    feat1, feat2, feat3=ss(datas)
    print(feat1.shape, feat2.shape, feat3.shape)