【YOLOv8】YOLOv8改进系列（1）----替换主干网络之EfficientViT(CVPR2023)

import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.utils.checkpoint as checkpoint
import itertools

from timm.models.layers import SqueezeExcite

import numpy as np
import itertools

__all__ = ['EfficientViT_M0', 'EfficientViT_M1', 'EfficientViT_M2', 'EfficientViT_M3', 'EfficientViT_M4', 'EfficientViT_M5']

class Conv2d_BN(torch.nn.Sequential):
    def __init__(self, a, b, ks=1, stride=1, pad=0, dilation=1,
                 groups=1, bn_weight_init=1, resolution=-10000):
        super().__init__()
        self.add_module('c', torch.nn.Conv2d(
            a, b, ks, stride, pad, dilation, groups, bias=False))
        self.add_module('bn', torch.nn.BatchNorm2d(b))
        torch.nn.init.constant_(self.bn.weight, bn_weight_init)
        torch.nn.init.constant_(self.bn.bias, 0)

    @torch.no_grad()
    def switch_to_deploy(self):
        c, bn = self._modules.values()
        w = bn.weight / (bn.running_var + bn.eps)**0.5
        w = c.weight * w[:, None, None, None]
        b = bn.bias - bn.running_mean * bn.weight / \
            (bn.running_var + bn.eps)**0.5
        m = torch.nn.Conv2d(w.size(1) * self.c.groups, w.size(
            0), w.shape[2:], stride=self.c.stride, padding=self.c.padding, dilation=self.c.dilation, groups=self.c.groups)
        m.weight.data.copy_(w)
        m.bias.data.copy_(b)
        return m

def replace_batchnorm(net):
    for child_name, child in net.named_children():
        if hasattr(child, 'fuse'):
            setattr(net, child_name, child.fuse())
        elif isinstance(child, torch.nn.BatchNorm2d):
            setattr(net, child_name, torch.nn.Identity())
        else:
            replace_batchnorm(child)
            

class PatchMerging(torch.nn.Module):
    def __init__(self, dim, out_dim, input_resolution):
        super().__init__()
        hid_dim = int(dim * 4)
        self.conv1 = Conv2d_BN(dim, hid_dim, 1, 1, 0, resolution=input_resolution)
        self.act = torch.nn.ReLU()
        self.conv2 = Conv2d_BN(hid_dim, hid_dim, 3, 2, 1, groups=hid_dim, resolution=input_resolution)
        self.se = SqueezeExcite(hid_dim, .25)
        self.conv3 = Conv2d_BN(hid_dim, out_dim, 1, 1, 0, resolution=input_resolution // 2)

    def forward(self, x):
        x = self.conv3(self.se(self.act(self.conv2(self.act(self.conv1(x))))))
        return x


class Residual(torch.nn.Module):
    def __init__(self, m, drop=0.):
        super().__init__()
        self.m = m
        self.drop = drop

    def forward(self, x):
        if self.training and self.drop > 0:
            return x + self.m(x) * torch.rand(x.size(0), 1, 1, 1,
                                              device=x.device).ge_(self.drop).div(1 - self.drop).detach()
        else:
            return x + self.m(x)


class FFN(torch.nn.Module):
    def __init__(self, ed, h, resolution):
        super().__init__()
        self.pw1 = Conv2d_BN(ed, h, resolution=resolution)
        self.act = torch.nn.ReLU()
        self.pw2 = Conv2d_BN(h, ed, bn_weight_init=0, resolution=resolution)

    def forward(self, x):
        x = self.pw2(self.act(self.pw1(x)))
        return x


class CascadedGroupAttention(torch.nn.Module):
    r""" Cascaded Group Attention.

    Args:
        dim (int): Number of input channels.
        key_dim (int): The dimension for query and key.
        num_heads (int): Number of attention heads.
        attn_ratio (int): Multiplier for the query dim for value dimension.
        resolution (int): Input resolution, correspond to the window size.
        kernels (List[int]): The kernel size of the dw conv on query.
    """
    def __init__(self, dim, key_dim, num_heads=8,
                 attn_ratio=4,
                 resolution=14,
                 kernels=[5, 5, 5, 5],):
        super().__init__()
        self.num_heads = num_heads
        self.scale = key_dim ** -0.5
        self.key_dim = key_dim
        self.d = int(attn_ratio * key_dim)
        self.attn_ratio = attn_ratio

        qkvs = []
        dws = []
        for i in range(num_heads):
            qkvs.append(Conv2d_BN(dim // (num_heads), self.key_dim * 2 + self.d, resolution=resolution))
            dws.append(Conv2d_BN(self.key_dim, self.key_dim, kernels[i], 1, kernels[i]//2, groups=self.key_dim, resolution=resolution))
        self.qkvs = torch.nn.ModuleList(qkvs)
        self.dws = torch.nn.ModuleList(dws)
        self.proj = torch.nn.Sequential(torch.nn.ReLU(), Conv2d_BN(
            self.d * num_heads, dim, bn_weight_init=0, resolution=resolution))

        points = list(itertools.product(range(resolution), range(resolution)))
        N = len(points)
        attention_offsets = {}
        idxs = []
        for p1 in points:
            for p2 in points:
                offset = (abs(p1[0] - p2[0]), abs(p1[1] - p2[1]))
                if offset not in attention_offsets:
                    attention_offsets[offset] = len(attention_offsets)
                idxs.append(attention_offsets[offset])
        self.attention_biases = torch.nn.Parameter(
            torch.zeros(num_heads, len(attention_offsets)))
        self.register_buffer('attention_bias_idxs',
                             torch.LongTensor(idxs).view(N, N))

