YOLOv11改进 | 主干/Backbone篇 | 华为移动端目标检测模型Ghostnetv1改进yolov11特征提取网络

​

​

​

import torch
import torch.nn as nn
import torch.nn.functional as F
import math
 
 
__all__ = ['Ghostnetv1']
 
 
def _make_divisible(v, divisor, min_value=None):
    """
    This function is taken from the original tf repo.
    It ensures that all layers have a channel number that is divisible by 8
    It can be seen here:
    https://github.com/tensorflow/models/blob/master/research/slim/nets/mobilenet/mobilenet.py
    """
    if min_value is None:
        min_value = divisor
    new_v = max(min_value, int(v + divisor / 2) // divisor * divisor)
    # Make sure that round down does not go down by more than 10%.
    if new_v < 0.9 * v:
        new_v += divisor
    return new_v
 
 
def hard_sigmoid(x, inplace: bool = False):
    if inplace:
        return x.add_(3.).clamp_(0., 6.).div_(6.)
    else:
        return F.relu6(x + 3.) / 6.
 
 
class SqueezeExcite(nn.Module):
    def __init__(self, in_chs, se_ratio=0.25, reduced_base_chs=None,
                 act_layer=nn.ReLU, gate_fn=hard_sigmoid, divisor=4, **_):
        super(SqueezeExcite, self).__init__()
        self.gate_fn = gate_fn
        reduced_chs = _make_divisible((reduced_base_chs or in_chs) * se_ratio, divisor)
        self.avg_pool = nn.AdaptiveAvgPool2d(1)
        self.conv_reduce = nn.Conv2d(in_chs, reduced_chs, 1, bias=True)
        self.act1 = act_layer(inplace=True)
        self.conv_expand = nn.Conv2d(reduced_chs, in_chs, 1, bias=True)
 
    def forward(self, x):
        x_se = self.avg_pool(x)
        x_se = self.conv_reduce(x_se)
        x_se = self.act1(x_se)
        x_se = self.conv_expand(x_se)
        x = x * self.gate_fn(x_se)
        return x
 
 
class ConvBnAct(nn.Module):
    def __init__(self, in_chs, out_chs, kernel_size,
                 stride=1, act_layer=nn.ReLU):
        super(ConvBnAct, self).__init__()
        self.conv = nn.Conv2d(in_chs, out_chs, kernel_size, stride, kernel_size//2, bias=False)
        self.bn1 = nn.BatchNorm2d(out_chs)
        self.act1 = act_layer(inplace=True)
 
    def forward(self, x):
        x = self.conv(x)
        x = self.bn1(x)
        x = self.act1(x)
        return x
 
 
class GhostModule(nn.Module):
    def __init__(self, inp, oup, kernel_size=1, ratio=2, dw_size=3, stride=1, relu=True):
        super(GhostModule, self).__init__()
        self.oup = oup
        init_channels = math.ceil(oup / ratio)
        new_channels = init_channels*(ratio-1)
 
        self.primary_conv = nn.Sequential(
            nn.Conv2d(inp, init_channels, kernel_size, stride, kernel_size//2, bias=False),
            nn.BatchNorm2d(init_channels),
            nn.ReLU(inplace=True) if relu else nn.Sequential(),
        )
 
        self.cheap_operation = nn.Sequential(
            nn.Conv2d(init_channels, new_channels, dw_size, 1, dw_size//2, groups=init_channels, bias=False),
            nn.BatchNorm2d(new_channels),
            nn.ReLU(inplace=True) if relu else nn.Sequential(),
        )
 
    def forward(self, x):
        x1 = self.primary_conv(x)
        x2 = self.cheap_operation(x1)
        out = torch.cat([x1,x2], dim=1)
        return out[:,:self.oup,:,:]
 
 
class GhostBottleneck(nn.Module):
    """ Ghost bottleneck w/ optional SE"""
 
    def __init__(self, in_chs, mid_chs, out_chs, dw_kernel_size=3,
                 stride=1, act_layer=nn.ReLU, se_ratio=0.):
        super(GhostBottleneck, self).__init__()
        has_se = se_ratio is not None and se_ratio > 0.
        self.stride = stride
 
        # Point-wise expansion
        self.ghost1 = GhostModule(in_chs, mid_chs, relu=True)
 
        # Depth-wise convolution
        if self.stride > 1:
            self.conv_dw = nn.Conv2d(mid_chs, mid_chs, dw_kernel_size, stride=stride,
                             padding=(dw_kernel_size-1)//2,
                             groups=mid_chs, bias=False)
            self.bn_dw = nn.BatchNorm2d(mid_chs)
 
        # Squeeze-and-excitation
        if has_se:
            self.se = SqueezeExcite(mid_chs, se_ratio=se_ratio)
        else:
            self.se = None
 
        # Point-wise linear projection
        self.ghost2 = GhostModule(mid_chs, out_chs, relu=False)
 
        # shortcut
        if (in_chs == out_chs and self.stride == 1):
            self.shortcut = nn.Sequential()
        else:
            self.shortcut = nn.Sequential(
                nn.Conv2d(in_chs, in_chs, dw_kernel_size, stride=stride,
                       padding=(dw_kernel_size-1)//2, groups=in_chs, bias=False),
                nn.BatchNorm2d(in_chs),
                nn.Conv2d(in_chs, out_chs, 1, stride=1, padding=0, bias=False),
                nn.BatchNorm2d(out_chs),
            )
 
 
    def forward(self, x):
        residual = x
 
        # 1st ghost bottleneck
        x = self.ghost1(x)
 
        # Depth-wise convolution
        if self.stride > 1:
            x = self.conv_dw(x)
            x = self.bn_dw(x)
 
        # Squeeze-and-excitation
        if self.se is not None:
            x = self.se(x)
 
        # 2nd ghost bottleneck
        x = self.ghost2(x)
 
        x += self.shortcut(residual)
        return x
 
 
class GhostNet(nn.Module):
    def __init__(self, cfgs, num_classes=1000, width=1.0, dropout=0.2):
        super(GhostNet, self).__init__()
        # setting of inverted residual blocks
        self.cfgs = cfgs
        self.dropout = dropout
 
