前言

论文地址
YOLOv7源码

下面对v0.1版本的整体网络结构及各个组件,结合源码和train文件夹中的yolov7.yaml配置文件进行解析。

 

整体网络结构

【YOLOv7_0.1】网络结构与源码解析-LMLPHP

 

分解的yolov7.yaml

# parameters
nc: 80  # number of classes
depth_multiple: 1.0  # model depth multiple
width_multiple: 1.0  # layer channel multiple

# anchors
anchors:
  - [12,16, 19,36, 40,28]  # P3/8
  - [36,75, 76,55, 72,146]  # P4/16
  - [142,110, 192,243, 459,401]  # P5/32

# yolov7 backbone
backbone:
  # [from, number, module, args]
  [[-1, 1, Conv, [32, 3, 1]],  # 0
   [-1, 1, Conv, [64, 3, 2]],  # 1-P1/2      
   [-1, 1, Conv, [64, 3, 1]],
   [-1, 1, Conv, [128, 3, 2]],  # 3-P2/4

   # ELAN1
   [-1, 1, Conv, [64, 1, 1]],
   [-2, 1, Conv, [64, 1, 1]],
   [-1, 1, Conv, [64, 3, 1]],
   [-1, 1, Conv, [64, 3, 1]],
   [-1, 1, Conv, [64, 3, 1]],
   [-1, 1, Conv, [64, 3, 1]],
   [[-1, -3, -5, -6], 1, Concat, [1]],
   [-1, 1, Conv, [256, 1, 1]],  # 11

   # MPConv
   [-1, 1, MP, []],
   [-1, 1, Conv, [128, 1, 1]],
   [-3, 1, Conv, [128, 1, 1]],
   [-1, 1, Conv, [128, 3, 2]],
   [[-1, -3], 1, Concat, [1]],  # 16-P3/8

   # ELAN1
   [-1, 1, Conv, [128, 1, 1]],
   [-2, 1, Conv, [128, 1, 1]],
   [-1, 1, Conv, [128, 3, 1]],
   [-1, 1, Conv, [128, 3, 1]],
   [-1, 1, Conv, [128, 3, 1]],
   [-1, 1, Conv, [128, 3, 1]],
   [[-1, -3, -5, -6], 1, Concat, [1]],
   [-1, 1, Conv, [512, 1, 1]],  # 24

   # MPConv
   [-1, 1, MP, []],
   [-1, 1, Conv, [256, 1, 1]],
   [-3, 1, Conv, [256, 1, 1]],
   [-1, 1, Conv, [256, 3, 2]],
   [[-1, -3], 1, Concat, [1]],  # 29-P4/16

   # ELAN1
   [-1, 1, Conv, [256, 1, 1]],
   [-2, 1, Conv, [256, 1, 1]],
   [-1, 1, Conv, [256, 3, 1]],
   [-1, 1, Conv, [256, 3, 1]],
   [-1, 1, Conv, [256, 3, 1]],
   [-1, 1, Conv, [256, 3, 1]],
   [[-1, -3, -5, -6], 1, Concat, [1]],
   [-1, 1, Conv, [1024, 1, 1]],  # 37

   # MPConv
   [-1, 1, MP, []],
   [-1, 1, Conv, [512, 1, 1]],
   [-3, 1, Conv, [512, 1, 1]],
   [-1, 1, Conv, [512, 3, 2]],
   [[-1, -3], 1, Concat, [1]],  # 42-P5/32

   # ELAN1
   [-1, 1, Conv, [256, 1, 1]],
   [-2, 1, Conv, [256, 1, 1]],
   [-1, 1, Conv, [256, 3, 1]],
   [-1, 1, Conv, [256, 3, 1]],
   [-1, 1, Conv, [256, 3, 1]],
   [-1, 1, Conv, [256, 3, 1]],
   [[-1, -3, -5, -6], 1, Concat, [1]],
   [-1, 1, Conv, [1024, 1, 1]],  # 50
  ]

# yolov7 head
head:
  [[-1, 1, SPPCSPC, [512]], # 51

   [-1, 1, Conv, [256, 1, 1]],
   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
   [37, 1, Conv, [256, 1, 1]], # route backbone P4
   [[-1, -2], 1, Concat, [1]],

   # ELAN2
   [-1, 1, Conv, [256, 1, 1]],
   [-2, 1, Conv, [256, 1, 1]],
   [-1, 1, Conv, [128, 3, 1]],
   [-1, 1, Conv, [128, 3, 1]],
   [-1, 1, Conv, [128, 3, 1]],
   [-1, 1, Conv, [128, 3, 1]],
   [[-1, -2, -3, -4, -5, -6], 1, Concat, [1]],
   [-1, 1, Conv, [256, 1, 1]], # 63