    @torch.no_grad()
    def train(self, mode=True):
        super().train(mode)
        if mode and hasattr(self, 'ab'):
            del self.ab
        else:
            self.ab = self.attention_biases[:, self.attention_bias_idxs]

    def forward(self, x):  # x (B,C,H,W)
        B, C, H, W = x.shape
        trainingab = self.attention_biases[:, self.attention_bias_idxs]
        feats_in = x.chunk(len(self.qkvs), dim=1)
        feats_out = []
        feat = feats_in[0]
        for i, qkv in enumerate(self.qkvs):
            if i > 0: # add the previous output to the input
                feat = feat + feats_in[i]
            feat = qkv(feat)
            q, k, v = feat.view(B, -1, H, W).split([self.key_dim, self.key_dim, self.d], dim=1) # B, C/h, H, W
            q = self.dws[i](q)
            q, k, v = q.flatten(2), k.flatten(2), v.flatten(2) # B, C/h, N
            attn = (
                (q.transpose(-2, -1) @ k) * self.scale
                +
                (trainingab[i] if self.training else self.ab[i])
            )
            attn = attn.softmax(dim=-1) # BNN
            feat = (v @ attn.transpose(-2, -1)).view(B, self.d, H, W) # BCHW
            feats_out.append(feat)
        x = self.proj(torch.cat(feats_out, 1))
        return x


class LocalWindowAttention(torch.nn.Module):
    r""" Local Window Attention.

    Args:
        dim (int): Number of input channels.
        key_dim (int): The dimension for query and key.
        num_heads (int): Number of attention heads.
        attn_ratio (int): Multiplier for the query dim for value dimension.
        resolution (int): Input resolution.
        window_resolution (int): Local window resolution.
        kernels (List[int]): The kernel size of the dw conv on query.
    """
    def __init__(self, dim, key_dim, num_heads=8,
                 attn_ratio=4,
                 resolution=14,
                 window_resolution=7,
                 kernels=[5, 5, 5, 5],):
        super().__init__()
        self.dim = dim
        self.num_heads = num_heads
        self.resolution = resolution
        assert window_resolution > 0, 'window_size must be greater than 0'
        self.window_resolution = window_resolution
        
        self.attn = CascadedGroupAttention(dim, key_dim, num_heads,
                                attn_ratio=attn_ratio, 
                                resolution=window_resolution,
                                kernels=kernels,)

    def forward(self, x):
        B, C, H, W = x.shape
               
        if H <= self.window_resolution and W <= self.window_resolution:
            x = self.attn(x)
        else:
            x = x.permute(0, 2, 3, 1)
            pad_b = (self.window_resolution - H %
                     self.window_resolution) % self.window_resolution
            pad_r = (self.window_resolution - W %
                     self.window_resolution) % self.window_resolution
            padding = pad_b > 0 or pad_r > 0

            if padding:
                x = torch.nn.functional.pad(x, (0, 0, 0, pad_r, 0, pad_b))

            pH, pW = H + pad_b, W + pad_r
            nH = pH // self.window_resolution
            nW = pW // self.window_resolution
            # window partition, BHWC -> B(nHh)(nWw)C -> BnHnWhwC -> (BnHnW)hwC -> (BnHnW)Chw
            x = x.view(B, nH, self.window_resolution, nW, self.window_resolution, C).transpose(2, 3).reshape(
                B * nH * nW, self.window_resolution, self.window_resolution, C
            ).permute(0, 3, 1, 2)
            x = self.attn(x)
            # window reverse, (BnHnW)Chw -> (BnHnW)hwC -> BnHnWhwC -> B(nHh)(nWw)C -> BHWC
            x = x.permute(0, 2, 3, 1).view(B, nH, nW, self.window_resolution, self.window_resolution,
                       C).transpose(2, 3).reshape(B, pH, pW, C)

            if padding:
                x = x[:, :H, :W].contiguous()

            x = x.permute(0, 3, 1, 2)

        return x


class EfficientViTBlock(torch.nn.Module):
    """ A basic EfficientViT building block.

    Args:
        type (str): Type for token mixer. Default: 's' for self-attention.
        ed (int): Number of input channels.
        kd (int): Dimension for query and key in the token mixer.
        nh (int): Number of attention heads.
        ar (int): Multiplier for the query dim for value dimension.
        resolution (int): Input resolution.
        window_resolution (int): Local window resolution.
        kernels (List[int]): The kernel size of the dw conv on query.
    """
    def __init__(self, type,
                 ed, kd, nh=8,
                 ar=4,
                 resolution=14,
                 window_resolution=7,
                 kernels=[5, 5, 5, 5],):
        super().__init__()
            
        self.dw0 = Residual(Conv2d_BN(ed, ed, 3, 1, 1, groups=ed, bn_weight_init=0., resolution=resolution))
        self.ffn0 = Residual(FFN(ed, int(ed * 2), resolution))

        if type == 's':
            self.mixer = Residual(LocalWindowAttention(ed, kd, nh, attn_ratio=ar, \
                    resolution=resolution, window_resolution=window_resolution, kernels=kernels))
                
        self.dw1 = Residual(Conv2d_BN(ed, ed, 3, 1, 1, groups=ed, bn_weight_init=0., resolution=resolution))
        self.ffn1 = Residual(FFN(ed, int(ed * 2), resolution))

    def forward(self, x):
        return self.ffn1(self.dw1(self.mixer(self.ffn0(self.dw0(x)))))


class EfficientViT(torch.nn.Module):
    def __init__(self, img_size=400,
                 patch_size=16,
                 frozen_stages=0,
                 in_chans=3,
                 stages=['s', 's', 's'],
                 embed_dim=[64, 128, 192],
                 key_dim=[16, 16, 16],
                 depth=[1, 2, 3],
                 num_heads=[4, 4, 4],
                 window_size=[7, 7, 7],
                 kernels=[5, 5, 5, 5],
                 down_ops=[['subsample', 2], ['subsample', 2], ['']],
                 pretrained=None,
                 distillation=False,):
        super().__init__()

