# Parameters
nc: 1000  # 数据集有多少类别
scales:   # 调整YOLO模型的深度、宽度和通道数，通过选择不同的规模，可以根据具体的需求来调整模型的大小和性能，从而实现更好的检测结果。
  # 网络规模：[深度、宽度和通道数]
  n: [0.33, 0.25, 1024]       # n: 较小的规模
  s: [0.33, 0.50, 1024]       # s: 小规模
  m: [0.67, 0.75, 1024]       # m: 中等规模
  l: [1.00, 1.00, 1024]       # l: 大规模
  x: [1.00, 1.25, 1024]       # x: 最大规模

# YOLOv8.0n backbone
backbone:
  # [ 从哪层获取输入（-1是上一层，[-1,6]是从上一层和第6层）, 模块重复次数, 模块名字（Conv是卷积层）, args]
  - [-1, 1, Conv, [64, 3, 2]]   # 0-P1/2  第 0 层：P1是第1特征层，缩小为输入图像的1/2，64代表输出通道数，3代表卷积核大小k，2代表stride步长
  - [-1, 1, Conv, [128, 3, 2]]  # 1-P2/4  第 1 层：P2是第2特征层，缩小为输入图像的1/4，128代表输出通道数，3代表卷积核大小k，2代表stride步长
  - [-1, 3, C2f, [128, True]]             第 2 层：本层是C2f模块，3代表本层重复3次。128代表输出通道数，True表示Bottleneck有shortcut。
  - [-1, 1, Conv, [256, 3, 2]]  # 3-P3/8  P3是第3特征层，缩小为输入图像的1/8
  - [-1, 6, C2f, [256, True]]
  - [-1, 1, Conv, [512, 3, 2]]  # 5-P4/16  P4是第4特征层，缩小为输入图像的1/16
  - [-1, 6, C2f, [512, True]]
  - [-1, 1, Conv, [1024, 3, 2]]  # 7-P5/32  P5是第5特征层，缩小为输入图像的1/32
  - [-1, 3, C2f, [1024, True]]

# YOLOv8.0n head
head:
  - [-1, 1, Classify, [nc]]  # Classify

0 0.329611 0.329853 0.339493 0.259214
0 0.698680 0.656634 0.339493 0.266585
0 0.770694 0.244472 0.318917 0.194103
0 0.813131 0.104423 0.073300 0.063882
类别标签   目标中心点坐标x    目标中心点坐标y    宽度     高度
类别标签：此处的序号是按照Make Sense中的标签"顺序"排列的，0 是第一个类别

import argparse
import contextlib
import os
import platform
import sys
from copy import deepcopy
from pathlib import Path

FILE = Path(__file__).resolve()
ROOT = FILE.parents[1]  # YOLOv5 root directory
if str(ROOT) not in sys.path:
    sys.path.append(str(ROOT))  # add ROOT to PATH
if platform.system() != 'Windows':
    ROOT = Path(os.path.relpath(ROOT, Path.cwd()))  # relative

from models.common import *  # noqa
from models.experimental import *  # noqa
from utils.autoanchor import check_anchor_order
from utils.general import LOGGER, check_version, check_yaml, make_divisible, print_args
from utils.plots import feature_visualization
from utils.torch_utils import (fuse_conv_and_bn, initialize_weights, model_info, profile, scale_img, select_device,
                               time_sync)

try:
    import thop  # for FLOPs computation
except ImportError:
    thop = None


class Detect(nn.Module):
    # YOLOv5 Detect head for detection models
    stride = None  # strides computed during build
    dynamic = False  # force grid reconstruction
    export = False  # export mode

    def __init__(self, nc=80, anchors=(), ch=(), inplace=True):  # detection layer
        super().__init__()
        self.nc = nc  # number of classes
        self.no = nc + 5  # number of outputs per anchor
        self.nl = len(anchors)  # number of detection layers
        self.na = len(anchors[0]) // 2  # number of anchors
        self.grid = [torch.empty(0) for _ in range(self.nl)]  # init grid
        self.anchor_grid = [torch.empty(0) for _ in range(self.nl)]  # init anchor grid
        self.register_buffer('anchors', torch.tensor(anchors).float().view(self.nl, -1, 2))  # shape(nl,na,2)
        self.m = nn.ModuleList(nn.Conv2d(x, self.no * self.na, 1) for x in ch)  # output conv
        self.inplace = inplace  # use inplace ops (e.g. slice assignment)

    def forward(self, x):
        z = []  # inference output
        for i in range(self.nl):
            x[i] = self.m[i](x[i])  # conv
            bs, _, ny, nx = x[i].shape  # x(bs,255,20,20) to x(bs,3,20,20,85)
            x[i] = x[i].view(bs, self.na, self.no, ny, nx).permute(0, 1, 3, 4, 2).contiguous()

            if not self.training:  # inference
                if self.dynamic or self.grid[i].shape[2:4] != x[i].shape[2:4]:
                    self.grid[i], self.anchor_grid[i] = self._make_grid(nx, ny, i)

                if isinstance(self, Segment):  # (boxes + masks)
                    xy, wh, conf, mask = x[i].split((2, 2, self.nc + 1, self.no - self.nc - 5), 4)
                    xy = (xy.sigmoid() * 2 + self.grid[i]) * self.stride[i]  # xy
                    wh = (wh.sigmoid() * 2) ** 2 * self.anchor_grid[i]  # wh
                    y = torch.cat((xy, wh, conf.sigmoid(), mask), 4)
                else:  # Detect (boxes only)
                    xy, wh, conf = x[i].sigmoid().split((2, 2, self.nc + 1), 4)
                    xy = (xy * 2 + self.grid[i]) * self.stride[i]  # xy
                    wh = (wh * 2) ** 2 * self.anchor_grid[i]  # wh
                    y = torch.cat((xy, wh, conf), 4)
                z.append(y.view(bs, self.na * nx * ny, self.no))

        return x if self.training else (torch.cat(z, 1), ) if self.export else (torch.cat(z, 1), x)

    def _make_grid(self, nx=20, ny=20, i=0, torch_1_10=check_version(torch.__version__, '1.10.0')):
        d = self.anchors[i].device
        t = self.anchors[i].dtype
        shape = 1, self.na, ny, nx, 2  # grid shape
        y, x = torch.arange(ny, device=d, dtype=t), torch.arange(nx, device=d, dtype=t)
        yv, xv = torch.meshgrid(y, x, indexing='ij') if torch_1_10 else torch.meshgrid(y, x)  # torch>=0.7 compatibility
        grid = torch.stack((xv, yv), 2).expand(shape) - 0.5  # add grid offset, i.e. y = 2.0 * x - 0.5
        anchor_grid = (self.anchors[i] * self.stride[i]).view((1, self.na, 1, 1, 2)).expand(shape)
        return grid, anchor_grid


class Segment(Detect):
    # YOLOv5 Segment head for segmentation models
    def __init__(self, nc=80, anchors=(), nm=32, npr=256, ch=(), inplace=True):
        super().__init__(nc, anchors, ch, inplace)
        self.nm = nm  # number of masks
        self.npr = npr  # number of protos
        self.no = 5 + nc + self.nm  # number of outputs per anchor
        self.m = nn.ModuleList(nn.Conv2d(x, self.no * self.na, 1) for x in ch)  # output conv
        self.proto = Proto(ch[0], self.npr, self.nm)  # protos
        self.detect = Detect.forward

    def forward(self, x):
        p = self.proto(x[0])
        x = self.detect(self, x)
        return (x, p) if self.training else (x[0], p) if self.export else (x[0], p, x[1])


class BaseModel(nn.Module):
    # YOLOv5 base model
    def forward(self, x, profile=False, visualize=False):
        return self._forward_once(x, profile, visualize)  # single-scale inference, train

    def _forward_once(self, x, profile=False, visualize=False):
        y, dt = [], []  # outputs
        for m in self.model:
            if m.f != -1:  # if not from previous layer
                x = y[m.f] if isinstance(m.f, int) else [x if j == -1 else y[j] for j in m.f]  # from earlier layers
            if profile:
                self._profile_one_layer(m, x, dt)
            x = m(x)  # run
            y.append(x if m.i in self.save else None)  # save output
            if visualize:
                feature_visualization(x, m.type, m.i, save_dir=visualize)
        return x

    def _profile_one_layer(self, m, x, dt):
        c = m == self.model[-1]  # is final layer, copy input as inplace fix
        o = thop.profile(m, inputs=(x.copy() if c else x, ), verbose=False)[0] / 1E9 * 2 if thop else 0  # FLOPs
        t = time_sync()
        for _ in range(10):
            m(x.copy() if c else x)
        dt.append((time_sync() - t) * 100)
        if m == self.model[0]:
            LOGGER.info(f"{'time (ms)':>10s} {'GFLOPs':>10s} {'params':>10s}  module")
        LOGGER.info(f'{dt[-1]:10.2f} {o:10.2f} {m.np:10.0f}  {m.type}')
        if c:
            LOGGER.info(f"{sum(dt):10.2f} {'-':>10s} {'-':>10s}  Total")

