yolo模块

yolov9论文代码：https://github.com/WongKinYiu/yolov9
yolov9论文链接：https://arxiv.org/abs/2402.13616
yolov10论文代码：https://github.com/THU-MIG/yolov10
yolov10论文链接：https://arxiv.org/abs/2405.14458

Conv是Conv2d+BN+SiLU
ch_in是输入通道 ch_out是输出通道

1 YOLOv8

1.1 C2f

n是由下面代码决定的，C1是ch_in，C2是ch_out

n = n_ = max(round(n * depth), 1) if n > 1 else n  # depth gain

这个depth的值是来源于yolov8.yaml文件

# [depth, width, max_channels]
n: [0.33, 0.25, 1024] # YOLOv8n summary

n也是来源于yolov8n.yaml文件

# [from, repeats, module, args]
- [-1, 6, C2f, [256, True]] # 这个repeats=6就是n

n = n_ = max(round(n * depth), 1) if n > 1 else n  
n = max(round(6 * 0.33), 1) = 2 
# 最终这个C2f中Bottleneck重复了两次

class C2f(nn.Module):
    """Faster Implementation of CSP Bottleneck with 2 convolutions."""

    def __init__(self, c1, c2, n=1, shortcut=False, g=1, e=0.5):
        """Initialize CSP bottleneck layer with two convolutions with arguments ch_in, ch_out, number, shortcut, groups,
        expansion.
        """
        super().__init__()
        self.c = int(c2 * e)  # hidden channels
        self.cv1 = Conv(c1, 2 * self.c, 1, 1)
        self.cv2 = Conv((2 + n) * self.c, c2, 1)  # optional act=FReLU(c2)
        self.m = nn.ModuleList(Bottleneck(self.c, self.c, shortcut, g, k=((3, 3), (3, 3)), e=1.0) for _ in range(n))

    def forward(self, x):
        """Forward pass through C2f layer."""
        y = list(self.cv1(x).chunk(2, 1))
        y.extend(m(y[-1]) for m in self.m)
        return self.cv2(torch.cat(y, 1))

    def forward_split(self, x):
        """Forward pass using split() instead of chunk()."""
        y = list(self.cv1(x).split((self.c, self.c), 1))
        y.extend(m(y[-1]) for m in self.m)
        return self.cv2(torch.cat(y, 1))

1.2 Detect

class Detect(nn.Module):
    # YOLO Detect head for detection models
    dynamic = False  # force grid reconstruction
    export = False  # export mode
    shape = None
    anchors = torch.empty(0)  # init
    strides = torch.empty(0)  # init

    def __init__(self, nc=80, ch=(), inplace=True):  # detection layer
        super().__init__()
        self.nc = nc  # number of classes
        self.nl = len(ch)  # number of detection layers
        self.reg_max = 16
        self.no = nc + self.reg_max * 4  # number of outputs per anchor
        self.inplace = inplace  # use inplace ops (e.g. slice assignment)
        self.stride = torch.zeros(self.nl)  # strides computed during build

        c2, c3 = max((ch[0] // 4, self.reg_max * 4, 16)), max((ch[0], min((self.nc * 2, 128))))  # channels
        self.cv2 = nn.ModuleList(
            nn.Sequential(Conv(x, c2, 3), Conv(c2, c2, 3), nn.Conv2d(c2, 4 * self.reg_max, 1)) for x in ch)
        self.cv3 = nn.ModuleList(
            nn.Sequential(Conv(x, c3, 3), Conv(c3, c3, 3), nn.Conv2d(c3, self.nc, 1)) for x in ch)
        self.dfl = DFL(self.reg_max) if self.reg_max > 1 else nn.Identity()

    def forward(self, x):
        shape = x[0].shape  # BCHW
        for i in range(self.nl):
            x[i] = torch.cat((self.cv2[i](x[i]), self.cv3[i](x[i])), 1)
        if self.training:
            return x
        elif self.dynamic or self.shape != shape:
            self.anchors, self.strides = (x.transpose(0, 1) for x in make_anchors(x, self.stride, 0.5))
            self.shape = shape

        box, cls = torch.cat([xi.view(shape[0], self.no, -1) for xi in x], 2).split((self.reg_max * 4, self.nc), 1)
        dbox = dist2bbox(self.dfl(box), self.anchors.unsqueeze(0), xywh=True, dim=1) * self.strides
        y = torch.cat((dbox, cls.sigmoid()), 1)
        return y if self.export else (y, x)

    def bias_init(self):
        # Initialize Detect() biases, WARNING: requires stride availability
        m = self  # self.model[-1]  # Detect() module
        # cf = torch.bincount(torch.tensor(np.concatenate(dataset.labels, 0)[:, 0]).long(), minlength=nc) + 1
        # ncf = math.log(0.6 / (m.nc - 0.999999)) if cf is None else torch.log(cf / cf.sum())  # nominal class frequency
        for a, b, s in zip(m.cv2, m.cv3, m.stride):  # from
            a[-1].bias.data[:] = 1.0  # box
            b[-1].bias.data[:m.nc] = math.log(5 / m.nc / (640 / s) ** 2)  # cls (5 objects and 80 classes per 640 image)

2 YOLOv9

2.1 ADown

C1是ch_in，C2是ch_out

class ADown(nn.Module):
    def __init__(self, c1, c2):  # ch_in, ch_out, shortcut, kernels, groups, expand
        super().<