        resolution = img_size
        self.patch_embed = torch.nn.Sequential(Conv2d_BN(in_chans, embed_dim[0] // 8, 3, 2, 1, resolution=resolution), torch.nn.ReLU(),
                           Conv2d_BN(embed_dim[0] // 8, embed_dim[0] // 4, 3, 2, 1, resolution=resolution // 2), torch.nn.ReLU(),
                           Conv2d_BN(embed_dim[0] // 4, embed_dim[0] // 2, 3, 2, 1, resolution=resolution // 4), torch.nn.ReLU(),
                           Conv2d_BN(embed_dim[0] // 2, embed_dim[0], 3, 1, 1, resolution=resolution // 8))

        resolution = img_size // patch_size
        attn_ratio = [embed_dim[i] / (key_dim[i] * num_heads[i]) for i in range(len(embed_dim))]
        self.blocks1 = []
        self.blocks2 = []
        self.blocks3 = []
        for i, (stg, ed, kd, dpth, nh, ar, wd, do) in enumerate(
                zip(stages, embed_dim, key_dim, depth, num_heads, attn_ratio, window_size, down_ops)):
            for d in range(dpth):
                eval('self.blocks' + str(i+1)).append(EfficientViTBlock(stg, ed, kd, nh, ar, resolution, wd, kernels))
            if do[0] == 'subsample':
                #('Subsample' stride)
                blk = eval('self.blocks' + str(i+2))
                resolution_ = (resolution - 1) // do[1] + 1
                blk.append(torch.nn.Sequential(Residual(Conv2d_BN(embed_dim[i], embed_dim[i], 3, 1, 1, groups=embed_dim[i], resolution=resolution)),
                                    Residual(FFN(embed_dim[i], int(embed_dim[i] * 2), resolution)),))
                blk.append(PatchMerging(*embed_dim[i:i + 2], resolution))
                resolution = resolution_
                blk.append(torch.nn.Sequential(Residual(Conv2d_BN(embed_dim[i + 1], embed_dim[i + 1], 3, 1, 1, groups=embed_dim[i + 1], resolution=resolution)),
                                    Residual(FFN(embed_dim[i + 1], int(embed_dim[i + 1] * 2), resolution)),))
        self.blocks1 = torch.nn.Sequential(*self.blocks1)
        self.blocks2 = torch.nn.Sequential(*self.blocks2)
        self.blocks3 = torch.nn.Sequential(*self.blocks3)
        
        self.channel = [i.size(1) for i in self.forward(torch.randn(1, 3, 640, 640))]

    def forward(self, x):
        outs = []
        x = self.patch_embed(x)
        x = self.blocks1(x)
        outs.append(x)
        x = self.blocks2(x)
        outs.append(x)
        x = self.blocks3(x)
        outs.append(x)
        return outs

EfficientViT_m0 = {
        'img_size': 224,
        'patch_size': 16,
        'embed_dim': [64, 128, 192],
        'depth': [1, 2, 3],
        'num_heads': [4, 4, 4],
        'window_size': [7, 7, 7],
        'kernels': [7, 5, 3, 3],
    }

EfficientViT_m1 = {
        'img_size': 224,
        'patch_size': 16,
        'embed_dim': [128, 144, 192],
        'depth': [1, 2, 3],
        'num_heads': [2, 3, 3],
        'window_size': [7, 7, 7],
        'kernels': [7, 5, 3, 3],
    }

EfficientViT_m2 = {
        'img_size': 224,
        'patch_size': 16,
        'embed_dim': [128, 192, 224],
        'depth': [1, 2, 3],
        'num_heads': [4, 3, 2],
        'window_size': [7, 7, 7],
        'kernels': [7, 5, 3, 3],
    }

EfficientViT_m3 = {
        'img_size': 224,
        'patch_size': 16,
        'embed_dim': [128, 240, 320],
        'depth': [1, 2, 3],
        'num_heads': [4, 3, 4],
        'window_size': [7, 7, 7],
        'kernels': [5, 5, 5, 5],
    }

EfficientViT_m4 = {
        'img_size': 224,
        'patch_size': 16,
        'embed_dim': [128, 256, 384],
        'depth': [1, 2, 3],
        'num_heads': [4, 4, 4],
        'window_size': [7, 7, 7],
        'kernels': [7, 5, 3, 3],
    }

EfficientViT_m5 = {
        'img_size': 224,
        'patch_size': 16,
        'embed_dim': [192, 288, 384],
        'depth': [1, 3, 4],
        'num_heads': [3, 3, 4],
        'window_size': [7, 7, 7],
        'kernels': [7, 5, 3, 3],
    }

def EfficientViT_M0(pretrained='', frozen_stages=0, distillation=False, fuse=False, pretrained_cfg=None, model_cfg=EfficientViT_m0):
    model = EfficientViT(frozen_stages=frozen_stages, distillation=distillation, pretrained=pretrained, **model_cfg)
    if pretrained:
        model.load_state_dict(update_weight(model.state_dict(), torch.load(pretrained)['model']))
    if fuse:
        replace_batchnorm(model)
    return model

def EfficientViT_M1(pretrained='', frozen_stages=0, distillation=False, fuse=False, pretrained_cfg=None, model_cfg=EfficientViT_m1):
    model = EfficientViT(frozen_stages=frozen_stages, distillation=distillation, pretrained=pretrained, **model_cfg)
    if pretrained:
        model.load_state_dict(update_weight(model.state_dict(), torch.load(pretrained)['model']))
    if fuse:
        replace_batchnorm(model)
    return model

def EfficientViT_M2(pretrained='', frozen_stages=0, distillation=False, fuse=False, pretrained_cfg=None, model_cfg=EfficientViT_m2):
    model = EfficientViT(frozen_stages=frozen_stages, distillation=distillation, pretrained=pretrained, **model_cfg)
    if pretrained:
        model.load_state_dict(update_weight(model.state_dict(), torch.load(pretrained)['model']))
    if fuse:
        replace_batchnorm(model)
    return model

