​

​

import torch.nn as nn
from timm.models.layers import DropPath
import torch
__all__ = ['FocalModulation']
class Mlp(nn.Module):
    """ Multilayer perceptron."""
    def __init__(self, in_features, hidden_features=None, out_features=None, act_layer=nn.GELU, drop=0.):
        super().__init__()
        out_features = out_features or in_features
        hidden_features = hidden_features or in_features
        self.fc1 = nn.Linear(in_features, hidden_features)
        self.act = act_layer()
        self.fc2 = nn.Linear(hidden_features, out_features)
        self.drop = nn.Dropout(drop)
    def forward(self, x):
        x = self.fc1(x)
        x = self.act(x)
        x = self.drop(x)
        x = self.fc2(x)
        x = self.drop(x)
        return x
class FocalModulation(nn.Module):
    def __init__(self, dim, focal_window=3, focal_level=2, focal_factor=2, bias=True, proj_drop=0.,
                 use_postln_in_modulation=False, normalize_modulator=False):
        super().__init__()
        self.dim = dim
        self.focal_window = focal_window
        self.focal_level = focal_level
        self.focal_factor = focal_factor
        self.use_postln_in_modulation = use_postln_in_modulation
        self.normalize_modulator = normalize_modulator
        self.f_linear = nn.Conv2d(dim, 2 * dim + (self.focal_level + 1), kernel_size=1, bias=bias)
        self.h = nn.Conv2d(dim, dim, kernel_size=1, stride=1, bias=bias)
        self.act = nn.GELU()
        self.proj = nn.Conv2d(dim, dim, kernel_size=1)
        self.proj_drop = nn.Dropout(proj_drop)
        self.focal_layers = nn.ModuleList()
        self.kernel_sizes = []
        for k in range(self.focal_level):
            kernel_size = self.focal_factor * k + self.focal_window
            self.focal_layers.append(
                nn.Sequential(
                    nn.Conv2d(dim, dim, kernel_size=kernel_size, stride=1,
                              groups=dim, padding=kernel_size // 2, bias=False),
                    nn.GELU(),
                )
            )
            self.kernel_sizes.append(kernel_size)
    def forward(self, x):
        """
        Args:
            x: input features with shape of (B, H, W, C)
        """
        C = x.shape[1]
        # pre linear projection
        x = self.f_linear(x).contiguous()
        q, ctx, gates = torch.split(x, (C, C, self.focal_level + 1), 1)
        # context aggreation
        ctx_all = 0.0
        for l in range(self.focal_level):
            ctx = self.focal_layers[l](ctx)
            ctx_all = ctx_all + ctx * gates[:, l:l + 1]
        ctx_global = self.act(ctx.mean(2, keepdim=True).mean(3, keepdim=True))
        ctx_all = ctx_all + ctx_global * gates[:, self.focal_level:]
        # normalize context
        if self.normalize_modulator:
            ctx_all = ctx_all / (self.focal_level + 1)
        # focal modulation
        x_out = q * self.h(ctx_all)
        x_out = x_out.contiguous()
        if self.use_postln_in_modulation:
            x_out = self.ln(x_out)
        # post linear porjection
        x_out = self.proj(x_out)
        x_out = self.proj_drop(x_out)
        return x_out
class FocalModulationBlock(nn.Module):
    """ Focal Modulation Block.
    Args:
        dim (int): Number of input channels.
        mlp_ratio (float): Ratio of mlp hidden dim to embedding dim.
        drop (float, optional): Dropout rate. Default: 0.0
        drop_path (float, optional): Stochastic depth rate. Default: 0.0
        act_layer (nn.Module, optional): Activation layer. Default: nn.GELU
        norm_layer (nn.Module, optional): Normalization layer.  Default: nn.LayerNorm
        focal_level (int): number of focal levels
        focal_window (int): focal kernel size at level 1
    """
    def __init__(self, dim, mlp_ratio=4., drop=0., drop_path=0.,
                 act_layer=nn.GELU, norm_layer=nn.LayerNorm,
                 focal_level=2, focal_window=9, use_layerscale=False, layerscale_value=1e-4):
        super().__init__()
        self.dim = dim
        self.mlp_ratio = mlp_ratio
        self.focal_window = focal_window
        self.focal_level = focal_level
        self.use_layerscale = use_layerscale
        self.norm1 = norm_layer(dim)
        self.modulation = FocalModulation(
            dim, focal_window=self.focal_window, focal_level=self.focal_level, proj_drop=drop
        )
        self.drop_path = DropPath(drop_path) if drop_path > 0. else nn.Identity()
        self.norm2 = norm_layer(dim)
        mlp_hidden_dim = int(dim * mlp_ratio)
        self.mlp = Mlp(in_features=dim, hidden_features=mlp_hidden_dim, act_layer=act_layer, drop=drop)
        self.H = None
        self.W = None
        self.gamma_1 = 1.0
        self.gamma_2 = 1.0
        if self.use_layerscale:
            self.gamma_1 = nn.Parameter(layerscale_value * torch.ones((dim)), requires_grad=True)
            self.gamma_2 = nn.Parameter(layerscale_value * torch.ones((dim)), requires_grad=True)
    def forward(self, x):
        """ Forward function.
        Args:
            x: Input feature, tensor size (B, H*W, C).
            H, W: Spatial resolution of the input feature.
        """
        B, L, C = x.shape
        H, W = self.H, self.W
        assert L == H * W, "input feature has wrong size"
        shortcut = x
        x = self.norm1(x)
        x = x.view(B, H, W, C)
        # FM
        x = self.modulation(x).view(B, H * W, C)
        # FFN
        x = shortcut + self.drop_path(self.gamma_1 * x)
        x = x + self.drop_path(self.gamma_2 * self.mlp(self.norm2(x)))
        return x

