Yolov8配置文件解读

引言

根据业务对yolov8进行魔改，先从配置文件学起。这里主要看模型得配置文件与代码读取机制。

yolov8网络结构图

yolov8配置

# Ultralytics YOLO 🚀, AGPL-3.0 license
# YOLOv8 object detection model with P3-P5 outputs. For Usage examples see https://docs.ultralytics.com/tasks/detect

# Parameters
nc: 80 # number of classes
scales: # model compound scaling constants, i.e. 'model=yolov8n.yaml' will call yolov8.yaml with scale 'n'
  # [depth, width, max_channels]
  n: [0.33, 0.25, 1024] # YOLOv8n summary: 225 layers,  3157200 parameters,  3157184 gradients,   8.9 GFLOPs
  s: [0.33, 0.50, 1024] # YOLOv8s summary: 225 layers, 11166560 parameters, 11166544 gradients,  28.8 GFLOPs
  m: [0.67, 0.75, 768] # YOLOv8m summary: 295 layers, 25902640 parameters, 25902624 gradients,  79.3 GFLOPs
  l: [1.00, 1.00, 512] # YOLOv8l summary: 365 layers, 43691520 parameters, 43691504 gradients, 165.7 GFLOPs
  x: [1.00, 1.25, 512] # YOLOv8x summary: 365 layers, 68229648 parameters, 68229632 gradients, 258.5 GFLOPs

# YOLOv8.0n 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, [1024, 3, 2]] # 7-P5/32
  - [-1, 3, C2f, [1024, True]]
  - [-1, 1, SPPF, [1024, 5]] # 9

# YOLOv8.0n 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, [1024]] # 21 (P5/32-large)

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

配置中的参数

nc: number of classes， 类别数
[from, repeats, module, args]：

• 数据从哪里来，-1 表示上一层
• 重复次数
• 模块
• 参数

配置读取机制

代码入口ultralytics/models/yolo/detect/train.py

主要看DetectionModel，在nn/task.py代码如下：

class DetectionModel(BaseModel):
    """YOLOv8 detection model."""

    def __init__(self, cfg="yolov8n.yaml", ch=3, nc=None, verbose=True):  # model, input channels, number of classes
        """Initialize the YOLOv8 detection model with the given config and parameters."""
        super().__init__()
        self.yaml = cfg if isinstance(cfg, dict) else yaml_model_load(cfg)  # cfg dict

        # Define model
        ch = self.yaml["ch"] = self.yaml.get("ch", ch)  # input channels
        if nc and nc != self.yaml["nc"]:
            LOGGER.info(f"Overriding model.yaml nc={self.yaml['nc']} with nc={nc}")
            self.yaml["nc"] = nc  # override YAML value
        self.model, self.save = parse_model(deepcopy(self.yaml), ch=ch, verbose=verbose)  # model, savelist
        self.names = {i: f"{i}" for i in range(self.yaml["nc"])}  # default names dict
        self.inplace = self.yaml.get("inplace", True)

        # Build strides
        m = self.model[-1]  # Detect()
        if isinstance(m, Detect):  # includes all Detect subclasses like Segment, Pose, OBB, WorldDetect
            s = 256  # 2x min stride
            m.inplace = self.inplace
            forward = lambda x: self.forward(x)[0] if isinstance(m, (Segment, Pose, OBB)) else self.forward(x)
            m.stride = torch.tensor([s / x.shape[-2] for x in forward(torch.zeros(1, ch, s, s))])  # forward
            self.stride = m.stride
            m.bias_init()  # only run once
        else:
            self.stride = torch.Tensor([32])  # default stride for i.e. RTDETR

        # Init weights, biases
        initialize_weights(self)
        if verbose:
            self.info()
            LOGGER.info("")

  

配置文件解析方法也在task.py中，如下：

def parse_model(d, ch, verbose=True):  # model_dict, input_channels(3)
    """Parse a YOLO model.yaml dictionary into a PyTorch model."""
    import ast