def EfficientViT_M3(pretrained='', frozen_stages=0, distillation=False, fuse=False, pretrained_cfg=None, model_cfg=EfficientViT_m3):
    model = EfficientViT(frozen_stages=frozen_stages, distillation=distillation, pretrained=pretrained, **model_cfg)
    if pretrained:
        model.load_state_dict(update_weight(model.state_dict(), torch.load(pretrained)['model']))
    if fuse:
        replace_batchnorm(model)
    return model
    
def EfficientViT_M4(pretrained='', frozen_stages=0, distillation=False, fuse=False, pretrained_cfg=None, model_cfg=EfficientViT_m4):
    model = EfficientViT(frozen_stages=frozen_stages, distillation=distillation, pretrained=pretrained, **model_cfg)
    if pretrained:
        model.load_state_dict(update_weight(model.state_dict(), torch.load(pretrained)['model']))
    if fuse:
        replace_batchnorm(model)
    return model

def EfficientViT_M5(pretrained='', frozen_stages=0, distillation=False, fuse=False, pretrained_cfg=None, model_cfg=EfficientViT_m5):
    model = EfficientViT(frozen_stages=frozen_stages, distillation=distillation, pretrained=pretrained, **model_cfg)
    if pretrained:
        model.load_state_dict(update_weight(model.state_dict(), torch.load(pretrained)['model']))
    if fuse:
        replace_batchnorm(model)
    return model

def update_weight(model_dict, weight_dict):
    idx, temp_dict = 0, {}
    for k, v in weight_dict.items():
        # k = k[9:]
        if k in model_dict.keys() and np.shape(model_dict[k]) == np.shape(v):
            temp_dict[k] = v
            idx += 1
    model_dict.update(temp_dict)
    print(f'loading weights... {idx}/{len(model_dict)} items')
    return model_dict

if __name__ == '__main__':
    model = EfficientViT_M0('efficientvit_m0.pth')
    inputs = torch.randn((1, 3, 640, 640))
    res = model(inputs)
    for i in res:
        print(i.size())

'YOLOv8_EfficientViT_M0', 
'YOLOv8_EfficientViT_M1', 
'YOLOv8_EfficientViT_M2', 
'YOLOv8_EfficientViT_M3',
'YOLOv8_EfficientViT_M4',
'YOLOv8_EfficientViT_M5'

from ultralytics.nn.backbone.efficientViT import *

    def _predict_once(self, x, profile=False, visualize=False, embed=None):
        """
        Perform a forward pass through the network.

        Args:
            x (torch.Tensor): The input tensor to the model.
            profile (bool):  Print the computation time of each layer if True, defaults to False.
            visualize (bool): Save the feature maps of the model if True, defaults to False.
            embed (list, optional): A list of feature vectors/embeddings to return.

        Returns:
            (torch.Tensor): The last output of the model.
        """
        y, dt, embeddings = [], [], []  # outputs
        for idx, m in enumerate(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)
            if hasattr(m, 'backbone'):
                x = m(x)
                for _ in range(5 - len(x)):
                    x.insert(0, None)
                for i_idx, i in enumerate(x):
                    if i_idx in self.save:
                        y.append(i)
                    else:
                        y.append(None)
                # print(f'layer id:{idx:>2} {m.type:>50} output shape:{", ".join([str(x_.size()) for x_ in x if x_ is not None])}')
                x = x[-1]
            else:
                x = m(x)  # run
                y.append(x if m.i in self.save else None)  # save output
            
            # if type(x) in {list, tuple}:
            #     if idx == (len(self.model) - 1):
            #         if type(x[1]) is dict:
            #             print(f'layer id:{idx:>2} {m.type:>50} output shape:{", ".join([str(x_.size()) for x_ in x[1]["one2one"]])}')
            #         else:
            #             print(f'layer id:{idx:>2} {m.type:>50} output shape:{", ".join([str(x_.size()) for x_ in x[1]])}')
            #     else:
            #         print(f'layer id:{idx:>2} {m.type:>50} output shape:{", ".join([str(x_.size()) for x_ in x if x_ is not None])}')
            # elif type(x) is dict:
            #     print(f'layer id:{idx:>2} {m.type:>50} output shape:{", ".join([str(x_.size()) for x_ in x["one2one"]])}')
            # else:
            #     if not hasattr(m, 'backbone'):
            #         print(f'layer id:{idx:>2} {m.type:>50} output shape:{x.size()}')
            
            if visualize:
                feature_visualization(x, m.type, m.i, save_dir=visualize)
            if embed and m.i in embed:
                embeddings.append(nn.functional.adaptive_avg_pool2d(x, (1, 1)).squeeze(-1).squeeze(-1))  # flatten
                if m.i == max(embed):
                    return torch.unbind(torch.cat(embeddings, 1), dim=0)
        return x

