YOLOv8代码解读

本文参考：Yolov 8源码超详细逐行解读+ 网络结构细讲(自我用的小白笔记)_yolov8源码-CSDN博客

YOLOv8源码地址： https://gitcode.com/gh_mirrors/ul/ultralytics?utm_source=csdn_github_accelerator&isLogin=1

笔者采用YOLOv8训练自定义数据集：基于SeaShips数据集的yolov8训练教程_yolov8训练seaships数据集-CSDN博客

一、网络结构

首先我们来看YOLOv8的整体网络结构：

接下来我们将分为backbone和Head两部分进行介绍：

二、backbone骨干网络

backbone文件保存在yolov8-main/ultralytics/models/v8/yolov8l.yaml

这里的yolov8l.yaml的l代表large，同理还有s（small）、m（medium）x（extra large）以及n（nano），n是代表模型尺寸小、计算量最少的版本。这里介绍以l为例。yaml文件如下所示：

# Ultralytics YOLO 🚀, GPL-3.0 license

# Parameters
nc: 6  # number of classes
depth_multiple: 1.00  # scales module repeats
width_multiple: 1.00  # scales convolution channels

# YOLOv8.0l backbone
backbone:
  # [from, repeats, module, args]
  - [-1, 1, Conv, [64, 3, 2]]  # 0-P1/2
  - [-1, 1, Conv, [128, 3, 2]]  # 1-P2/4
  - [-1, 3, C2f, [128, True]]
  - [-1, 1, Conv, [256, 3, 2]]  # 3-P3/8
  - [-1, 6, C2f, [256, True]]
  - [-1, 1, Conv, [512, 3, 2]]  # 5-P4/16
  - [-1, 6, C2f, [512, True]]
  - [-1, 1, Conv, [512, 3, 2]]  # 7-P5/32
  - [-1, 3, C2f, [512, True]]
  - [-1, 1, SPPF, [512, 5]]  # 9

# YOLOv8.0l head
head:
  - [-1, 1, nn.Upsample, [None, 2, 'nearest']]
  - [[-1, 6], 1, Concat, [1]]  # cat backbone P4
  - [-1, 3, C2f, [512]]  # 12

  - [-1, 1, nn.Upsample, [None, 2, 'nearest']]
  - [[-1, 4], 1, Concat, [1]]  # cat backbone P3
  - [-1, 3, C2f, [256]]  # 15 (P3/8-small)

  - [-1, 1, Conv, [256, 3, 2]]
  - [[-1, 12], 1, Concat, [1]]  # cat head P4
  - [-1, 3, C2f, [512]]  # 18 (P4/16-medium)

  - [-1, 1, Conv, [512, 3, 2]]
  - [[-1, 9], 1, Concat, [1]]  # cat head P5
  - [-1, 3, C2f, [512]]  # 21 (P5/32-large)

  - [[15, 18, 21], 1, Detect, [nc]]  # Detect(P3, P4, P5)

可以看到其中包含了backbone和head两个块的代码，这里先介绍backbone部分：

# YOLOv8.0l backbone
backbone:
  # [from, repeats, module, args]
  - [-1, 1, Conv, [64, 3, 2]]  # 0-P1/2
  - [-1, 1, Conv, [128, 3, 2]]  # 1-P2/4
  - [-1, 3, C2f, [128, True]]
  - [-1, 1, Conv, [256, 3, 2]]  # 3-P3/8
  - [-1, 6, C2f, [256, True]]
  - [-1, 1, Conv, [512, 3, 2]]  # 5-P4/16
  - [-1, 6, C2f, [512, True]]
  - [-1, 1, Conv, [512, 3, 2]]  # 7-P5/32
  - [-1, 3, C2f, [512, True]]
  - [-1, 1, SPPF, [512, 5]]  # 9

backbone下第一行注释的四个参数分别表示：

• from：输入，-1表示上层的输出作为本层的输入
• repeats：模块的重复次数
• module：使用的模块
• args：模块传入的参数

另外计算尺寸的公式：

 

这里我们可以看到backbone部分一共有10层（0层~9层），一共采用三种模块：Conv、C2f和SPPF。

2.1 标准卷积模块Conv

代码文件存放在yolov8-main/ultralytics/nn/modules.py/Class Conv

def autopad(k, p=None, d=1):  # kernel, padding, dilation
    # Pad to 'same' shape outputs
    if d > 1:
        k = d * (k - 1) + 1 if isinstance(k, int) else [d * (x - 1) + 1 for x in k]  # actual kernel-size
    if p is None:
        p = k // 2 if isinstance(k, int) else [x // 2 for x in k]  # auto-pad
    return p

# 标准卷积
class Conv(nn.Module):
    # Standard convolution with args(ch_in, ch_out, kernel, stride, padding, groups, dilation, activation)
    default_act = nn.SiLU()  # default activation

    def __init__(self, c1, c2, k=1, s=1, p=None, g=1, d=1, act=True):
        super().__init__()
        self.conv = nn.Conv2d(c1, c2, k, s, autopad(k, p, d), groups=g, dilation=d, bias=False)
        self.bn = nn.BatchNorm2d(c2)
        self.act = self.default_act if act is True else act if isinstance(act, nn.Module) else nn.Identity()

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

    def forward_fuse(self, x