        # building first layer
        output_channel = _make_divisible(16 * width, 4)
        self.conv_stem = nn.Conv2d(3, output_channel, 3, 2, 1, bias=False)
        self.bn1 = nn.BatchNorm2d(output_channel)
        self.act1 = nn.ReLU(inplace=True)
        input_channel = output_channel
 
        # building inverted residual blocks
        stages = []
        block = GhostBottleneck
        for cfg in self.cfgs:
            layers = []
            for k, exp_size, c, se_ratio, s in cfg:
                output_channel = _make_divisible(c * width, 4)
                hidden_channel = _make_divisible(exp_size * width, 4)
                layers.append(block(input_channel, hidden_channel, output_channel, k, s,
                              se_ratio=se_ratio))
                input_channel = output_channel
            stages.append(nn.Sequential(*layers))
 
        output_channel = _make_divisible(exp_size * width, 4)
        stages.append(nn.Sequential(ConvBnAct(input_channel, output_channel, 1)))
        input_channel = output_channel
        self.blocks = nn.Sequential(*stages)
        self.width_list = [i.size(1) for i in self.forward(torch.randn(1, 3, 640, 640))]
    def forward(self, x):
        unique_tensors = {}
        x = self.conv_stem(x)
        x = self.bn1(x)
        x = self.act1(x)
        for model in self.blocks:
            x = model(x)
            if self.dropout > 0.:
                x = F.dropout(x, p=self.dropout, training=self.training)
            width, height = x.shape[2], x.shape[3]
            unique_tensors[(width, height)] = x
        result_list = list(unique_tensors.values())[-4:]
        return result_list
 
 
def Ghostnetv1(**kwargs):
    """
    Constructs a GhostNet model
    """
    cfgs = [
        # k, t, c, SE, s
        # stage1
        [[3,  16,  16, 0, 1]],
        # stage2
        [[3,  48,  24, 0, 2]],
        [[3,  72,  24, 0, 1]],
        # stage3
        [[5,  72,  40, 0.25, 2]],
        [[5, 120,  40, 0.25, 1]],
        # stage4
        [[3, 240,  80, 0, 2]],
        [[3, 200,  80, 0, 1],
         [3, 184,  80, 0, 1],
         [3, 184,  80, 0, 1],
         [3, 480, 112, 0.25, 1],
         [3, 672, 112, 0.25, 1]
        ],
        # stage5
        [[5, 672, 160, 0.25, 2]],
        [[5, 960, 160, 0, 1],
         [5, 960, 160, 0.25, 1],
         [5, 960, 160, 0, 1],
         [5, 960, 160, 0.25, 1]
        ]
    ]
    return GhostNet(cfgs, **kwargs)
 
 
if __name__=='__main__':
    model = Ghostnetv1()
    model.eval()
    input = torch.randn(16,3,224,224)
    y = model(input)
    print(y.size())

​

​

​

        elif m in {自行添加对应的模型即可，下面都是一样的}:
            m = m(*args)
            c2 = m.width_list  # 返回通道列表
            backbone = True

        if isinstance(c2, list):
            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 backbone else i, f, t  # attach index, 'from' index, type

    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 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)
            if hasattr(m, 'backbone'):
                x = m(x)
                if len(x) != 5:  # 0 - 5
                    x.insert(0, None)
                for index, i in enumerate(x):
                    if index in self.save:
                        y.append(i)
                    else:
                        y.append(None)
                x = x[-1]  # 最后一个输出传给下一层
            else:
                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)
            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

​

# 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
 
# 共四个版本  "mobile_vit_small, mobile_vit_x_small, mobile_vit_xx_small"
# YOLO11n backbone
backbone:
  # [from, repeats, module, args]
  - [-1, 1, Ghostnetv1, []] # 0-4 P1/2
  - [-1, 1, SPPF, [1024, 5]] # 5
  - [-1, 2, C2PSA, [1024]] # 6
 
# YOLO11n head
head:
  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
  - [[-1, 3], 1, Concat, [1]] # cat backbone P4
  - [-1, 2, C3k2, [512, False]] # 9
 
  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
  - [[-1, 2], 1, Concat, [1]] # cat backbone P3
  - [-1, 2, C3k2, [256, False]] # 12 (P3/8-small)
 
  - [-1, 1, Conv, [256, 3, 2]]
  - [[-1, 9], 1, Concat, [1]] # cat head P4
  - [-1, 2, C3k2, [512, False]] # 15 (P4/16-medium)
 
  - [-1, 1, Conv, [512, 3, 2]]
  - [[-1, 6], 1, Concat, [1]] # cat head P5
  - [-1, 2, C3k2, [1024, True]] # 18 (P5/32-large)
 
  - [[12, 15, 18], 1, Detect, [nc]] # Detect(P3, P4, P5)

import warnings
warnings.filterwarnings('ignore')
from ultralytics import YOLO
 
if __name__ == '__main__':
    model = YOLO("替换你的yaml文件地址")
    model.load('yolov8n.pt') 
    model.train(data=r'你的数据集的地址',
                cache=False,
                imgsz=640,
                epochs=150,
                batch=4,
                close_mosaic=0,
                workers=0,
                device=0,
                optimizer='SGD'
                amp=False,
                )