def parse_model(d, ch, verbose=True, warehouse_manager=None):  # 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}'.")
        if len(scales[scale]) == 3:
            depth, width, max_channels = scales[scale]
        elif len(scales[scale]) == 4:
            depth, width, max_channels, threshold = 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':<60}{'arguments':<50}")
    ch = [ch]
    layers, save, c2 = [], [], ch[-1]  # layers, savelist, ch out
    is_backbone = False
    for i, (f, n, m, args) in enumerate(d["backbone"] + d["head"]):  # from, number, module, args
        try:
            if m == 'node_mode':
                m = d[m]
                if len(args) > 0:
                    if args[0] == 'head_channel':
                        args[0] = int(d[args[0]])
            t = m
            m = getattr(torch.nn, m[3:]) if 'nn.' in m else globals()[m]  # get module
        except:
            pass
        for j, a in enumerate(args):
            if isinstance(a, str):
                with contextlib.suppress(ValueError):
                    try:
                        args[j] = locals()[a] if a in locals() else ast.literal_eval(a)
                    except:
                        args[j] = 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, ELAN1, AConv, SPPELAN, C2fAttn, C3, C3TR, 
            C3Ghost, nn.Conv2d, nn.ConvTranspose2d, DWConvTranspose2d, C3x, RepC3, PSA, SCDown, C2fCIB, C2f_Faster, C2f_ODConv,
            C2f_Faster_EMA, C2f_DBB, GSConv, GSConvns, VoVGSCSP, VoVGSCSPns, VoVGSCSPC, C2f_CloAtt, C3_CloAtt, SCConv, C2f_SCConv, C3_SCConv, C2f_ScConv, C3_ScConv,
            C3_EMSC, C3_EMSCP, C2f_EMSC, C2f_EMSCP, RCSOSA, KWConv, C2f_KW, C3_KW, DySnakeConv, C2f_DySnakeConv, C3_DySnakeConv,
            DCNv2, C3_DCNv2, C2f_DCNv2, DCNV3_YOLO, C3_DCNv3, C2f_DCNv3, C3_Faster, C3_Faster_EMA, C3_ODConv,
            OREPA, OREPA_LargeConv, RepVGGBlock_OREPA, C3_OREPA, C2f_OREPA, C3_DBB, C3_REPVGGOREPA, C2f_REPVGGOREPA,
            C3_DCNv2_Dynamic, C2f_DCNv2_Dynamic, C3_ContextGuided, C2f_ContextGuided, C3_MSBlock, C2f_MSBlock,
            C3_DLKA, C2f_DLKA, CSPStage, SPDConv, RepBlock, C3_EMBC, C2f_EMBC, SPPF_LSKA, C3_DAttention, C2f_DAttention,
            C3_Parc, C2f_Parc, C3_DWR, C2f_DWR, RFAConv, RFCAConv, RFCBAMConv, C3_RFAConv, C2f_RFAConv,
            C3_RFCBAMConv, C2f_RFCBAMConv, C3_RFCAConv, C2f_RFCAConv, C3_FocusedLinearAttention, C2f_FocusedLinearAttention,
            C3_AKConv, C2f_AKConv, AKConv, C3_MLCA, C2f_MLCA,
            C3_UniRepLKNetBlock, C2f_UniRepLKNetBlock, C3_DRB, C2f_DRB, C3_DWR_DRB, C2f_DWR_DRB, CSP_EDLAN,
            C3_AggregatedAtt, C2f_AggregatedAtt, DCNV4_YOLO, C3_DCNv4, C2f_DCNv4, HWD, SEAM,
            C3_SWC, C2f_SWC, C3_iRMB, C2f_iRMB, C3_iRMB_Cascaded, C2f_iRMB_Cascaded, C3_iRMB_DRB, C2f_iRMB_DRB, C3_iRMB_SWC, C2f_iRMB_SWC,
            C3_VSS, C2f_VSS, C3_LVMB, C2f_LVMB, RepNCSPELAN4, DBBNCSPELAN4, OREPANCSPELAN4, DRBNCSPELAN4, ADown, V7DownSampling,
            C3_DynamicConv, C2f_DynamicConv, C3_GhostDynamicConv, C2f_GhostDynamicConv, C3_RVB, C2f_RVB, C3_RVB_SE, C2f_RVB_SE, C3_RVB_EMA, C2f_RVB_EMA, DGCST,
            C3_RetBlock, C2f_RetBlock, C3_PKIModule, C2f_PKIModule, RepNCSPELAN4_CAA, C3_FADC, C2f_FADC, C3_PPA, C2f_PPA, SRFD, DRFD, RGCSPELAN,
            C3_Faster_CGLU, C2f_Faster_CGLU, C3_Star, C2f_Star, C3_Star_CAA, C2f_Star_CAA, C3_KAN, C2f_KAN, C3_EIEM, C2f_EIEM, C3_DEConv, C2f_DEConv,
            C3_SMPCGLU, C2f_SMPCGLU, C3_Heat, C2f_Heat, CSP_PTB, SimpleStem, VisionClueMerge, VSSBlock_YOLO, XSSBlock, GLSA, C2f_WTConv, WTConv2d, FeaturePyramidSharedConv,
            C2f_FMB, LDConv, C2f_gConv, C2f_WDBB, C2f_DeepDBB, C2f_AdditiveBlock, C2f_AdditiveBlock_CGLU, CSP_MSCB, C2f_MSMHSA_CGLU, CSP_PMSFA, C2f_MogaBlock,
            C2f_SHSA, C2f_SHSA_CGLU, C2f_SMAFB, C2f_SMAFB_CGLU, C2f_IdentityFormer, C2f_RandomMixing, C2f_PoolingFormer, C2f_ConvFormer, C2f_CaFormer,
            C2f_IdentityFormerCGLU, C2f_RandomMixingCGLU, C2f_PoolingFormerCGLU, C2f_ConvFormerCGLU, C2f_CaFormerCGLU, CSP_MutilScaleEdgeInformationEnhance, C2f_FFCM,
            C2f_SFHF, CSP_FreqSpatial, C2f_MSM, C2f_RAB, C2f_HDRAB, C2f_LFE, CSP_MutilScaleEdgeInformationSelect, C2f_SFA, C2f_CTA, C2f_CAMixer, MANet,
            MANet_FasterBlock, MANet_FasterCGLU, MANet_Star, C2f_HFERB, C2f_DTAB, C2f_ETB, C2f_JDPM, C2f_AP, PSConv, C2f_Kat, C2f_Faster_KAN, C2f_Strip, C2f_StripCGLU
        }:
            if args[0] == 'head_channel':
                args[0] = d[args[0]]
            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 (KWConv, C2f_KW, C3_KW):
                args.insert(2, f'layer{i}')
                args.insert(2, warehouse_manager)
            if m in (DySnakeConv,):
                c2 = c2 * 3
            if m in (RepNCSPELAN4, DBBNCSPELAN4, OREPANCSPELAN4, DRBNCSPELAN4, RepNCSPELAN4_CAA):
                args[2] = make_divisible(min(args[2], max_channels) * width, 8)
                args[3] = make_divisible(min(args[3], max_channels) * width, 8)
            if m in {
                     BottleneckCSP, C1, C2, C2f, C2fAttn, C3, C3TR, C3Ghost, C3x, RepC3, C2fCIB, C2f_Faster, C2f_ODConv, C2f_Faster_EMA, C2f_DBB,
                     VoVGSCSP, VoVGSCSPns, VoVGSCSPC, C2f_CloAtt, C3_CloAtt, C2f_SCConv, C3_SCConv, C2f_ScConv, C3_ScConv,
                     C3_EMSC, C3_EMSCP, C2f_EMSC, C2f_EMSCP, RCSOSA, C2f_KW, C3_KW, C2f_DySnakeConv, C3_DySnakeConv,
                     C3_DCNv2, C2f_DCNv2, C3_DCNv3, C2f_DCNv3, C3_Faster, C3_Faster_EMA, C3_ODConv, C3_OREPA, C2f_OREPA, C3_DBB,
                     C3_REPVGGOREPA, C2f_REPVGGOREPA, C3_DCNv2_Dynamic, C2f_DCNv2_Dynamic, C3_ContextGuided, C2f_ContextGuided, 
                     C3_MSBlock, C2f_MSBlock, C3_DLKA, C2f_DLKA, CSPStage, RepBlock, C3_EMBC, C2f_EMBC, C3_DAttention, C2f_DAttention,