    def fuse(self):  # fuse model Conv2d() + BatchNorm2d() layers
        LOGGER.info('Fusing layers... ')
        for m in self.model.modules():
            if isinstance(m, (Conv, DWConv)) and hasattr(m, 'bn'):
                m.conv = fuse_conv_and_bn(m.conv, m.bn)  # update conv
                delattr(m, 'bn')  # remove batchnorm
                m.forward = m.forward_fuse  # update forward
        self.info()
        return self

    def info(self, verbose=False, img_size=640):  # print model information
        model_info(self, verbose, img_size)

    def _apply(self, fn):
        # Apply to(), cpu(), cuda(), half() to model tensors that are not parameters or registered buffers
        self = super()._apply(fn)
        m = self.model[-1]  # Detect()
        if isinstance(m, (Detect, Segment)):
            m.stride = fn(m.stride)
            m.grid = list(map(fn, m.grid))
            if isinstance(m.anchor_grid, list):
                m.anchor_grid = list(map(fn, m.anchor_grid))
        return self


class DetectionModel(BaseModel):
    # YOLOv5 detection model
    def __init__(self, cfg='yolov5s.yaml', ch=3, nc=None, anchors=None):  # model, input channels, number of classes
        super().__init__()
        if isinstance(cfg, dict):
            self.yaml = cfg  # model dict
        else:  # is *.yaml
            import yaml  # for torch hub
            self.yaml_file = Path(cfg).name
            with open(cfg, encoding='ascii', errors='ignore') as f:
                self.yaml = yaml.safe_load(f)  # model 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
        if anchors:
            LOGGER.info(f'Overriding model.yaml anchors with anchors={anchors}')
            self.yaml['anchors'] = round(anchors)  # override yaml value
        self.model, self.save = parse_model(deepcopy(self.yaml), ch=[ch])  # model, savelist
        self.names = [str(i) for i in range(self.yaml['nc'])]  # default names
        self.inplace = self.yaml.get('inplace', True)

        # Build strides, anchors
        m = self.model[-1]  # Detect()
        if isinstance(m, (Detect, Segment)):
            s = 256  # 2x min stride
            m.inplace = self.inplace
            forward = lambda x: self.forward(x)[0] if isinstance(m, Segment) else self.forward(x)
            m.stride = torch.tensor([s / x.shape[-2] for x in forward(torch.zeros(1, ch, s, s))])  # forward
            check_anchor_order(m)
            m.anchors /= m.stride.view(-1, 1, 1)
            self.stride = m.stride
            self._initialize_biases()  # only run once

        # Init weights, biases
        initialize_weights(self)
        self.info()
        LOGGER.info('')

    def forward(self, x, augment=False, profile=False, visualize=False):
        if augment:
            return self._forward_augment(x)  # augmented inference, None
        return self._forward_once(x, profile, visualize)  # single-scale inference, train

    def _forward_augment(self, x):
        img_size = x.shape[-2:]  # height, width
        s = [1, 0.83, 0.67]  # scales
        f = [None, 3, None]  # flips (2-ud, 3-lr)
        y = []  # outputs
        for si, fi in zip(s, f):
            xi = scale_img(x.flip(fi) if fi else x, si, gs=int(self.stride.max()))
            yi = self._forward_once(xi)[0]  # forward
            # cv2.imwrite(f'img_{si}.jpg', 255 * xi[0].cpu().numpy().transpose((1, 2, 0))[:, :, ::-1])  # save
            yi = self._descale_pred(yi, fi, si, img_size)
            y.append(yi)
        y = self._clip_augmented(y)  # clip augmented tails
        return torch.cat(y, 1), None  # augmented inference, train

    def _descale_pred(self, p, flips, scale, img_size):
        # de-scale predictions following augmented inference (inverse operation)
        if self.inplace:
            p[..., :4] /= scale  # de-scale
            if flips == 2:
                p[..., 1] = img_size[0] - p[..., 1]  # de-flip ud
            elif flips == 3:
                p[..., 0] = img_size[1] - p[..., 0]  # de-flip lr
        else:
            x, y, wh = p[..., 0:1] / scale, p[..., 1:2] / scale, p[..., 2:4] / scale  # de-scale
            if flips == 2:
                y = img_size[0] - y  # de-flip ud
            elif flips == 3:
                x = img_size[1] - x  # de-flip lr
            p = torch.cat((x, y, wh, p[..., 4:]), -1)
        return p

    def _clip_augmented(self, y):
        # Clip YOLOv5 augmented inference tails
        nl = self.model[-1].nl  # number of detection layers (P3-P5)
        g = sum(4 ** x for x in range(nl))  # grid points
        e = 1  # exclude layer count
        i = (y[0].shape[1] // g) * sum(4 ** x for x in range(e))  # indices
        y[0] = y[0][:, :-i]  # large
        i = (y[-1].shape[1] // g) * sum(4 ** (nl - 1 - x) for x in range(e))  # indices
        y[-1] = y[-1][:, i:]  # small
        return y

    def _initialize_biases(self, cf=None):  # initialize biases into Detect(), cf is class frequency
        # https://arxiv.org/abs/1708.02002 section 3.3
        # cf = torch.bincount(torch.tensor(np.concatenate(dataset.labels, 0)[:, 0]).long(), minlength=nc) + 1.
        m = self.model[-1]  # Detect() module
        for mi, s in zip(m.m, m.stride):  # from
            b = mi.bias.view(m.na, -1)  # conv.bias(255) to (3,85)
            b.data[:, 4] += math.log(8 / (640 / s) ** 2)  # obj (8 objects per 640 image)
            b.data[:, 5:5 + m.nc] += math.log(0.6 / (m.nc - 0.99999)) if cf is None else torch.log(cf / cf.sum())  # cls
            mi.bias = torch.nn.Parameter(b.view(-1), requires_grad=True)


Model = DetectionModel  # retain YOLOv5 'Model' class for backwards compatibility


class SegmentationModel(DetectionModel):
    # YOLOv5 segmentation model
    def __init__(self, cfg='yolov5s-seg.yaml', ch=3, nc=None, anchors=None):
        super().__init__(cfg, ch, nc, anchors)


class ClassificationModel(BaseModel):
    # YOLOv5 classification model
    def __init__(self, cfg=None, model=None, nc=1000, cutoff=10):  # yaml, model, number of classes, cutoff index
        super().__init__()
        self._from_detection_model(model, nc, cutoff) if model is not None else self._from_yaml(cfg)

    def _from_detection_model(self, model, nc=1000, cutoff=10):
        # Create a YOLOv5 classification model from a YOLOv5 detection model
        if isinstance(model, DetectMultiBackend):
            model = model.model  # unwrap DetectMultiBackend
        model.model = model.model[:cutoff]  # backbone
        m = model.model[-1]  # last layer
        ch = m.conv.in_channels if hasattr(m, 'conv') else m.cv1.conv.in_channels  # ch into module
        c = Classify(ch, nc)  # Classify()
        c.i, c.f, c.type = m.i, m.f, 'models.common.Classify'  # index, from, type
        model.model[-1] = c  # replace
        self.model = model.model
        self.stride = model.stride
        self.save = []
        self.nc = nc

    def _from_yaml(self, cfg):
        # Create a YOLOv5 classification model from a *.yaml file
        self.model = None


def parse_model(d, ch):  # model_dict, input_channels(3)
    # Parse a YOLOv5 model.yaml dictionary
    LOGGER.info(f"\n{'':>3}{'from':>18}{'n':>3}{'params':>10}  {'module':<40}{'arguments':<30}")
    anchors, nc, gd, gw, act = d['anchors'], d['nc'], d['depth_multiple'], d['width_multiple'], d.get('activation')
    if act:
        Conv.default_act = eval（act)  # redefine default activation, i.e. Conv.default_act = nn.SiLU()
        LOGGER.info(f"{colorstr('activation:')} {act}")  # print
    na = (len(anchors[0]) // 2) if isinstance(anchors, list) else anchors  # number of anchors
    no = na * (nc + 5)  # number of outputs = anchors * (classes + 5)