   [-1, 1, Conv, [128, 1, 1]],
   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
   [24, 1, Conv, [128, 1, 1]], # route backbone P3
   [[-1, -2], 1, Concat, [1]],

   # ELAN2
   [-1, 1, Conv, [128, 1, 1]],
   [-2, 1, Conv, [128, 1, 1]],
   [-1, 1, Conv, [64, 3, 1]],
   [-1, 1, Conv, [64, 3, 1]],
   [-1, 1, Conv, [64, 3, 1]],
   [-1, 1, Conv, [64, 3, 1]],
   [[-1, -2, -3, -4, -5, -6], 1, Concat, [1]],
   [-1, 1, Conv, [128, 1, 1]], # 75

   # MPConv Channel × 2
   [-1, 1, MP, []],
   [-1, 1, Conv, [128, 1, 1]],
   [-3, 1, Conv, [128, 1, 1]],
   [-1, 1, Conv, [128, 3, 2]],
   [[-1, -3, 63], 1, Concat, [1]],

   # ELAN2
   [-1, 1, Conv, [256, 1, 1]],
   [-2, 1, Conv, [256, 1, 1]],
   [-1, 1, Conv, [128, 3, 1]],
   [-1, 1, Conv, [128, 3, 1]],
   [-1, 1, Conv, [128, 3, 1]],
   [-1, 1, Conv, [128, 3, 1]],
   [[-1, -2, -3, -4, -5, -6], 1, Concat, [1]],
   [-1, 1, Conv, [256, 1, 1]], # 88

   # MPConv Channel × 2
   [-1, 1, MP, []],
   [-1, 1, Conv, [256, 1, 1]],
   [-3, 1, Conv, [256, 1, 1]],
   [-1, 1, Conv, [256, 3, 2]],
   [[-1, -3, 51], 1, Concat, [1]],

   # ELAN2
   [-1, 1, Conv, [512, 1, 1]],
   [-2, 1, Conv, [512, 1, 1]],
   [-1, 1, Conv, [256, 3, 1]],
   [-1, 1, Conv, [256, 3, 1]],
   [-1, 1, Conv, [256, 3, 1]],
   [-1, 1, Conv, [256, 3, 1]],
   [[-1, -2, -3, -4, -5, -6], 1, Concat, [1]],
   [-1, 1, Conv, [512, 1, 1]], # 101

   [75, 1, RepConv, [256, 3, 1]],
   [88, 1, RepConv, [512, 3, 1]],
   [101, 1, RepConv, [1024, 3, 1]],

   [[102,103,104], 1, IDetect, [nc, anchors]],   # Detect(P3, P4, P5)
  ]

 

各组件结构

ELAN1 (backbone)

【YOLOv7_0.1】网络结构与源码解析-LMLPHP
  • yolov7.yaml中对应部分:
# ELAN1
   [-1, 1, Conv, [64, 1, 1]],
   [-2, 1, Conv, [64, 1, 1]],
   [-1, 1, Conv, [64, 3, 1]],
   [-1, 1, Conv, [64, 3, 1]],
   [-1, 1, Conv, [64, 3, 1]],
   [-1, 1, Conv, [64, 3, 1]],
   [[-1, -3, -5, -6], 1, Concat, [1]],
   [-1, 1, Conv, [256, 1, 1]],  # 11

 

ELAN2 (head)

【YOLOv7_0.1】网络结构与源码解析-LMLPHP
  • yolov7.yaml中对应部分:
# ELAN2
   [-1, 1, Conv, [256, 1, 1]],
   [-2, 1, Conv, [256, 1, 1]],
   [-1, 1, Conv, [128, 3, 1]],
   [-1, 1, Conv, [128, 3, 1]],
   [-1, 1, Conv, [128, 3, 1]],
   [-1, 1, Conv, [128, 3, 1]],
   [[-1, -2, -3, -4, -5, -6], 1, Concat, [1]],
   [-1, 1, Conv, [256, 1, 1]], # 63

 

MPConv

【YOLOv7_0.1】网络结构与源码解析-LMLPHP
  • backnone中的对应部分
  • 要注意相比于MP函数之前,通道数减少一半
   [-1, 1, Conv, [256, 1, 1]],  # 11

   # MPConv
   [-1, 1, MP, []],
   [-1, 1, Conv, [128, 1, 1]],
   [-3, 1, Conv, [128, 1, 1]],
   [-1, 1, Conv, [128, 3, 2]],
   [[-1, -3], 1, Concat, [1]],  # 16-P3/8
  • head中的对应部分
  • 要注意相比于MP函数之前,通道数不变
   [-1, 1, Conv, [128, 1, 1]], # 75

