0


Yolov5/Yolov7加入Yolov8 c2f模块,涨点

1.Yolov8简介

    Ultralytics YOLOv8 是由 Ultralytics 开发的一个前沿的 SOTA 模型。它在以前成功的 YOLO 版本基础上,引入了新的功能和改进,进一步提升了其性能和灵活性。YOLOv8 基于快速、准确和易于使用的设计理念,使其成为广泛的目标检测、图像分割和图像分类任务的绝佳选择。

下表为官方在 COCO Val 2017 数据集上测试的 mAP、参数量和 FLOPs 结果。可以看出 YOLOv8 相比 YOLOv5 精度提升非常多,但是 N/S/M 模型相应的参数量和 FLOPs 都增加了不少;
模型尺寸
(像素)mAPval
50-95推理速度
CPU ONNX
(ms)推理速度
A100 TensorRT
(ms)参数量
(M)FLOPs
(B)YOLOv8n64037.380.40.993.28.7YOLOv8s64044.9128.41.2011.228.6YOLOv8m64050.2234.71.8325.978.9YOLOv8l64052.9375.22.3943.7165.2YOLOv8x64053.9479.13.5368.2257.8

1.1 Yolov8优化点:

  将 YOLOv5 的C3结构换成了梯度流更丰富的 
C2f

结构,并对不同尺度模型调整了不同的通道数

C3模块的结构图,然后再对比与C2f的具体的区别。针对C3模块,其主要是借助CSPNet提取分流的思想,同时结合残差结构的思想,设计了C3 Block,CSP主分支梯度模块为BottleNeck模块。同时堆叠的个数由参数n来进行控制,也就是说不同规模的模型,n的值是有变化的。

C3模块的Pytorch的实现如下:

class C3(nn.Module):  
    # CSP Bottleneck with 3 convolutions  
    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 = Conv(c1, c_, 1, 1)  
        self.cv3 = Conv(2 * c_, c2, 1)  # optional act=FReLU(c2)  
        self.m = nn.Sequential(*(Bottleneck(c_, c_, shortcut, g, e=1.0) for _ in range(n)))  
  
    def forward(self, x):  
        return self.cv3(torch.cat((self.m(self.cv1(x)), self.cv2(x)), 1))  

C2f模块的结构图如下:

   C2f模块就是参考了C3模块以及ELAN的思想进行的设计,让YOLOv8可以在保证轻量化的同时获得更加丰富的梯度流信息。

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(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)) 

2.涨点技巧:Yolov5加入C2F提升小目标检测精度

2.1 Yolov5网络结构图

2.2 加入C2f代码修改位置

1)将如下代码添加到**

common.py

**中:

class v8_C2fBottleneck(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_C2fBottleneck(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))

2)在**

yolo.py

**中添加

C2f(PS:快速搜索C3对应位置)

2.3 修改配置文件

yolov8s.yaml

1)加入backbone

# 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)
  ]

改进后的网络图

  1. 加入head
# 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, 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, C2f, [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, C2f, [256, False]],  # 17 (P3/8-small)

   [-1, 1, Conv, [256, 3, 2]],
   [[-1, 14], 1, Concat, [1]],  # cat head P4
   [-1, 3, C2f, [512, False]],  # 20 (P4/16-medium)

   [-1, 1, Conv, [512, 3, 2]],
   [[-1, 10], 1, Concat, [1]],  # cat head P5
   [-1, 3, C2f, [1024, False]],  # 23 (P5/32-large)

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

3.总结

针对小目标等提升精度较显著


本文转载自: https://blog.csdn.net/m0_63774211/article/details/129493630
版权归原作者 AI&CV 所有, 如有侵权,请联系我们删除。

“Yolov5/Yolov7加入Yolov8 c2f模块,涨点”的评论:

还没有评论