    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 = eval（m) if isinstance(m, str) else m  # eval strings
        for j, a in enumerate(args):
            with contextlib.suppress(NameError):
                args[j] = eval（a) if isinstance(a, str) else a  # eval strings

        n = n_ = max(round(n * gd), 1) if n > 1 else n  # depth gain
        if m in {
                Conv, GhostConv, Bottleneck, GhostBottleneck, SPP, SPPF, DWConv, MixConv2d, Focus, CrossConv,
                BottleneckCSP, C3, C3TR, C3SPP, C3Ghost, nn.ConvTranspose2d, DWConvTranspose2d, C3x}:
            c1, c2 = ch[f], args[0]
            if c2 != no:  # if not output
                c2 = make_divisible(c2 * gw, 8)

            args = [c1, c2, *args[1:]]
            if m in {BottleneckCSP, C3, C3TR, C3Ghost, C3x}:
                args.insert(2, n)  # number of repeats
                n = 1
        elif m is nn.BatchNorm2d:
            args = [ch[f]]
        elif m is Concat:
            c2 = sum(ch[x] for x in f)
        # TODO: channel, gw, gd
        elif m in {Detect, Segment}:
            args.append([ch[x] for x in f])
            if isinstance(args[1], int):  # number of anchors
                args[1] = [list(range(args[1] * 2))] * len(f)
            if m is Segment:
                args[3] = make_divisible(args[3] * gw, 8)
        elif m is Contract:
            c2 = ch[f] * args[0] ** 2
        elif m is Expand:
            c2 = ch[f] // args[0] ** 2
        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
        np = sum(x.numel() for x in m_.parameters())  # number params
        m_.i, m_.f, m_.type, m_.np = i, f, t, np  # attach index, 'from' index, type, number params
        LOGGER.info(f'{i:>3}{str(f):>18}{n_:>3}{np:10.0f}  {t:<40}{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)


if __name__ == '__main__':
    parser = argparse.ArgumentParser()
    parser.add_argument('--cfg', type=str, default='yolov5s.yaml', help='model.yaml')
    parser.add_argument('--batch-size', type=int, default=1, help='total batch size for all GPUs')
    parser.add_argument('--device', default='', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
    parser.add_argument('--profile', action='store_true', help='profile model speed')
    parser.add_argument('--line-profile', action='store_true', help='profile model speed layer by layer')
    parser.add_argument('--test', action='store_true', help='test all yolo*.yaml')
    opt = parser.parse_args()
    opt.cfg = check_yaml(opt.cfg)  # check YAML
    print_args(vars(opt))
    device = select_device(opt.device)

    # Create model
    im = torch.rand(opt.batch_size, 3, 640, 640).to(device)
    model = Model(opt.cfg).to(device)

    # Options
    if opt.line_profile:  # profile layer by layer
        model(im, profile=True)

    elif opt.profile:  # profile forward-backward
        results = profile(input=im, ops=[model], n=3)

    elif opt.test:  # test all models
        for cfg in Path(ROOT / 'models').rglob('yolo*.yaml'):
            try:
                _ = Model(cfg)
            except Exception as e:
                print(f'Error in {cfg}: {e}')

    else:  # report fused model summary
        model.fuse()

# Parameters
nc: 80  # number of classes
scales: # model compound scaling constants, i.e. 'model=yolov5n.yaml' will call yolov5.yaml with scale 'n'
  # [depth, width, max_channels]
  n: [0.33, 0.25, 1024]
  s: [0.33, 0.50, 1024]
  m: [0.67, 0.75, 1024]
  l: [1.00, 1.00, 1024]
  x: [1.33, 1.25, 1024]

# YOLOv5 v6.0 backbone
backbone:
  # [from, number, module, args]
  [[-1, 1, Conv, [64, 6, 2, 2]],  # 0-P1/2
   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
   [-1, 3, C3, [128]],
   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
   [-1, 6, C3, [256]],
   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
   [-1, 9, C3, [512]],
   [-1, 1, Conv, [1024, 3, 2]],  # 7-P5/32
   [-1, 3, C3, [1024]],
   [-1, 1, SPPF, [1024, 5]],  # 9
  ]

# YOLOv5 v6.0 head
head:
  [[-1, 1, Conv, [512, 1, 1]],
   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
   [-1, 3, C3, [512, False]],  # 13

   [-1, 1, Conv, [256, 1, 1]],
   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
   [-1, 3, C3, [256, False]],  # 17 (P3/8-small)

   [-1, 1, Conv, [256, 3, 2]],
   [[-1, 14], 1, Concat, [1]],  # cat head P4
   [-1, 3, C3, [512, False]],  # 20 (P4/16-medium)

   [-1, 1, Conv, [512, 3, 2]],
   [[-1, 10], 1, Concat, [1]],  # cat head P5
   [-1, 3, C3, [1024, False]],  # 23 (P5/32-large)

   [[17, 20, 23], 1, Detect, [nc]],  # Detect(P3, P4, P5)
  ]

import torch.nn.functional as F

class CARAFE(nn.Module):     
    # CARAFE: Content-Aware ReAssembly of FEatures       https://arxiv.org/pdf/1905.02188.pdf
    def __init__(self, c1, c2, kernel_size=3, up_factor=2):
        super(CARAFE, self).__init__()
        self.kernel_size = kernel_size
        self.up_factor = up_factor
        self.down = nn.Conv2d(c1, c1 // 4, 1)
        self.encoder = nn.Conv2d(c1 // 4, self.up_factor ** 2 * self.kernel_size ** 2,
                                 self.kernel_size, 1, self.kernel_size // 2)
        self.out = nn.Conv2d(c1, c2, 1)

    def forward(self, x):
        N, C, H, W = x.size()
        # N,C,H,W -> N,C,delta*H,delta*W
        # kernel prediction module
        kernel_tensor = self.down(x)  # (N, Cm, H, W)
        kernel_tensor = self.encoder(kernel_tensor)  # (N, S^2 * Kup^2, H, W)
        kernel_tensor = F.pixel_shuffle(kernel_tensor, self.up_factor)  # (N, S^2 * Kup^2, H, W)->(N, Kup^2, S*H, S*W)
        kernel_tensor = F.softmax(kernel_tensor, dim=1)  # (N, Kup^2, S*H, S*W)
        kernel_tensor = kernel_tensor.unfold(2, self.up_factor, step=self.up_factor) # (N, Kup^2, H, W*S, S)
        kernel_tensor = kernel_tensor.unfold(3, self.up_factor, step=self.up_factor) # (N, Kup^2, H, W, S, S)
        kernel_tensor = kernel_tensor.reshape(N, self.kernel_size ** 2, H, W, self.up_factor ** 2) # (N, Kup^2, H, W, S^2)
        kernel_tensor = kernel_tensor.permute(0, 2, 3, 1, 4)  # (N, H, W, Kup^2, S^2)

        # content-aware reassembly module
        # tensor.unfold: dim, size, step
        x = F.pad(x, pad=(self.kernel_size // 2, self.kernel_size // 2,
                                          self.kernel_size // 2, self.kernel_size // 2),
                          				  mode='constant', value=0) # (N, C, H+Kup//2+Kup//2, W+Kup//2+Kup//2)
        x = x.unfold(2, self.kernel_size, step=1) # (N, C, H, W+Kup//2+Kup//2, Kup)
        x = x.unfold(3, self.kernel_size, step=1) # (N, C, H, W, Kup, Kup)
        x = x.reshape(N, C, H, W, -1) # (N, C, H, W, Kup^2)
        x = x.permute(0, 2, 3, 1, 4)  # (N, H, W, C, Kup^2)

        out_tensor = torch.matmul(x, kernel_tensor)  # (N, H, W, C, S^2)
        out_tensor = out_tensor.reshape(N, H, W, -1)
        out_tensor = out_tensor.permute(0, 3, 1, 2)
        out_tensor = F.pixel_shuffle(out_tensor, self.up_factor)
        out_tensor = self.out(out_tensor)
        return out_tensor

修改前：
 if m in {
                Conv, GhostConv, Bottleneck, GhostBottleneck, SPP, SPPF, DWConv, MixConv2d, Focus, CrossConv,
                BottleneckCSP, C3, C3TR, C3SPP, C3Ghost, nn.ConvTranspose2d, DWConvTranspose2d, C3x}:  
                
修改后：
 if m in {
                Conv, GhostConv, Bottleneck, GhostBottleneck, SPP, SPPF, DWConv, MixConv2d, Focus, CrossConv,
                BottleneckCSP, C3, C3TR, C3SPP, C3Ghost, nn.ConvTranspose2d, DWConvTranspose2d, C3x, CARAFE}:

# Parameters
nc: 80  # number of classes
scales: # model compound scaling constants, i.e. 'model=yolov5n.yaml' will call yolov5.yaml with scale 'n'
  # [depth, width, max_channels]
  n: [0.33, 0.25, 1024]
  s: [0.33, 0.50, 1024]
  m: [0.67, 0.75, 1024]
  l: [1.00, 1.00, 1024]
  x: [1.33, 1.25, 1024]

# YOLOv5 v6.0 backbone
backbone:
  # [from, number, module, args]
  [[-1, 1, Conv, [64, 6, 2, 2]],  # 0-P1/2
   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
   [-1, 3, C3, [128]],
   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
   [-1, 6, C3, [256]],
   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
   [-1, 9, C3, [512]],
   [-1, 1, Conv, [1024, 3, 2]],  # 7-P5/32
   [-1, 3, C3, [1024]],
   [-1, 1, SPPF, [1024, 5]],  # 9
  ]