   # MPConv Channel × 2
   [-1, 1, MP, []],
   [-1, 1, Conv, [128, 1, 1]],
   [-3, 1, Conv, [128, 1, 1]],
   [-1, 1, Conv, [128, 3, 2]],
   [[-1, -3, 63], 1, Concat, [1]],

 

SPPCSPC

类似于yolov5中的SPPF,不同的是,使用了5×5、9×9、13×13最大池化。
【YOLOv7_0.1】网络结构与源码解析-LMLPHP

  • common.py中对应部分:
class SPPCSPC(nn.Module):
    # CSP https://github.com/WongKinYiu/CrossStagePartialNetworks
    def __init__(self, c1, c2, n=1, shortcut=False, g=1, e=0.5, k=(5, 9, 13)):
        super(SPPCSPC, self).__init__()
        c_ = int(2 * c2 * e)  # hidden channels
        self.cv1 = Conv(c1, c_, 1, 1)
        self.cv2 = Conv(c1, c_, 1, 1)
        self.cv3 = Conv(c_, c_, 3, 1)
        self.cv4 = Conv(c_, c_, 1, 1)
        self.m = nn.ModuleList([nn.MaxPool2d(kernel_size=x, stride=1, padding=x // 2) for x in k])
        self.cv5 = Conv(4 * c_, c_, 1, 1)
        self.cv6 = Conv(c_, c_, 3, 1)
        self.cv7 = Conv(2 * c_, c2, 1, 1)

    def forward(self, x):
        x1 = self.cv4(self.cv3(self.cv1(x)))
        y1 = self.cv6(self.cv5(torch.cat([x1] + [m(x1) for m in self.m], 1)))
        y2 = self.cv2(x)
        return self.cv7(torch.cat((y1, y2), dim=1))

 

RepConv

原理理解层面

  • 训练时:三个卷积相加得到输出
  • 推理时:将三个卷积重参数化,合并为一个卷积输出

代码实现层面

  • 训练时:不执行Model类的fuse函数
  • 推理时:在attempt_load函数加载训练好的模型时,会执行Model类的fuse函数,进而调用fuse_repvgg_block函数,实现将三个卷积重参数化,合并为一个卷积输出
  • common.py中对应部分:
# Represented convolution https://arxiv.org/abs/2101.03697
class RepConv(nn.Module):
    '''重参数卷积
    训练时:
        deploy = False
        rbr_dense(3*3卷积) + rbr_1x1(1*1卷积) + rbr_identity(c2 == c1时) 三者相加
        rbr_reparam = None
    推理时:
        deploy = True
        rbr_reparam = Conv2d
        rbr_dense = None
        rbr_1x1 = None
        rbr_identity = None
    '''
    def __init__(self, c1, c2, k=3, s=1, p=None, g=1, act=True, deploy=False):
        super(RepConv, self).__init__()

        self.deploy = deploy
        self.groups = g
        self.in_channels = c1
        self.out_channels = c2

        assert k == 3
        assert autopad(k, p) == 1

        padding_11 = autopad(k, p) - k // 2

        self.act = nn.SiLU() if act is True else (act if isinstance(act, nn.Module) else nn.Identity())

        # 推理阶段,仅有一个3×3的卷积来替换
        if deploy:
            self.rbr_reparam = nn.Conv2d(c1, c2, k, s, autopad(k, p), groups=g, bias=True)

        else:
            # 训练阶段,当输入和输出的通道数相同时,会在加一个BN层
            self.rbr_identity = (nn.BatchNorm2d(num_features=c1) if c2 == c1 and s == 1 else None)
            # 3×3的卷积(padding=1)
            self.rbr_dense = nn.Sequential(
                nn.Conv2d(c1, c2, k, s, autopad(k, p), groups=g, bias=False),
                nn.BatchNorm2d(num_features=c2),
            )
            # 1×1的卷积
            self.rbr_1x1 = nn.Sequential(
                nn.Conv2d(c1, c2, 1, s, padding_11, groups=g, bias=False),
                nn.BatchNorm2d(num_features=c2),
            )

    def forward(self, inputs):
        if hasattr(self, "rbr_reparam"):
            return self.act(self.rbr_reparam(inputs))

        if self.rbr_identity is None:
            id_out = 0
        else:
            id_out = self.rbr_identity(inputs)

        return self.act(self.rbr_dense(inputs) + self.rbr_1x1(inputs) + id_out)