​

​

# Ultralytics YOLO 🚀, AGPL-3.0 license
# YOLO11 object detection model with P3-P5 outputs. For Usage examples see https://docs.ultralytics.com/tasks/detect
# Parameters
nc: 80 # number of classes
scales: # model compound scaling constants, i.e. 'model=yolo11n.yaml' will call yolo11.yaml with scale 'n'
  # [depth, width, max_channels]
  n: [0.50, 0.25, 1024] # summary: 319 layers, 2624080 parameters, 2624064 gradients, 6.6 GFLOPs
  s: [0.50, 0.50, 1024] # summary: 319 layers, 9458752 parameters, 9458736 gradients, 21.7 GFLOPs
  m: [0.50, 1.00, 512] # summary: 409 layers, 20114688 parameters, 20114672 gradients, 68.5 GFLOPs
  l: [1.00, 1.00, 512] # summary: 631 layers, 25372160 parameters, 25372144 gradients, 87.6 GFLOPs
  x: [1.00, 1.50, 512] # summary: 631 layers, 56966176 parameters, 56966160 gradients, 196.0 GFLOPs
# YOLO11n backbone
backbone:
  # [from, repeats, module, args]
  - [-1, 1, Conv, [64, 3, 2]] # 0-P1/2
  - [-1, 1, Conv, [128, 3, 2]] # 1-P2/4
  - [-1, 2, C3k2, [256, False, 0.25]]
  - [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
  - [-1, 2, C3k2, [512, False, 0.25]]
  - [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
  - [-1, 2, C3k2, [512, True]]
  - [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32
  - [-1, 2, C3k2, [1024, True]]
  - [-1, 1, FocalModulation, []] # 9
  - [-1, 2, C2PSA, [1024]] # 10
# YOLO11n head
head:
  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
  - [[-1, 6], 1, Concat, [1]] # cat backbone P4
  - [-1, 2, C3k2, [512, False]] # 13
  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
  - [[-1, 4], 1, Concat, [1]] # cat backbone P3
  - [-1, 2, C3k2, [256, False]] # 16 (P3/8-small)
  - [-1, 1, Conv, [256, 3, 2]]
  - [[-1, 13], 1, Concat, [1]] # cat head P4
  - [-1, 2, C3k2, [512, False]] # 19 (P4/16-medium)
  - [-1, 1, Conv, [512, 3, 2]]
  - [[-1, 10], 1, Concat, [1]] # cat head P5
  - [-1, 2, C3k2, [1024, True]] # 22 (P5/32-large)
  - [[16, 19, 22], 1, Detect, [nc]] # Detect(P3, P4, P5)

import warnings
warnings.filterwarnings('ignore')
from ultralytics import YOLO
if __name__ == '__main__':
    model = YOLO('yolov8-MLLA.yaml')
    # 如何切换模型版本, 上面的ymal文件可以改为 yolov8s.yaml就是使用的v8s,
    # 类似某个改进的yaml文件名称为yolov8-XXX.yaml那么如果想使用其它版本就把上面的名称改为yolov8l-XXX.yaml即可（改的是上面YOLO中间的名字不是配置文件的）！
    # model.load('yolov8n.pt') # 是否加载预训练权重,科研不建议大家加载否则很难提升精度
    model.train(data=r"C:\Users\Administrator\PycharmProjects\yolov5-master\yolov5-master\Construction Site Safety.v30-raw-images_latestversion.yolov8\data.yaml",
                # 如果大家任务是其它的'ultralytics/cfg/default.yaml'找到这里修改task可以改成detect, segment, classify, pose
                cache=False,
                imgsz=640,
                epochs=150,
                single_cls=False,  # 是否是单类别检测
                batch=16,
                close_mosaic=0,
                workers=0,
                device='0',
                optimizer='SGD', # using SGD
                # resume='runs/train/exp21/weights/last.pt', # 如过想续训就设置last.pt的地址
                amp=True,  # 如果出现训练损失为Nan可以关闭amp
                project='runs/train',
                name='exp',
                )