# YOLOv5 v6.0 head
head:
  [[-1, 1, Conv, [512, 1, 1]],
   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
   [-1, 3, C3, [512, False]],  # 13

   [-1, 1, Conv, [256, 1, 1]],
   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
   [-1, 3, C3, [256, False]],  # 17 (P3/8-small)

   [-1, 1, Conv, [256, 3, 2]],
   [[-1, 14], 1, Concat, [1]],  # cat head P4
   [-1, 3, C3, [512, False]],  # 20 (P4/16-medium)

   [-1, 1, Conv, [512, 3, 2]],
   [[-1, 10], 1, Concat, [1]],  # cat head P5
   [-1, 3, C3, [1024, False]],  # 23 (P5/32-large)

   [[17, 20, 23], 1, Detect, [nc]],  # Detect(P3, P4, P5)
  ]

backbone:
  # [from, number, module, args]
  [[-1, 1, Conv, [64, 6, 2, 2]],  # 0-P1/2
   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
   [-1, 3, C3, [128]],
   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
   [-1, 6, C3, [256]],
   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
   [-1, 9, C3, [512]],
   [-1, 1, Conv, [1024, 3, 2]],  # 7-P5/32
   [-1, 3, C3, [1024]],
   [-1, 1, SPPF, [1024, 5]],  # 9
   # [-1, 1, ASPP, [512]],  # 9
   # [-1, 1, SPP, [1024]],
   # [-1, 1, SimSPPF, [1024, 5]],
   # [-1, 1, BasicRFB, [1024]],
   # [-1, 1, SPPCSPC, [1024]],
   # [-1, 1, SPPFCSPC, [1024, 5]], # 🍀
  ]

class SPP(nn.Module):
    # Spatial Pyramid Pooling (SPP) layer https://arxiv.org/abs/1406.4729
    def __init__(self, c1, c2, k=(5, 9, 13)):
        super().__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)
        with warnings.catch_warnings():
            warnings.simplefilter('ignore')  # suppress torch 1.9.0 max_pool2d() warning
            return self.cv2(torch.cat([x] + [m(x) for m in self.m], 1))

class SPPF(nn.Module):
    # Spatial Pyramid Pooling - Fast (SPPF) layer for YOLOv5 by Glenn Jocher
    def __init__(self, c1, c2, k=5):  # equivalent to SPP(k=(5, 9, 13))
        super().__init__()
        c_ = c1 // 2  # hidden channels
        self.cv1 = Conv(c1, c_, 1, 1)
        self.cv2 = Conv(c_ * 4, c2, 1, 1)
        self.m = nn.MaxPool2d(kernel_size=k, stride=1, padding=k // 2)

    def forward(self, x):
        x = self.cv1(x)
        with warnings.catch_warnings():
            warnings.simplefilter('ignore')  # suppress torch 1.9.0 max_pool2d() warning
            y1 = self.m(x)
            y2 = self.m(y1)
            return self.cv2(torch.cat((x, y1, y2, self.m(y2)), 1))

class SimConv(nn.Module):
    '''Normal Conv with ReLU activation'''
    def __init__(self, in_channels, out_channels, kernel_size, stride, groups=1, bias=False):
        super().__init__()
        padding = kernel_size // 2
        self.conv = nn.Conv2d(
            in_channels,
            out_channels,
            kernel_size=kernel_size,
            stride=stride,
            padding=padding,
            groups=groups,
            bias=bias,
        )
        self.bn = nn.BatchNorm2d(out_channels)
        self.act = nn.ReLU()

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

    def forward_fuse(self, x):
        return self.act(self.conv(x))

class SimSPPF(nn.Module):
    '''Simplified SPPF with ReLU activation'''
    def __init__(self, in_channels, out_channels, kernel_size=5):
        super().__init__()
        c_ = in_channels // 2  # hidden channels
        self.cv1 = SimConv(in_channels, c_, 1, 1)
        self.cv2 = SimConv(c_ * 4, out_channels, 1, 1)
        self.m = nn.MaxPool2d(kernel_size=kernel_size, stride=1, padding=kernel_size // 2)

    def forward(self, x):
        x = self.cv1(x)
        with warnings.catch_warnings():
            warnings.simplefilter('ignore')
            y1 = self.m(x)
            y2 = self.m(y1)
            return self.cv2(torch.cat([x, y1, y2, self.m(y2)], 1))

# without BN version
class ASPP(nn.Module):
    def __init__(self, in_channel=512, out_channel=256):
        super(ASPP, self).__init__()
        self.mean = nn.AdaptiveAvgPool2d((1, 1))  # (1,1)means ouput_dim
        self.conv = nn.Conv2d(in_channel,out_channel, 1, 1)
        self.atrous_block1 = nn.Conv2d(in_channel, out_channel, 1, 1)
        self.atrous_block6 = nn.Conv2d(in_channel, out_channel, 3, 1, padding=6, dilation=6)
        self.atrous_block12 = nn.Conv2d(in_channel, out_channel, 3, 1, padding=12, dilation=12)
        self.atrous_block18 = nn.Conv2d(in_channel, out_channel, 3, 1, padding=18, dilation=18)
        self.conv_1x1_output = nn.Conv2d(out_channel * 5, out_channel, 1, 1)

    def forward(self, x):
        size = x.shape[2:]

        image_features = self.mean(x)
        image_features = self.conv(image_features)
        image_features = F.upsample(image_features, size=size, mode='bilinear')

        atrous_block1 = self.atrous_block1(x)
        atrous_block6 = self.atrous_block6(x)
        atrous_block12 = self.atrous_block12(x)
        atrous_block18 = self.atrous_block18(x)

        net = self.conv_1x1_output(torch.cat([image_features, atrous_block1, atrous_block6,
                                              atrous_block12, atrous_block18], dim=1))
        return net

class BasicConv(nn.Module):

    def __init__(self, in_planes, out_planes, kernel_size, stride=1, padding=0, dilation=1, groups=1, relu=True, bn=True):
        super(BasicConv, self).__init__()
        self.out_channels = out_planes
        if bn:
            self.conv = nn.Conv2d(in_planes, out_planes, kernel_size=kernel_size, stride=stride, padding=padding, dilation=dilation, groups=groups, bias=False)
            self.bn = nn.BatchNorm2d(out_planes, eps=1e-5, momentum=0.01, affine=True)
            self.relu = nn.ReLU(inplace=True) if relu else None
        else:
            self.conv = nn.Conv2d(in_planes, out_planes, kernel_size=kernel_size, stride=stride, padding=padding, dilation=dilation, groups=groups, bias=True)
            self.bn = None
            self.relu = nn.ReLU(inplace=True) if relu else None

    def forward(self, x):
        x = self.conv(x)
        if self.bn is not None:
            x = self.bn(x)
        if self.relu is not None:
            x = self.relu(x)
        return x


class BasicRFB(nn.Module):

    def __init__(self, in_planes, out_planes, stride=1, scale=0.1, map_reduce=8, vision=1, groups=1):
        super(BasicRFB, self).__init__()
        self.scale = scale
        self.out_channels = out_planes
        inter_planes = in_planes // map_reduce

        self.branch0 = nn.Sequential(
            BasicConv(in_planes, inter_planes, kernel_size=1, stride=1, groups=groups, relu=False),
            BasicConv(inter_planes, 2 * inter_planes, kernel_size=(3, 3), stride=stride, padding=(1, 1), groups=groups),
            BasicConv(2 * inter_planes, 2 * inter_planes, kernel_size=3, stride=1, padding=vision, dilation=vision, relu=False, groups=groups)
        )
        self.branch1 = nn.Sequential(
            BasicConv(in_planes, inter_planes, kernel_size=1, stride=1, groups=groups, relu=False),
            BasicConv(inter_planes, 2 * inter_planes, kernel_size=(3, 3), stride=stride, padding=(1, 1), groups=groups),
            BasicConv(2 * inter_planes, 2 * inter_planes, kernel_size=3, stride=1, padding=vision + 2, dilation=vision + 2, relu=False, groups=groups)
        )
        self.branch2 = nn.Sequential(
            BasicConv(in_planes, inter_planes, kernel_size=1, stride=1, groups=groups, relu=False),
            BasicConv(inter_planes, (inter_planes // 2) * 3, kernel_size=3, stride=1, padding=1, groups=groups),
            BasicConv((inter_planes // 2) * 3, 2 * inter_planes, kernel_size=3, stride=stride, padding=1, groups=groups),
            BasicConv(2 * inter_planes, 2 * inter_planes, kernel_size=3, stride=1, padding=vision + 4, dilation=vision + 4, relu=False, groups=groups)
        )

        self.ConvLinear = BasicConv(6 * inter_planes, out_planes, kernel_size=1, stride=1, relu=False)
        self.shortcut = BasicConv(in_planes, out_planes, kernel_size=1, stride=stride, relu=False)
        self.relu = nn.ReLU(inplace=False)

    def forward(self, x):
        x0 = self.branch0(x)
        x1 = self.branch1(x)
        x2 = self.branch2(x)

        out = torch.cat((x0, x1, x2), 1)
        out = self.ConvLinear(out)
        short = self.shortcut(x)
        out = out * self.scale + short
        out = self.relu(out)

        return out

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))

import torch
import torch.nn as nn
import torch.nn.functional as F


class SiLU(nn.Module):
    @staticmethod
    def forward(x):
        return x * torch.sigmoid(x)


class Hardswish(nn.Module):
    @staticmethod
    def forward(x):
        return x * F.hardtanh(x + 3, 0.0, 6.0) / 6.0  # for TorchScript, CoreML and ONNX


class Mish(nn.Module):
    @staticmethod
    def forward(x):
        return x * F.softplus(x).tanh()


class MemoryEfficientMish(nn.Module):
    class F(torch.autograd.Function):