                     C3_Parc, C2f_Parc, C3_DWR, C2f_DWR, C3_RFAConv, C2f_RFAConv, C3_RFCBAMConv, C2f_RFCBAMConv, C3_RFCAConv, C2f_RFCAConv,
                     C3_FocusedLinearAttention, C2f_FocusedLinearAttention, C3_AKConv, C2f_AKConv, C3_MLCA, C2f_MLCA,
                     C3_UniRepLKNetBlock, C2f_UniRepLKNetBlock, C3_DRB, C2f_DRB, C3_DWR_DRB, C2f_DWR_DRB, CSP_EDLAN,
                     C3_AggregatedAtt, C2f_AggregatedAtt, C3_DCNv4, C2f_DCNv4, C3_SWC, C2f_SWC,
                     C3_iRMB, C2f_iRMB, C3_iRMB_Cascaded, C2f_iRMB_Cascaded, C3_iRMB_DRB, C2f_iRMB_DRB, C3_iRMB_SWC, C2f_iRMB_SWC,
                     C3_VSS, C2f_VSS, C3_LVMB, C2f_LVMB, C3_DynamicConv, C2f_DynamicConv, C3_GhostDynamicConv, C2f_GhostDynamicConv,
                     C3_RVB, C2f_RVB, C3_RVB_SE, C2f_RVB_SE, C3_RVB_EMA, C2f_RVB_EMA, C3_RetBlock, C2f_RetBlock, C3_PKIModule, C2f_PKIModule,
                     C3_FADC, C2f_FADC, C3_PPA, C2f_PPA, RGCSPELAN, C3_Faster_CGLU, C2f_Faster_CGLU, C3_Star, C2f_Star, C3_Star_CAA, C2f_Star_CAA,
                     C3_KAN, C2f_KAN, C3_EIEM, C2f_EIEM, C3_DEConv, C2f_DEConv, C3_SMPCGLU, C2f_SMPCGLU, C3_Heat, C2f_Heat, CSP_PTB, XSSBlock, C2f_WTConv,
                     C2f_FMB, C2f_gConv, C2f_WDBB, C2f_DeepDBB, C2f_AdditiveBlock, C2f_AdditiveBlock_CGLU, CSP_MSCB, C2f_MSMHSA_CGLU, CSP_PMSFA, C2f_MogaBlock,
                     C2f_SHSA, C2f_SHSA_CGLU, C2f_SMAFB, C2f_SMAFB_CGLU, C2f_IdentityFormer, C2f_RandomMixing, C2f_PoolingFormer, C2f_ConvFormer, C2f_CaFormer,
                     C2f_IdentityFormerCGLU, C2f_RandomMixingCGLU, C2f_PoolingFormerCGLU, C2f_ConvFormerCGLU, C2f_CaFormerCGLU, CSP_MutilScaleEdgeInformationEnhance, C2f_FFCM,
                     C2f_SFHF, CSP_FreqSpatial, C2f_MSM, C2f_RAB, C2f_HDRAB, C2f_LFE, CSP_MutilScaleEdgeInformationSelect, C2f_SFA, C2f_CTA, C2f_CAMixer, MANet,
                     MANet_FasterBlock, MANet_FasterCGLU, MANet_Star, C2f_HFERB, C2f_DTAB, C2f_ETB, C2f_JDPM, C2f_AP, C2f_Kat, C2f_Faster_KAN, C2f_Strip, C2f_StripCGLU
                     }:
                args.insert(2, n)  # number of repeats
                n = 1
        elif m in {AIFI, AIFI_RepBN}:
            args = [ch[f], *args]
            c2 = args[0]
        elif m in (HGStem, HGBlock, Ghost_HGBlock, Rep_HGBlock, Dynamic_HGBlock, EIEStem):
            c1, cm, c2 = ch[f], args[0], args[1]
            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)
                cm = make_divisible(min(cm, max_channels) * width, 8)
            args = [c1, cm, c2, *args[2:]]
            if m in (HGBlock, Ghost_HGBlock, Rep_HGBlock, Dynamic_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 ((WorldDetect, ImagePoolingAttn) + DETECT_CLASS + V10_DETECT_CLASS + SEGMENT_CLASS + POSE_CLASS + OBB_CLASS):
            args.append([ch[x] for x in f])
            if m in SEGMENT_CLASS:
                args[2] = make_divisible(min(args[2], max_channels) * width, 8)
                if m in (Segment_LSCD, Segment_TADDH, Segment_LSCSBD, Segment_LSDECD, Segment_RSCD):
                    args[3] = make_divisible(min(args[3], max_channels) * width, 8)
            if m in (Detect_LSCD, Detect_TADDH, Detect_LSCSBD, Detect_LSDECD, Detect_RSCD, v10Detect_LSCD, v10Detect_TADDH, v10Detect_RSCD, v10Detect_LSDECD):
                args[1] = make_divisible(min(args[1], max_channels) * width, 8)
            if m in (Pose_LSCD, Pose_TADDH, Pose_LSCSBD, Pose_LSDECD, Pose_RSCD, OBB_LSCD, OBB_TADDH, OBB_LSCSBD, OBB_LSDECD, OBB_RSCD):
                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])
        elif m is Fusion:
            args[0] = d[args[0]]
            c1, c2 = [ch[x] for x in f], (sum([ch[x] for x in f]) if args[0] == 'concat' else ch[f[0]])
            args = [c1, args[0]]
        elif m is CBLinear:
            c2 = make_divisible(min(args[0][-1], max_channels) * width, 8)
            c1 = ch[f]
            args = [c1, [make_divisible(min(c2_, max_channels) * width, 8) for c2_ in args[0]], *args[1:]]
        elif m is CBFuse:
            c2 = ch[f[-1]]
        elif isinstance(m, str):
            t = m
            if len(args) == 2:        
                m = timm.create_model(m, pretrained=args[0], pretrained_cfg_overlay={'file':args[1]}, features_only=True)
            elif len(args) == 1:
                m = timm.create_model(m, pretrained=args[0], features_only=True)
            c2 = m.feature_info.channels()
        elif m in {convnextv2_atto, convnextv2_femto, convnextv2_pico, convnextv2_nano, convnextv2_tiny, convnextv2_base, convnextv2_large, convnextv2_huge,
                   fasternet_t0, fasternet_t1, fasternet_t2, fasternet_s, fasternet_m, fasternet_l,
                   EfficientViT_M0, EfficientViT_M1, EfficientViT_M2, EfficientViT_M3, EfficientViT_M4, EfficientViT_M5,
                   efficientformerv2_s0, efficientformerv2_s1, efficientformerv2_s2, efficientformerv2_l,
                   vanillanet_5, vanillanet_6, vanillanet_7, vanillanet_8, vanillanet_9, vanillanet_10, vanillanet_11, vanillanet_12, vanillanet_13, vanillanet_13_x1_5, vanillanet_13_x1_5_ada_pool,
                   RevCol,
                   lsknet_t, lsknet_s,
                   SwinTransformer_Tiny,
                   repvit_m0_9, repvit_m1_0, repvit_m1_1, repvit_m1_5, repvit_m2_3,
                   CSWin_tiny, CSWin_small, CSWin_base, CSWin_large,
                   unireplknet_a, unireplknet_f, unireplknet_p, unireplknet_n, unireplknet_t, unireplknet_s, unireplknet_b, unireplknet_l, unireplknet_xl,
                   transnext_micro, transnext_tiny, transnext_small, transnext_base,
                   RMT_T, RMT_S, RMT_B, RMT_L,
                   PKINET_T, PKINET_S, PKINET_B,