    # Conv2D + BN -> Conv2D
    def fuse_conv_bn(self, conv, bn):

        std = (bn.running_var + bn.eps).sqrt()
        bias = bn.bias - bn.running_mean * bn.weight / std

        t = (bn.weight / std).reshape(-1, 1, 1, 1)
        weights = conv.weight * t

        bn = nn.Identity()
        conv = nn.Conv2d(in_channels=conv.in_channels,
                         out_channels=conv.out_channels,
                         kernel_size=conv.kernel_size,
                         stride=conv.stride,
                         padding=conv.padding,
                         dilation=conv.dilation,
                         groups=conv.groups,
                         bias=True,
                         padding_mode=conv.padding_mode)

        conv.weight = torch.nn.Parameter(weights)
        conv.bias = torch.nn.Parameter(bias)
        return conv

    # 在推理阶段才执行重参数操作
    def fuse_repvgg_block(self):
        if self.deploy:
            return
        print(f"RepConv.fuse_repvgg_block")

        self.rbr_dense = self.fuse_conv_bn(self.rbr_dense[0], self.rbr_dense[1])
        self.rbr_1x1 = self.fuse_conv_bn(self.rbr_1x1[0], self.rbr_1x1[1])
        rbr_1x1_bias = self.rbr_1x1.bias
        # self.rbr_1x1.weight [256, 128, 1, 1]
        # weight_1x1_expanded [256, 128, 3, 3]
        weight_1x1_expanded = torch.nn.functional.pad(self.rbr_1x1.weight, [1, 1, 1, 1])

        # Fuse self.rbr_identity
        if (isinstance(self.rbr_identity, nn.BatchNorm2d) or isinstance(self.rbr_identity,
                                                                        nn.modules.batchnorm.SyncBatchNorm)):
            # print(f"fuse: rbr_identity == BatchNorm2d or SyncBatchNorm")
            identity_conv_1x1 = nn.Conv2d(
                in_channels=self.in_channels,
                out_channels=self.out_channels,
                kernel_size=1,
                stride=1,
                padding=0,
                groups=self.groups,
                bias=False)
            identity_conv_1x1.weight.data = identity_conv_1x1.weight.data.to(self.rbr_1x1.weight.data.device)
            identity_conv_1x1.weight.data = identity_conv_1x1.weight.data.squeeze().squeeze()
            # print(f" identity_conv_1x1.weight = {identity_conv_1x1.weight.shape}")
            identity_conv_1x1.weight.data.fill_(0.0)
            identity_conv_1x1.weight.data.fill_diagonal_(1.0)
            identity_conv_1x1.weight.data = identity_conv_1x1.weight.data.unsqueeze(2).unsqueeze(3)
            # print(f" identity_conv_1x1.weight = {identity_conv_1x1.weight.shape}")

            identity_conv_1x1 = self.fuse_conv_bn(identity_conv_1x1, self.rbr_identity)
            bias_identity_expanded = identity_conv_1x1.bias
            weight_identity_expanded = torch.nn.functional.pad(identity_conv_1x1.weight, [1, 1, 1, 1])
        else:
            # print(f"fuse: rbr_identity != BatchNorm2d, rbr_identity = {self.rbr_identity}")
            bias_identity_expanded = torch.nn.Parameter(torch.zeros_like(rbr_1x1_bias))
            weight_identity_expanded = torch.nn.Parameter(torch.zeros_like(weight_1x1_expanded))

            # print(f"self.rbr_1x1.weight = {self.rbr_1x1.weight.shape}, ")
        # print(f"weight_1x1_expanded = {weight_1x1_expanded.shape}, ")
        # print(f"self.rbr_dense.weight = {self.rbr_dense.weight.shape}, ")

        self.rbr_dense.weight = torch.nn.Parameter(
            self.rbr_dense.weight + weight_1x1_expanded + weight_identity_expanded)
        self.rbr_dense.bias = torch.nn.Parameter(self.rbr_dense.bias + rbr_1x1_bias + bias_identity_expanded)

        self.rbr_reparam = self.rbr_dense
        # 前向推理时,使用重参数化后的 rbr_reparam 函数
        self.deploy = True

        if self.rbr_identity is not None:
            del self.rbr_identity
            self.rbr_identity = None

        if self.rbr_1x1 is not None:
            del self.rbr_1x1
            self.rbr_1x1 = None

        if self.rbr_dense is not None:
            del self.rbr_dense
            self.rbr_dense = None

 

References

[1] 深入浅出 Yolo 系列之 Yolov7 基础网络结构详解
[2] 【yolov7系列】网络框架细节拆解
[3] yolov7-GradCAM

08-05 09:45