        @staticmethod
        def forward(ctx, x):
            ctx.save_for_backward(x)
            return x.mul(torch.tanh(F.softplus(x)))  # x * tanh(ln(1 + exp(x)))

        @staticmethod
        def backward(ctx, grad_output):
            x = ctx.saved_tensors[0]
            sx = torch.sigmoid(x)
            fx = F.softplus(x).tanh()
            return grad_output * (fx + x * sx * (1 - fx * fx))

    def forward(self, x):
        return self.F.apply(x)


class FReLU(nn.Module):
    def __init__(self, c1, k=3):  # ch_in, kernel
        super().__init__()
        self.conv = nn.Conv2d(c1, c1, k, 1, 1, groups=c1, bias=False)
        self.bn = nn.BatchNorm2d(c1)

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


class AconC(nn.Module):
    def __init__(self, c1):
        super().__init__()
        self.p1 = nn.Parameter(torch.randn(1, c1, 1, 1))
        self.p2 = nn.Parameter(torch.randn(1, c1, 1, 1))
        self.beta = nn.Parameter(torch.ones(1, c1, 1, 1))

    def forward(self, x):
        dpx = (self.p1 - self.p2) * x
        return dpx * torch.sigmoid(self.beta * dpx) + self.p2 * x


class MetaAconC(nn.Module):
    def __init__(self, c1, k=1, s=1, r=16):  # ch_in, kernel, stride, r
        super().__init__()
        c2 = max(r, c1 // r)
        self.p1 = nn.Parameter(torch.randn(1, c1, 1, 1))
        self.p2 = nn.Parameter(torch.randn(1, c1, 1, 1))
        self.fc1 = nn.Conv2d(c1, c2, k, s, bias=True)
        self.fc2 = nn.Conv2d(c2, c1, k, s, bias=True)

    def forward(self, x):
        y = x.mean(dim=2, keepdims=True).mean(dim=3, keepdims=True)
        beta = torch.sigmoid(self.fc2(self.fc1(y)))  # bug patch BN layers removed
        dpx = (self.p1 - self.p2) * x
        return dpx * torch.sigmoid(beta * dpx) + self.p2 * x

class Conv(nn.Module):
    default_act = nn.SiLU()  # 默认激活函数，选择你要更换的激活函数

    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()

default_act = nn.SiLU()  # 默认激活函数
default_act = nn.Identity()
default_act = nn.Tanh()
default_act = nn.Sigmoid()
default_act = nn.ReLU() 
default_act = nn.LeakyReLU(0.1)
default_act = nn.Hardswish() 
default_act = nn.SiLU() 
default_act = Mish()
default_act = FReLU(c2)
default_act = AconC(c2)
default_act = MetaAconC(c2) 
default_act = SiLU_beta(c2)
default_act = FReLU_noBN_biasFalse(c2)
default_act = FReLU_noBN_biasTrue(c2)

class BottleneckCSP(nn.Module):
    def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):  # ch_in, ch_out, number, shortcut, groups, expansion
        super().__init__()
        c_ = int(c2 * e)  # hidden channels
        self.cv1 = Conv(c1, c_, 1, 1)
        self.cv2 = nn.Conv2d(c1, c_, 1, 1, bias=False)
        self.cv3 = nn.Conv2d(c_, c_, 1, 1, bias=False)
        self.cv4 = Conv(2 * c_, c2, 1, 1)
        self.bn = nn.BatchNorm2d(2 * c_)  # applied to cat(cv2, cv3)
        self.act = nn.SiLU()   # 选择你要更换的激活函数

# ---------------------------GSConv Begin---------------------------
class Conv_Mish(nn.Module):
    # Standard convolution
    def __init__(self, c1, c2, k=1, s=1, p=None, g=1, act=True):  # ch_in, ch_out, kernel, stride, padding, groups
        super().__init__()
        self.conv = nn.Conv2d(c1, c2, k, s, autopad(k, p), groups=g, bias=False)
        self.bn = nn.BatchNorm2d(c2)
        self.act = nn.Mish() if act else nn.Identity()

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

    def forward_fuse(self, x):
        return self.act(self.conv(x))


class GSConv(nn.Module):
    # GSConv https://github.com/AlanLi1997/slim-neck-by-gsconv
    def __init__(self, c1, c2, k=1, s=1, g=1, act=True):
        super().__init__()
        c_ = c2 // 2
        self.cv1 = Conv_Mish(c1, c_, k, s, None, g, act)
        self.cv2 = Conv_Mish(c_, c_, 5, 1, None, c_, act)

    def forward(self, x):
        x1 = self.cv1(x)
        x2 = torch.cat((x1, self.cv2(x1)), 1)
        # shuffle
        # y = x2.reshape(x2.shape[0], 2, x2.shape[1] // 2, x2.shape[2], x2.shape[3])
        # y = y.permute(0, 2, 1, 3, 4)
        # return y.reshape(y.shape[0], -1, y.shape[3], y.shape[4])

        b, n, h, w = x2.data.size()
        b_n = b * n // 2
        y = x2.reshape(b_n, 2, h * w)
        y = y.permute(1, 0, 2)
        y = y.reshape(2, -1, n // 2, h, w)

        return torch.cat((y[0], y[1]), 1)


class GSConvns(GSConv):
    # GSConv with a normative-shuffle https://github.com/AlanLi1997/slim-neck-by-gsconv
    def __init__(self, c1, c2, k=1, s=1, g=1, act=True):
        super().__init__(c1, c2, k=1, s=1, g=1, act=True)
        c_ = c2 // 2
        self.shuf = nn.Conv2d(c_ * 2, c2, 1, 1, 0, bias=False)

    def forward(self, x):
        x1 = self.cv1(x)
        x2 = torch.cat((x1, self.cv2(x1)), 1)
        # normative-shuffle, TRT supported
        return nn.ReLU(self.shuf(x2))


class GSBottleneck(nn.Module):
    # GS Bottleneck https://github.com/AlanLi1997/slim-neck-by-gsconv
    def __init__(self, c1, c2, k=3, s=1, e=0.5):
        super().__init__()
        c_ = int(c2 * e)
        # for lighting
        self.conv_lighting = nn.Sequential(
            GSConv(c1, c_, 1, 1),
            GSConv(c_, c2, 3, 1, act=False))
        self.shortcut = Conv_Mish(c1, c2, 1, 1, act=False)

    def forward(self, x):
        return self.conv_lighting(x) + self.shortcut(x)


class VoVGSCSP(nn.Module):
    # VoVGSCSP module with GSBottleneck
    def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):
        super().__init__()
        c_ = int(c2 * e)  # hidden channels
        self.cv1 = Conv_Mish(c1, c_, 1, 1)
        self.cv2 = Conv_Mish(c1, c_, 1, 1)
        # self.gc1 = GSConv(c_, c_, 1, 1)
        # self.gc2 = GSConv(c_, c_, 1, 1)
        # self.gsb = GSBottleneck(c_, c_, 1, 1)
        self.gsb = nn.Sequential(*(GSBottleneck(c_, c_, e=1.0) for _ in range(n)))
        self.res = Conv_Mish(c_, c_, 3, 1, act=False)
        self.cv3 = Conv_Mish(2 * c_, c2, 1)  #

    def forward(self, x):
        x1 = self.gsb(self.cv1(x))
        y = self.cv2(x)
        return self.cv3(torch.cat((y, x1), dim=1))


class GSBottleneckC(GSBottleneck):
    # cheap GS Bottleneck https://github.com/AlanLi1997/slim-neck-by-gsconv
    def __init__(self, c1, c2, k=3, s=1):
        super().__init__(c1, c2, k, s)
        self.shortcut = DWConv(c1, c2, k, s, act=False)