                   MobileNetV4ConvSmall, MobileNetV4ConvMedium, MobileNetV4ConvLarge, MobileNetV4HybridMedium, MobileNetV4HybridLarge,
                   starnet_s050, starnet_s100, starnet_s150, starnet_s1, starnet_s2, starnet_s3, starnet_s4
                   }:
            if m is RevCol:
                args[1] = [make_divisible(min(k, max_channels) * width, 8) for k in args[1]]
                args[2] = [max(round(k * depth), 1) for k in args[2]]
            m = m(*args)
            c2 = m.channel
        elif m in {EMA, SpatialAttention, BiLevelRoutingAttention, BiLevelRoutingAttention_nchw,
                   TripletAttention, CoordAtt, CBAM, BAMBlock, LSKBlock, ScConv, LAWDS, EMSConv, EMSConvP,
                   SEAttention, CPCA, Partial_conv3, FocalModulation, EfficientAttention, MPCA, deformable_LKA,
                   EffectiveSEModule, LSKA, SegNext_Attention, DAttention, MLCA, TransNeXt_AggregatedAttention,
                   FocusedLinearAttention, LocalWindowAttention, ChannelAttention_HSFPN, ELA_HSFPN, CA_HSFPN, CAA_HSFPN, 
                   DySample, CARAFE, CAA, ELA, CAFM, AFGCAttention, EUCB, ContrastDrivenFeatureAggregation, FSA}:
            c2 = ch[f]
            args = [c2, *args]
            # print(args)
        elif m in {SimAM, SpatialGroupEnhance}:
            c2 = ch[f]
        elif m is ContextGuidedBlock_Down:
            c2 = ch[f] * 2
            args = [ch[f], c2, *args]
        elif m is BiFusion:
            c1 = [ch[x] for x in f]
            c2 = make_divisible(min(args[0], max_channels) * width, 8)
            args = [c1, c2]
        # --------------GOLD-YOLO--------------
        elif m in {SimFusion_4in, AdvPoolFusion}:
            c2 = sum(ch[x] for x in f)
        elif m is SimFusion_3in:
            c2 = 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)
            args = [[ch[f_] for f_ in f], c2]
        elif m is IFM:
            c1 = ch[f]
            c2 = sum(args[0])
            args = [c1, *args]
        elif m is InjectionMultiSum_Auto_pool:
            c1 = ch[f[0]]
            c2 = args[0]
            args = [c1, *args]
        elif m is PyramidPoolAgg:
            c2 = args[0]
            args = [sum([ch[f_] for f_ in f]), *args]
        elif m is TopBasicLayer:
            c2 = sum(args[1])
        # --------------GOLD-YOLO--------------
        # --------------ASF--------------
        elif m is Zoom_cat:
            c2 = sum(ch[x] for x in f)
        elif m is Add:
            c2 = ch[f[-1]]
        elif m in {ScalSeq, DynamicScalSeq}:
            c1 = [ch[x] for x in f]
            c2 = make_divisible(args[0] * width, 8)
            args = [c1, c2]
        elif m is asf_attention_model:
            args = [ch[f[-1]]]
        # --------------ASF--------------
        elif m is SDI:
            args = [[ch[x] for x in f]]
        elif m is Multiply:
            c2 = ch[f[0]]
        elif m is FocusFeature:
            c1 = [ch[x] for x in f]
            c2 = int(c1[1] * 0.5 * 3)
            args = [c1, *args]
        elif m is DASI:
            c1 = [ch[x] for x in f]
            args = [c1, c2]
        elif m is CSMHSA:
            c1 = [ch[x] for x in f]
            c2 = ch[f[-1]]
            args = [c1, c2]
        elif m is CFC_CRB:
            c1 = ch[f]
            c2 = c1 // 2
            args = [c1, *args]
        elif m is SFC_G2:
            c1 = [ch[x] for x in f]
            c2 = c1[0]
            args = [c1]
        elif m in {CGAFusion, CAFMFusion, SDFM, PSFM}:
            c2 = ch[f[1]]
            args = [c2, *args]
        elif m in {ContextGuideFusionModule}:
            c1 = [ch[x] for x in f]
            c2 = 2 * c1[1]
            args = [c1]
        # elif m in {PSA}:
        #     c2 = ch[f]
        #     args = [c2, *args]
        elif m in {SBA}:
            c1 = [ch[x] for x in f]
            c2 = c1[-1]
            args = [c1, c2]
        elif m in {WaveletPool}:
            c2 = ch[f] * 4
        elif m in {WaveletUnPool}:
            c2 = ch[f] // 4
        elif m in {CSPOmniKernel}:
            c2 = ch[f]
            args = [c2]
        elif m in {ChannelTransformer, PyramidContextExtraction}:
            c1 = [ch[x] for x in f]
            c2 = c1
            args = [c1]
        elif m in {RCM}:
            c2 = ch[f]
            args = [c2, *args]
        elif m in {DynamicInterpolationFusion}:
            c2 = ch[f[0]]
            args = [[ch[x] for x in f]]
        elif m in {FuseBlockMulti}:
            c2 = ch[f[0]]
            args = [c2]
        elif m in {CrossLayerChannelAttention, CrossLayerSpatialAttention}:
            c2 = [ch[x] for x in f]
            args = [c2[0], *args]
        elif m in {FreqFusion}:
            c2 = ch[f[0]]
            args = [[ch[x] for x in f], *args]
        elif m in {DynamicAlignFusion}:
            c2 = args[0]
            args = [[ch[x] for x in f], c2]
        elif m in {ConvEdgeFusion}:
            c2 = make_divisible(min(args[0], max_channels) * width, 8)
            args = [[ch[x] for x in f], c2]
        elif m in {MutilScaleEdgeInfoGenetator}:
            c1 = ch[f]
            c2 = [make_divisible(min(i, max_channels) * width, 8) for i in args[0]]
            args = [c1, c2]
        elif m in {MultiScaleGatedAttn}:
            c1 = [ch[x] for x in f]
            c2 = min(c1)
            args = [c1]
        elif m in {WFU, MultiScalePCA, MultiScalePCA_Down}:
            c1 = [ch[x] for x in f]
            c2 = c1[0]
            args = [c1]
        elif m in {GetIndexOutput}:
            c2 = ch[f][args[0]]
        elif m is HyperComputeModule:
            c1, c2 = ch[f], args[0]
            c2 = make_divisible(min(c2, max_channels) * width, 8)
            args = [c1, c2, threshold]
        else:
            c2 = ch[f]