    # Args
    max_channels = float("inf")
    nc, act, scales = (d.get(x) for x in ("nc", "activation", "scales"))
    depth, width, kpt_shape = (d.get(x, 1.0) for x in ("depth_multiple", "width_multiple", "kpt_shape"))
    if scales:
        scale = d.get("scale")
        if not scale:
            scale = tuple(scales.keys())[0]
            LOGGER.warning(f"WARNING ⚠️ no model scale passed. Assuming scale='{scale}'.")
        depth, width, max_channels = scales[scale]

    if act:
        Conv.default_act = eval(act)  # redefine default activation, i.e. Conv.default_act = nn.SiLU()
        if verbose:
            LOGGER.info(f"{colorstr('activation:')} {act}")  # print

    if verbose:
        LOGGER.info(f"\n{'':>3}{'from':>20}{'n':>3}{'params':>10}  {'module':<45}{'arguments':<30}")
    ch = [ch]
    layers, save, c2 = [], [], ch[-1]  # layers, savelist, ch out
    for i, (f, n, m, args) in enumerate(d["backbone"] + d["head"]):  # from, number, module, args
        m = getattr(torch.nn, m[3:]) if "nn." in m else globals()[m]  # get module
        for j, a in enumerate(args):
            if isinstance(a, str):
                with contextlib.suppress(ValueError):
                    args[j] = locals()[a] if a in locals() else ast.literal_eval(a)

        n = n_ = max(round(n * depth), 1) if n > 1 else n  # depth gain
        if m in (
            Classify,
            Conv,
            ConvTranspose,
            GhostConv,
            Bottleneck,
            GhostBottleneck,
            SPP,
            SPPF,
            DWConv,
            Focus,
            BottleneckCSP,
            C1,
            C2,
            C2f,
            C2fAttn,
            C3,
            C3TR,
            C3Ghost,
            nn.ConvTranspose2d,
            DWConvTranspose2d,
            C3x,
            RepC3,
        ):
            c1, c2 = ch[f], args[0]
            if c2 != nc:  # if c2 not equal to number of classes (i.e. for Classify() output)
                c2 = make_divisible(min(c2, max_channels) * width, 8)
            if m is C2fAttn:
                args[1] = make_divisible(min(args[1], max_channels // 2) * width, 8)  # embed channels
                args[2] = int(
                    max(round(min(args[2], max_channels // 2 // 32)) * width, 1) if args[2] > 1 else args[2]
                )  # num heads

            args = [c1, c2, *args[1:]]
            if m in (BottleneckCSP, C1, C2, C2f, C2fAttn, C3, C3TR, C3Ghost, C3x, RepC3):
                args.insert(2, n)  # number of repeats
                n = 1
        elif m is AIFI:
            args = [ch[f], *args]
        elif m in (HGStem, HGBlock):
            c1, cm, c2 = ch[f], args[0], args[1]
            args = [c1, cm, c2, *args[2:]]
            if m is HGBlock:
                args.insert(4, n)  # number of repeats
                n = 1
        elif m is ResNetLayer:
            c2 = args[1] if args[3] else args[1] * 4
        elif m is nn.BatchNorm2d:
            args = [ch[f]]
        elif m is Concat:
            c2 = sum(ch[x] for x in f)
        elif m in (Detect, WorldDetect, Segment, Pose, OBB, ImagePoolingAttn):
            args.append([ch[x] for x in f])
            if m is Segment:
                args[2] = make_divisible(min(args[2], max_channels) * width, 8)
        elif m is RTDETRDecoder:  # special case, channels arg must be passed in index 1
            args.insert(1, [ch[x] for x in f])
        else:
            c2 = ch[f]

        m_ = nn.Sequential(*(m(*args) for _ in range(n))) if n > 1 else m(*args)  # module
        t = str(m)[8:-2].replace("__main__.", "")  # module type
        m.np = sum(x.numel() for x in m_.parameters())  # number params
        m_.i, m_.f, m_.type = i, f, t  # attach index, 'from' index, type
        if verbose:
            LOGGER.info(f"{i:>3}{str(f):>20}{n_:>3}{m.np:10.0f}  {t:<45}{str(args):<30}")  # print
        save.extend(x % i for x in ([f] if isinstance(f, int) else f) if x != -1)  # append to savelist
        layers.append(m_)
        if i == 0:
            ch = []
        ch.append(c2)
    return nn.Sequential(*layers), sorted(save)

to-list：

• 配置解读
• 模型多任务设计
• 配置修改
• dataloader修改
• loss 回传机制修改
• 多任务训练