class VoVGSCSPC(VoVGSCSP):
    # cheap VoVGSCSP module with GSBottleneck
    def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):
        super().__init__(c1, c2)
        c_ = int(c2 * 0.5)  # hidden channels
        self.gsb = GSBottleneckC(c_, c_, 1, 1)
# ---------------------------GSConv End---------------------------

if m in {
            Conv, GhostConv, Bottleneck, GhostBottleneck, SPP, SPPF, DWConv, MixConv2d, Focus, CrossConv,
            BottleneckCSP, C3, C3TR, C3SPP, C3Ghost, nn.ConvTranspose2d, DWConvTranspose2d, C3x, 
            GSConvns, VoVGSCSP, VoVGSCSPC}:     # 添加 GSConvns, VoVGSCSP, VoVGSCSPC
            c1, c2 = ch[f], args[0]
            if c2 != no:  # if not output
                c2 = make_divisible(c2 * gw, 8)

            args = [c1, c2, *args[1:]]
            if m in {BottleneckCSP, C3, C3TR, C3Ghost, C3x, VoVGSCSP, VoVGSCSPC}: # 添加 VoVGSCSP, VoVGSCSPC
                args.insert(2, n)  # number of repeats

    def fuse(self):  # fuse model Conv2d() + BatchNorm2d() layers
        LOGGER.info('Fusing layers... ')
        for m in self.model.modules():
            if isinstance(m, (Conv, DWConv)) and hasattr(m, 'bn'):
                m.conv = fuse_conv_and_bn(m.conv, m.bn)  # update conv
                delattr(m, 'bn')  # remove batchnorm
                m.forward = m.forward_fuse  # update forward

    def fuse(self):  # fuse model Conv2d() + BatchNorm2d() layers
        LOGGER.info('Fusing layers... ')
        for m in self.model.modules():
            if isinstance(m, (Conv, DWConv, Conv_Mish)) and hasattr(m, 'bn'):    # 添加 Conv_Mish
                m.conv = fuse_conv_and_bn(m.conv, m.bn)  # update conv
                delattr(m, 'bn')  # remove batchnorm
                m.forward = m.forward_fuse  # update forward

nc: 80  # number of classes
depth_multiple: 0.33  # model depth multiple
width_multiple: 0.50  # layer channel multiple
anchors:
  - [10,13, 16,30, 33,23]  # P3/8
  - [30,61, 62,45, 59,119]  # P4/16
  - [116,90, 156,198, 373,326]  # P5/32

# YOLOv5 v6.0 backbone
backbone:
  # [from, number, module, args]
  [[-1, 1, Conv, [64, 6, 2, 2]],  # 0-P1/2
   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
   [-1, 3, C3, [128]],
   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
   [-1, 6, C3, [256]],
   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
   [-1, 9, C3, [512]],
   [-1, 1, Conv, [1024, 3, 2]],  # 7-P5/32
   [-1, 3, C3, [1024]],
   [-1, 1, SPPF, [1024, 5]],  # 9
  ]

# YOLOv5 v6.0 head
head:
  [[-1, 1, GSConv, [512, 1, 1]],
   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
   [-1, 3, C3, [512, False]],  # 13

   [-1, 1, GSConv, [256, 1, 1]],
   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
   [-1, 3, C3, [256, False]],  # 17 (P3/8-small)

   [-1, 1, GSConv, [256, 3, 2]],
   [[-1, 14], 1, Concat, [1]],  # cat head P4
   [-1, 3, C3, [512, False]],  # 20 (P4/16-medium)

   [-1, 1, GSConv, [512, 3, 2]],
   [[-1, 10], 1, Concat, [1]],  # cat head P5
   [-1, 3, C3, [1024, False]],  # 23 (P5/32-large)

   [[17, 20, 23], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5)
  ]

# BiFPN 两个特征图add操作
class BiFPN_Add2(nn.Module):
    def __init__(self, c1, c2):
        super(BiFPN_Add2, self).__init__()
        # 设置可学习参数 nn.Parameter的作用是：将一个不可训练的类型Tensor转换成可以训练的类型parameter
        # 并且会向宿主模型注册该参数 成为其一部分 即model.parameters()会包含这个parameter
        # 从而在参数优化的时候可以自动一起优化
        self.w = nn.Parameter(torch.ones(2, dtype=torch.float32), requires_grad=True)
        self.epsilon = 0.0001
        self.conv = nn.Conv2d(c1, c2, kernel_size=1, stride=1, padding=0)
        self.silu = nn.SiLU()

    def forward(self, x):
        w = self.w
        weight = w / (torch.sum(w, dim=0) + self.epsilon)
        return self.conv(self.silu(weight[0] * x[0] + weight[1] * x[1]))


# 三个特征图add操作
class BiFPN_Add3(nn.Module):
    def __init__(self, c1, c2):
        super(BiFPN_Add3, self).__init__()
        self.w = nn.Parameter(torch.ones(3, dtype=torch.float32), requires_grad=True)
        self.epsilon = 0.0001
        self.conv = nn.Conv2d(c1, c2, kernel_size=1, stride=1, padding=0)
        self.silu = nn.SiLU()

    def forward(self, x):
        w = self.w
        weight = w / (torch.sum(w, dim=0) + self.epsilon)  
        # Fast normalized fusion
        return self.conv(self.silu(weight[0] * x[0] + weight[1] * x[1] + weight[2] * x[2]))

def parse_model(d, ch):  
        elif m is Concat:
            c2 = sum(ch[x] for x in f)
        elif m in [BiFPN_Add2, BiFPN_Add3]:     # 在 Concat 后，添加 BiFPN 结构
        	c2 = max([ch[x] for x in f)

from models.common import BiFPN_Add3, BiFPN_Add2

g0, g1, g2 = [], [], []  # optimizer parameter groups
    for v in model.modules():
    	······
        # BiFPN_Concat
        elif isinstance(v, BiFPN_Add2) and hasattr(v, 'w') and isinstance(v.w, nn.Parameter):
            g1.append(v.w)
        elif isinstance(v, BiFPN_Add3) and hasattr(v, 'w') and isinstance(v.w, nn.Parameter):
            g1.append(v.w)

# Parameters
nc: 80  # number of classes
depth_multiple: 0.33  # model depth multiple
width_multiple: 0.50  # layer channel multiple
anchors:
  - [10,13, 16,30, 33,23]  # P3/8
  - [30,61, 62,45, 59,119]  # P4/16
  - [116,90, 156,198, 373,326]  # P5/32

# YOLOv5 v6.0 backbone
backbone:
  # [from, number, module, args]
  [[-1, 1, Conv, [64, 6, 2, 2]],  # 0-P1/2
   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
   [-1, 3, C3, [128]],
   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
   [-1, 6, C3, [256]],
   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
   [-1, 9, C3, [512]],
   [-1, 1, Conv, [1024, 3, 2]],  # 7-P5/32
   [-1, 3, C3, [1024]],
   [-1, 1, SPPF, [1024, 5]],  # 9
  ]

# YOLOv5 v6.1 BiFPN head
head:
  [[-1, 1, Conv, [512, 1, 1]],
   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
   [[-1, 6], 1, BiFPN_Add2, [256, 256]],  # cat backbone P4
   [-1, 3, C3, [512, False]],  # 13

   [-1, 1, Conv, [256, 1, 1]],
   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
   [[-1, 4], 1, BiFPN_Add2, [128, 128]],  # cat backbone P3
   [-1, 3, C3, [256, False]],  # 17 

   [-1, 1, Conv, [512, 3, 2]],  
   [[-1, 13, 6], 1, BiFPN_Add3, [256, 256]],  #v5s通道数是默认参数的一半
   [-1, 3, C3, [512, False]],  # 20 

   [-1, 1, Conv, [512, 3, 2]],
   [[-1, 10], 1, BiFPN_Add2, [256, 256]],  # cat head P5
   [-1, 3, C3, [1024, False]],  # 23 

   [[17, 20, 23], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5)
  ]

class space_to_depth(nn.Module):
    # Changing the dimension of the Tensor
    def __init__(self, dimension=1):
        super().__init__()
        self.d = dimension

    def forward(self, x):
         return torch.cat([x[..., ::2, ::2], x[..., 1::2, ::2], x[..., ::2, 1::2], x[..., 1::2, 1::2]], 1)

elif m is Contract: 
	c2 = ch[f] * args[0] ** 2
elif m is space_to_depth:          # 在 Contract 后面加入 space_to_depth
	c2 = 4 * ch[f]

# Parameters
nc: 80  # number of classes
depth_multiple: 0.33  # model depth multiple
width_multiple: 0.50  # layer channel multiple
anchors:
  - [10,13, 16,30, 33,23]  # P3/8
  - [30,61, 62,45, 59,119]  # P4/16
  - [116,90, 156,198, 373,326]  # P5/32