        if isinstance(c2, list) and m not in {ChannelTransformer, PyramidContextExtraction, CrossLayerChannelAttention, CrossLayerSpatialAttention, MutilScaleEdgeInfoGenetator}:
            is_backbone = True
            m_ = m
            m_.backbone = True
        else:
            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 + 4 if is_backbone else 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:<60}{str(args):<50}")  # print
        save.extend(x % (i + 4 if is_backbone else i) for x in ([f] if isinstance(f, int) else f) if x != -1)  # append to savelist
        layers.append(m_)
        if i == 0:
            ch = []
        if isinstance(c2, list) and m not in {ChannelTransformer, PyramidContextExtraction, CrossLayerChannelAttention, CrossLayerSpatialAttention, MutilScaleEdgeInfoGenetator}:
            ch.extend(c2)
            for _ in range(5 - len(ch)):
                ch.insert(0, 0)
        else:
            ch.append(c2)
    return nn.Sequential(*layers), sorted(save)

# 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

# 0-P1/2
# 1-P2/4
# 2-P3/8
# 3-P4/16
# 4-P5/32

# YOLOv8.0n backbone
backbone:
  # [from, repeats, module, args]
  - [-1, 1, EfficientViT_M0, []]  # 4
  - [-1, 1, SPPF, [1024, 5]]  # 5

# YOLOv8.0n head
head:
  - [-1, 1, nn.Upsample, [None, 2, 'nearest']] # 6
  - [[-1, 3], 1, Concat, [1]]  # 7 cat backbone P4
  - [-1, 3, C2f, [512]]  # 8

  - [-1, 1, nn.Upsample, [None, 2, 'nearest']] # 9
  - [[-1, 2], 1, Concat, [1]]  # 10 cat backbone P3
  - [-1, 3, C2f, [256]]  # 11 (P3/8-small)

  - [-1, 1, Conv, [256, 3, 2]] # 12
  - [[-1, 8], 1, Concat, [1]]  # 13 cat head P4
  - [-1, 3, C2f, [512]]  # 14 (P4/16-medium)

  - [-1, 1, Conv, [512, 3, 2]] # 15
  - [[-1, 5], 1, Concat, [1]]  # 16 cat head P5
  - [-1, 3, C2f, [1024]]  # 17 (P5/32-large)

  - [[11, 14, 17], 1, Detect, [nc]]  # Detect(P3, P4, P5)