CSPPC模块替换c2f模块(YOLOv8)

炸弹天堂

于 2024-07-28 19:51:32 发布

阅读量88

点赞数 4

文章标签： YOLO

本文链接：https://blog.csdn.net/weixin_45932783/article/details/140754980

版权

YOLOv8轻量化(CSPPC模块替换c2f)

YOLOv8模型参数：

在这里插入图片描述

YOLOv8模型（CSPPC模块替换c2f）参数：

在这里插入图片描述

1.在…/ultralytics/ultralytics/nn/modules下新建CSPPC.py文件夹

import torch
import torch.nn as nn

__all__ = ['CSPPC']


def autopad(k, p=None, d=1): 
    if d > 1:
        k = d * (k - 1) + 1 if isinstance(k, int) else [d * (x - 1) + 1 for x in k]
    if p is None:
        p = k // 2 if isinstance(k, int) else [x // 2 for x in k]
    return p


class Conv(nn.Module):
    default_act = nn.SiLU()

    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()

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

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


class Partial_conv3(nn.Module):
    def __init__(self, dim, n_div, forward):
        super().__init__()
        self.dim_conv3 = dim // n_div
        self.dim_untouched = dim - self.dim_conv3
        self.partial_conv3 = nn.Conv2d(self.dim_conv3, self.dim_conv3, 3, 1, 1, bias=False)

        if forward == 'slicing':
            self.forward = self.forward_slicing
        elif forward == 'split_cat':
            self.forward = self.forward_split_cat
        else:
            raise NotImplementedError

    def forward_slicing(self, x):
        x = x.clone()
        x[:, :self.dim_conv3, :, :] = self.partial_conv3(x[:, :self.dim_conv3, :, :])
        return x

    def forward_split_cat(self, x):
        x1, x2 = torch.split(x, [self.dim_conv3, self.dim_untouched], dim=1)
        x1 = self.partial_conv3(x1)
        x = torch.cat((x1, x2), 1)
        return x


class CSPPC_Bottleneck(nn.Module):
    def __init__(self, dim):
        super().__init__()
        self.DualPConv = nn.Sequential(Partial_conv3(dim, n_div=4, forward='split_cat'),Partial_conv3(dim, n_div=4, forward='split_cat'))

    def forward(self, x):
        return self.DualPConv(x)


class CSPPC(nn.Module):
    def __init__(self, c1, c2, n=1, shortcut=False, g=1, e=0.5):
        super().__init__()
        self.c = int(c2 * e)
        self.cv1 = Conv(c1, 2 * self.c, 1, 1)
        self.cv2 = Conv((2 + n) * self.c, c2, 1)
        self.m = nn.ModuleList(CSPPC_Bottleneck(self.c) 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))

2.在…/ultralytics/ultralytics/nn/modules/init.py文件中导入CSPPC

在这里插入图片描述

3.在…/ultralytics/ultralytics/nn/tasks.py文件中添加CSPPC

1）先导入

在这里插入图片描述

2）在parse_model函数中导入CSPPC

在这里插入图片描述

4.在…/ultralytics/ultralytics/cfg/models/v8中新建文件夹yolov8-CSPPC.yaml

nc: 80  # number of classes
scales:  # model compound scaling constants, i.e. 'model=yolov8n.yaml' will call yolov8.yaml with scale 'n'
  # [depth, width, max_channels]
  n: [0.33, 0.25, 1024]  # YOLOv8n summary: 225 layers,  3157200 parameters,  3157184 gradients,   8.9 GFLOPs
  s: [0.33, 0.50, 1024]  # YOLOv8s summary: 225 layers, 11166560 parameters, 11166544 gradients,  28.8 GFLOPs
  m: [0.67, 0.75, 768]   # YOLOv8m summary: 295 layers, 25902640 parameters, 25902624 gradients,  79.3 GFLOPs
  l: [1.00, 1.00, 512]   # YOLOv8l summary: 365 layers, 43691520 parameters, 43691504 gradients, 165.7 GFLOPs
  x: [1.00, 1.25, 512]   # YOLOv8x summary: 365 layers, 68229648 parameters, 68229632 gradients, 258.5 GFLOPs
 
# YOLOv8.0n backbone
backbone:
  # [from, repeats, module, args]
  - [-1, 1, Conv, [64, 3, 2]]  # 0-P1/2
  - [-1, 1, Conv, [128, 3, 2]]  # 1-P2/4
  - [-1, 3, CSPPC, [128, True]]
  - [-1, 1, Conv, [256, 3, 2]]  # 3-P3/8
  - [-1, 6, CSPPC, [256, True]]
  - [-1, 1, Conv, [512, 3, 2]]  # 5-P4/16
  - [-1, 6, CSPPC, [512, True]]
  - [-1, 1, Conv, [1024, 3, 2]]  # 7-P5/32
  - [-1, 3, CSPPC, [1024, True]]
  - [-1, 1, SPPF, [1024, 5]]  # 9
 
# YOLOv8.0n head
head:
  - [-1, 1, nn.Upsample, [None, 2, 'nearest']]
  - [[-1, 6], 1, Concat, [1]]  # cat backbone P4
  - [-1, 3, CSPPC, [512]]  # 12
 
  - [-1, 1, nn.Upsample, [None, 2, 'nearest']]
  - [[-1, 4], 1, Concat, [1]]  # cat backbone P3
  - [-1, 3, CSPPC, [256]]  # 15 (P3/8-small)
 
  - [-1, 1, Conv, [256, 3, 2]]
  - [[-1, 12], 1, Concat, [1]]  # cat head P4
  - [-1, 3, CSPPC, [512]]  # 18 (P4/16-medium)
 
  - [-1, 1, Conv, [512, 3, 2]]
  - [[-1, 9], 1, Concat, [1]]  # cat head P5
  - [-1, 3, CSPPC, [1024]]  # 21 (P5/32-large)
 
  - [[15, 18, 21], 1, Detect, [nc]]  # Detect(P3, P4, P5)

5.在…/ultralytics文件夹中新建train.py文件夹

from ultralytics import YOLO

if __name__ == '__main__':

    model = YOLO('yolov8-CSPPC.yaml')  # build from YAML and transfer weights

    # Train the model
    results = model.train(data='your_data.yaml', epochs=300, imgsz=640, batch=32)