# YOLOv5 v6.0 backbone
backbone:
  # [from, number, module, args]
  [[-1, 1, Focus, [64, 3]],     # 0-P1/2
   [-1, 1, Conv, [128, 3, 1]],  # 1
   [-1,1,space_to_depth,[1]],   # 2 -P2/4
   [-1, 3, C3, [128]],          # 3
   [-1, 1, Conv, [256, 3, 1]],  # 4
   [-1,1,space_to_depth,[1]],   # 5 -P3/8
   [-1, 6, C3, [256]],          # 6
   [-1, 1, Conv, [512, 3, 1]],  # 7-P4/16
   [-1,1,space_to_depth,[1]],   # 8 -P4/16
   [-1, 9, C3, [512]],          # 9
   [-1, 1, Conv, [1024, 3, 1]], # 10-P5/32
   [-1,1,space_to_depth,[1]],   # 11 -P5/32
   [-1, 3, C3, [1024]],         # 12
   [-1, 1, SPPF, [1024, 5]],    # 13
  ]

# YOLOv5 v6.0 head
head:
  [[-1, 1, Conv, [512, 1, 1]],                    # 14
   [-1, 1, nn.Upsample, [None, 2, 'nearest']],    # 15
   [[-1, 9], 1, Concat, [1]],                     # 16 cat backbone P4
   [-1, 3, C3, [512, False]],                     # 17

   [-1, 1, Conv, [256, 1, 1]],                    # 18
   [-1, 1, nn.Upsample, [None, 2, 'nearest']],    # 19
   [[-1, 6], 1, Concat, [1]],                     # 20 cat backbone P3
   [-1, 3, C3, [256, False]],                     # 21 (P3/8-small)

   [-1, 1, Conv, [256, 3, 1]],                    # 22
   [-1,1,space_to_depth,[1]],                     # 23 -P2/4
   [[-1, 18], 1, Concat, [1]],                    # 24 cat head P4
   [-1, 3, C3, [512, False]],                     # 25 (P4/16-medium)

   [-1, 1, Conv, [512, 3, 1]],                    # 26
   [-1,1,space_to_depth,[1]],                     # 27 -P2/4
   [[-1, 14], 1, Concat, [1]],                    # 28 cat head P5
   [-1, 3, C3, [1024, False]],                    # 29 (P5/32-large)

   [[21, 25, 29], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5)
  ]

class AttentionConv(nn.Module):
    def __init__(self, in_channels, out_channels, kernel_size, stride=1, padding=1, groups=1, bias=False):
        super(AttentionConv, self).__init__()
        self.out_channels = out_channels
        self.kernel_size = kernel_size
        self.stride = stride
        self.padding = padding
        self.groups = groups

        assert self.out_channels % self.groups == 0, "out_channels should be divided by groups. (example: out_channels: 40, groups: 4)"

        self.rel_h = nn.Parameter(torch.randn(out_channels // 2, 1, 1, kernel_size, 1), requires_grad=True)
        self.rel_w = nn.Parameter(torch.randn(out_channels // 2, 1, 1, 1, kernel_size), requires_grad=True)

        self.key_conv = nn.Conv2d(in_channels, out_channels, kernel_size=1, bias=bias)
        self.query_conv = nn.Conv2d(in_channels, out_channels, kernel_size=1, bias=bias)
        self.value_conv = nn.Conv2d(in_channels, out_channels, kernel_size=1, bias=bias)

        self.reset_parameters()

    def forward(self, x):
        batch, channels, height, width = x.size()

        padded_x = F.pad(x, [self.padding, self.padding, self.padding, self.padding])
        q_out = self.query_conv(x)
        k_out = self.key_conv(padded_x)
        v_out = self.value_conv(padded_x)

        k_out = k_out.unfold(2, self.kernel_size, self.stride).unfold(3, self.kernel_size, self.stride)
        v_out = v_out.unfold(2, self.kernel_size, self.stride).unfold(3, self.kernel_size, self.stride)

        k_out_h, k_out_w = k_out.split(self.out_channels // 2, dim=1)
        k_out = torch.cat((k_out_h + self.rel_h, k_out_w + self.rel_w), dim=1)

        k_out = k_out.contiguous().view(batch, self.groups, self.out_channels // self.groups, height, width, -1)
        v_out = v_out.contiguous().view(batch, self.groups, self.out_channels // self.groups, height, width, -1)

        q_out = q_out.view(batch, self.groups, self.out_channels // self.groups, height, width, 1)

        out = q_out * k_out
        out = F.softmax(out, dim=-1)
        out = torch.einsum('bnchwk,bnchwk -> bnchw', out, v_out).view(batch, -1, height, width)

        return out

    def reset_parameters(self):
        init.kaiming_normal_(self.key_conv.weight, mode='fan_out', nonlinearity='relu')
        init.kaiming_normal_(self.value_conv.weight, mode='fan_out', nonlinearity='relu')
        init.kaiming_normal_(self.query_conv.weight, mode='fan_out', nonlinearity='relu')

        init.normal_(self.rel_h, 0, 1)
        init.normal_(self.rel_w, 0, 1)


class AttentionStem(nn.Module):
    def __init__(self, in_channels, out_channels, kernel_size, stride=1, padding=0, groups=1, m=4, bias=False):
        super(AttentionStem, self).__init__()
        self.out_channels = out_channels
        self.kernel_size = kernel_size
        self.stride = stride
        self.padding = padding
        self.groups = groups
        self.m = m

        assert self.out_channels % self.groups == 0, "out_channels should be divided by groups. (example: out_channels: 40, groups: 4)"

        self.emb_a = nn.Parameter(torch.randn(out_channels // groups, kernel_size), requires_grad=True)
        self.emb_b = nn.Parameter(torch.randn(out_channels // groups, kernel_size), requires_grad=True)
        self.emb_mix = nn.Parameter(torch.randn(m, out_channels // groups), requires_grad=True)

        self.key_conv = nn.Conv2d(in_channels, out_channels, kernel_size=1, bias=bias)
        self.query_conv = nn.Conv2d(in_channels, out_channels, kernel_size=1, bias=bias)
        self.value_conv = nn.ModuleList([nn.Conv2d(in_channels, out_channels, kernel_size=1, bias=bias) for _ in range(m)])

        self.reset_parameters()

    def forward(self, x):
        batch, channels, height, width = x.size()

        padded_x = F.pad(x, [self.padding, self.padding, self.padding, self.padding])

        q_out = self.query_conv(x)
        k_out = self.key_conv(padded_x)
        v_out = torch.stack([self.value_conv[_](padded_x) for _ in range(self.m)], dim=0)

        k_out = k_out.unfold(2, self.kernel_size, self.stride).unfold(3, self.kernel_size, self.stride)
        v_out = v_out.unfold(3, self.kernel_size, self.stride).unfold(4, self.kernel_size, self.stride)

        k_out = k_out[:, :, :height, :width, :, :]
        v_out = v_out[:, :, :, :height, :width, :, :]

        emb_logit_a = torch.einsum('mc,ca->ma', self.emb_mix, self.emb_a)
        emb_logit_b = torch.einsum('mc,cb->mb', self.emb_mix, self.emb_b)
        emb = emb_logit_a.unsqueeze(2) + emb_logit_b.unsqueeze(1)
        emb = F.softmax(emb.view(self.m, -1), dim=0).view(self.m, 1, 1, 1, 1, self.kernel_size, self.kernel_size)

        v_out = emb * v_out

        k_out = k_out.contiguous().view(batch, self.groups, self.out_channels // self.groups, height, width, -1)
        v_out = v_out.contiguous().view(self.m, batch, self.groups, self.out_channels // self.groups, height, width, -1)
        v_out = torch.sum(v_out, dim=0).view(batch, self.groups, self.out_channels // self.groups, height, width, -1)

        q_out = q_out.view(batch, self.groups, self.out_channels // self.groups, height, width, 1)

        out = q_out * k_out
        out = F.softmax(out, dim=-1)
        out = torch.einsum('bnchwk,bnchwk->bnchw', out, v_out).view(batch, -1, height, width)

        return out

    def reset_parameters(self):
        init.kaiming_normal_(self.key_conv.weight, mode='fan_out', nonlinearity='relu')
        init.kaiming_normal_(self.query_conv.weight, mode='fan_out', nonlinearity='relu')
        for _ in self.value_conv:
            init.kaiming_normal_(_.weight, mode='fan_out', nonlinearity='relu')

        init.normal_(self.emb_a, 0, 1)
        init.normal_(self.emb_b, 0, 1)
        init.normal_(self.emb_mix, 0, 1)

if m in {
	Conv, GhostConv, Bottleneck, GhostBottleneck, SPP, SPPF, DWConv, MixConv2d, Focus, CrossConv,
	BottleneckCSP, C3, C3TR, C3SPP, C3Ghost, nn.ConvTranspose2d, DWConvTranspose2d, C3x, AttentionConv, AttentionStem}:  
	# AttentionConv, AttentionStem

# Parameters
nc: 80  # number of classes
depth_multiple: 0.33  # model depth multiple
width_multiple: 0.50  # layer channel multiple
anchors:
  - [10,13, 16,30, 33,23]  # P3/8
  - [30,61, 62,45, 59,119]  # P4/16
  - [116,90, 156,198, 373,326]  # P5/32

# YOLOv5 v6.0 backbone
backbone:
  # [from, number, module, args]
  [[-1, 1, Conv, [64, 6, 2, 2]],  # 0-P1/2
   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
   [-1, 3, C3, [128]],
   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
   [-1, 6, C3, [256]],
   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
   [-1, 9, C3, [512]],
   [-1, 1, Conv, [1024, 3, 2]],  # 7-P5/32
   [-1, 3, C3, [1024]],
   [-1, 1, SPPF, [1024, 5]],  # 9
  ]

# YOLOv5 v6.0 head
head:
   [ [ -1, 1, AttentionConv, [ 512, 3, 1, 1 ] ],
   [ -1, 1, nn.Upsample, [ None, 2, 'nearest' ] ],
   [ [ -1, 6 ], 1, Concat, [ 1 ] ],  # cat backbone P4
   [ -1, 1, AttentionConv, [ 512, 3, 1, 1 ] ] , # 13

   [ -1, 1, AttentionConv, [ 256, 3, 1, 1 ] ],
   [ -1, 1, nn.Upsample, [ None, 2, 'nearest' ] ],
   [ [ -1, 4 ], 1, Concat, [ 1 ] ],  # cat backbone P3
   [ -1, 1, AttentionConv, [ 256, 3, 1, 1 ] ],  # 17 (P3/8-small)

   [-1, 1, Conv, [256, 3, 2]],
   [[-1, 14], 1, Concat, [1]],  # cat head P4
   [-1, 3, AttentionConv, [512, 3, 1, 1]],  # 20 (P4/16-medium)

   [-1, 1, Conv, [512, 3, 2]],
   [[-1, 10], 1, Concat, [1]],  # cat head P5
   [-1, 3, AttentionConv, [1024, 3, 1, 1]],  # 23 (P5/32-large)

   [[17, 20, 23], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5)
   ]

class DecoupledHead(nn.Module):
    def __init__(self, ch=256, nc=80, width=1.0, anchors=()):
        super().__init__()
        self.nc = nc  # number of classes
        self.nl = len(anchors)  # number of detection layers 3
        self.na = len(anchors[0]) // 2  # number of anchors 3
        self.merge = Conv(ch, 256 * width, 1, 1)
        self.cls_convs1 = Conv(256 * width, 256 * width, 3, 1, 1)
        self.cls_convs2 = Conv(256 * width, 256 * width, 3, 1, 1)
        self.reg_convs1 = Conv(256 * width, 256 * width, 3, 1, 1)
        self.reg_convs2 = Conv(256 * width, 256 * width, 3, 1, 1)
        self.cls_preds = nn.Conv2d(256 * width, self.nc * self.na, 1)
        self.reg_preds = nn.Conv2d(256 * width, 4 * self.na, 1)
        self.obj_preds = nn.Conv2d(256 * width, 1 * self.na, 1)

    def forward(self, x):
        x = self.merge(x)
        # 分类=3x3conv + 3x3conv + 1x1convpred
        x1 = self.cls_convs1(x)
        x1 = self.cls_convs2(x1)
        x1 = self.cls_preds(x1)
        # 回归=3x3conv（共享） + 3x3conv（共享） + 1x1pred
        x2 = self.reg_convs1(x)
        x2 = self.reg_convs2(x2)
        x21 = self.reg_preds(x2)
        # 置信度=3x3conv（共享）+ 3x3conv（共享） + 1x1pred
        x22 = self.obj_preds(x2)
        out = torch.cat([x21, x22, x1], 1)
        return out

class Detect(nn.Module):
    def __init__(self, nc=80, anchors=(), ch=(), inplace=True):  # detection layer
        self.m = nn.ModuleList(DecoupledHead(x, self.no * self.na, 1) for x in ch)  # DecoupledHead 换成 nn.Conv2d

class Detect(nn.Module):
    def __init__(self, nc=80, anchors=(), ch=(), inplace=True, Decoupled=False):  # 添加：Decoupled=False 
    	······
        self.decoupled = Decoupled       # 添加：self.decoupled = Decoupled

# Parameters
nc: 80  # number of classes
depth_multiple: 0.33  # model depth multiple
width_multiple: 0.50  # layer channel multiple
anchors:
  - [10,13, 16,30, 33,23]  # P3/8
  - [30,61, 62,45, 59,119]  # P4/16
  - [116,90, 156,198, 373,326]  # P5/32

# YOLOv5 v6.1 backbone
backbone:
  # [from, number, module, args]
  [[-1, 1, Conv, [64, 6, 2, 2]],  # 0-P1/2
   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
   [-1, 3, C3, [128]],
   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
   [-1, 6, C3, [256]],
   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
   [-1, 9, C3, [512]],
   [-1, 1, Conv, [1024, 3, 2]],  # 7-P5/32
   [-1, 3, C3, [1024]],
   [-1, 1, SPPF, [1024, 5]],  # 9
  ]

# YOLOv5 v6.0 head
head:
  [[-1, 1, Conv, [512, 1, 1]],
   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
   [-1, 3, C3, [512, False]],  # 13

   [-1, 1, Conv, [256, 1, 1]],
   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
   [-1, 3, C3, [256, False]],  # 17 (P3/8-small)

   [-1, 1, Conv, [256, 3, 2]],
   [[-1, 14], 1, Concat, [1]],  # cat head P4
   [-1, 3, C3, [512, False]],  # 20 (P4/16-medium)

   [-1, 1, Conv, [512, 3, 2]],
   [[-1, 10], 1, Concat, [1]],  # cat head P5
   [-1, 3, C3, [1024, False]],  # 23 (P5/32-large)

   [[17, 20, 23], 1, Detect, [nc, anchors,True]],  # Detect(P3, P4, P5)
  ]

class v8_Bottleneck(nn.Module):
    # Standard bottleneck
    def __init__(self, c1, c2, shortcut=True, g=1, k=(3, 3), e=0.5):  # ch_in, ch_out, shortcut, groups, kernels, expand
        super().__init__()
        c_ = int(c2 * e)  # hidden channels
        self.cv1 = Conv(c1, c_, k[0], 1)
        self.cv2 = Conv(c_, c2, k[1], 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))


class C2f(nn.Module):
    # CSP Bottleneck with 2 convolutions
    def __init__(self, c1, c2, n=1, shortcut=False, g=1, e=0.5):  # 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(v8_Bottleneck(self.c, self.c, shortcut, g, k=((3, 3), (3, 3)), e=1.0) for _ in range(n))

    def forward(self, x):
        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))

if m in {
                Conv, GhostConv, Bottleneck, GhostBottleneck, SPP, SPPF, DWConv, MixConv2d, Focus, CrossConv,
                BottleneckCSP, C3, C3TR, C3SPP, C3Ghost, nn.ConvTranspose2d, DWConvTranspose2d, C3x, CARAFE, C2F}:  
                
 if m in {BottleneckCSP, C3, C3TR, C3Ghost, C3x, C2F}:
                args.insert(2, n)  # number of repeats

# YOLOv5 🚀 by Ultralytics, GPL-3.0 license

# Parameters
nc: 80  # number of classes
depth_multiple: 0.33  # model depth multiple
width_multiple: 0.50  # layer channel multiple
anchors:
  - [10,13, 16,30, 33,23]  # P3/8
  - [30,61, 62,45, 59,119]  # P4/16
  - [116,90, 156,198, 373,326]  # P5/32

# YOLOv5 v6.0 backbone
backbone:
  # [from, number, 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]]
  ]

# YOLOv5 v6.0 head
head:
  [[-1, 1, Conv, [512, 1, 1]],
   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
   [-1, 3, C3, [512, False]],  # 13

   [-1, 1, Conv, [256, 1, 1]],
   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
   [-1, 3, C3, [256, False]],  # 17 (P3/8-small)

   [-1, 1, Conv, [256, 3, 2]],
   [[-1, 14], 1, Concat, [1]],  # cat head P4
   [-1, 3, C3, [512, False]],  # 20 (P4/16-medium)

   [-1, 1, Conv, [512, 3, 2]],
   [[-1, 10], 1, Concat, [1]],  # cat head P5
   [-1, 3, C3, [1024, False]],  # 23 (P5/32-large)

   [[17, 20, 23], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5)
  ]