yolov5修改骨干网络–原网络说明

yolov5修改骨干网络-使用pytorch自带的网络-以Mobilenet和efficientnet为例

yolov5修改骨干网络-使用自己搭建的网络-以efficientnetv2为例

通过 yolov5修改骨干网络–原网络说明 我们知道：yolov5.yaml中存放的是我们模型构建参数          ，具体构建过程在yolo.py中的parse_model函数 
  
 
  
 
  
 
  
 
  
，通过循环遍历yolov5.yaml给的参数









，去寻找网络名称 
  
  
  
  
 ，并将args的参数传入网络 
  
  
  
  
 ，下面先用pytorch自带的mobile网络进行修改并替换原有yolov5网络          。

网络都是分层次的

 


 


 


 


 
，比如如果把某个网络模型Net按层次从外到内进行划分的话 
 
 
 
 
，features和classifier是Net的子层 
   
   
   
   
  ，而conv2d, ReLU, BatchNorm, Maxpool2d等基础操作可能是features的子层
 

 

 

 

 
， Linear, Dropout, ReLU等可能是classifier的子层 
  
 
  
 
  
 
  
 
  
。

model.modules()不但会遍历模型的子层
 

 

 

 

 
，还会遍历子层的子层          ，以及所有子层









。 model.children()只会遍历模型的子层 

 
 

 
 

 
 

 
 

 
，这里即是features和classifier 
  
  
  
  
 。

比如先调出pytorch中的Mobilnetv3网络









，输出一些相关信息               ，

from torchvision import models m = models.mobilenet_v3_small() print(list(m.children())[0]) print("---"*30) print(list(m.children())[1]) print("---"*30) print(list(m.children())[2]) print("len(m.modules()): ",len(list(m.modules()))) print("len(m.children()): ",len(list(m.children()))) print("len(m.children()[0]): ",len(list(m.children())[0])) -------------------------------------------------------------------- AdaptiveAvgPool2d(output_size=1) -------------------------------------------------------------------- Sequential( (0): Linear(in_features=576, out_features=1024, bias=True) (1): Hardswish() (2): Dropout(p=0.2, inplace=True) (3): Linear(in_features=1024, out_features=1000, bias=True) ) len(m.modules()): 209 len(m.children()): 3 len(m.children()[0]): 13

可以看到网络共三层 
 
 
 
 
 
 
 
 
 
，分别是0层：特征提取














，1层AdaptiveAvgPool2d          ，2层：分类层 
  
 
  
 
  
 
  
 
  
，特征提取部分共13层









，里面包含卷积 
  
  
  
  
 、BN
  
  
  
  
  、激活等 
  
  
  
  
 ，都加起来共209个这种小结构 
  
  
  
  
 。

list(m.children())[0]是网络结构 
  
  
  
  
 ，下面来具体分析

 


 


 


 


 
。

内容比较多

 


 


 


 


 
，重点关注哪里进行了下采样 
 
 
 
 
，卷积步长为2的地方 
   
   
   
   
  ，特征图就缩小一半 
 
 
 
 
。

在yolov5中是对尺寸为20
 


 


 


 


 

、40 
 
 
 
 
、80的特征图进行concat
 

 

 

 

 
，这里也是如此（当然其他尺寸也可以） 
   
   
   
   
  。

Ctrl F以下可以看到共5个地方使特征图缩小一半
 

 

 

 

 
，第一次

320

∗

320

320*320

320∗320；第二次：

160

∗

160

160*160

160∗160；第三次：

80

∗

80

80*80

80∗80；第四次：

40

∗

40

40*40

40∗40；第五次：

20

∗

20

20*20

20∗20
 

 

 

 

 
。

这样就可以划分了          ，到特征图为

40

∗

40

40*40

40∗40时 

 
 

 
 

 
 

 
 

 
，卷积在第五个操作中









，所以我们要讲前四个作为第一组               ，其输出与后面的特征图concat
 

 

 

 

 
。

同样分析后面是[4:9] 
 
 
 
 
 
 
 
 
 
，最后一块是[9:13]

分析出来后就可以开始改代码了          。

-------------------------------------------------------------------- Sequential( (0): Conv2dNormActivation( (0): Conv2d(3, 16, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False) (1): BatchNorm2d(16, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (2): Hardswish() ) (1): InvertedResidual( (block): Sequential( (0): Conv2dNormActivation( (0): Conv2d(16, 16, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), groups=16, bias=False) (1): BatchNorm2d(16, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) (1): SqueezeExcitation( (avgpool): AdaptiveAvgPool2d(output_size=1) (fc1): Conv2d(16, 8, kernel_size=(1, 1), stride=(1, 1)) (fc2): Conv2d(8, 16, kernel_size=(1, 1), stride=(1, 1)) (activation): ReLU() (scale_activation): Hardsigmoid() ) (2): Conv2dNormActivation( (0): Conv2d(16, 16, kernel_size=(1, 1), stride=(1, 1), bias=False) (1): BatchNorm2d(16, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) ) ) ) (2): InvertedResidual( (block): Sequential( (0): Conv2dNormActivation( (0): Conv2d(16, 72, kernel_size=(1, 1), stride=(1, 1), bias=False) (1): BatchNorm2d(72, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) (1): Conv2dNormActivation( (0): Conv2d(72, 72, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), groups=72, bias=False) (1): BatchNorm2d(72, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) (2): Conv2dNormActivation( (0): Conv2d(72, 24, kernel_size=(1, 1), stride=(1, 1), bias=False) (1): BatchNorm2d(24, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) ) ) ) (3): InvertedResidual( (block): Sequential( (0): Conv2dNormActivation( (0): Conv2d(24, 88, kernel_size=(1, 1), stride=(1, 1), bias=False) (1): BatchNorm2d(88, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) (1): Conv2dNormActivation( (0): Conv2d(88, 88, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=88, bias=False) (1): BatchNorm2d(88, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) (2): Conv2dNormActivation( (0): Conv2d(88, 24, kernel_size=(1, 1), stride=(1, 1), bias=False) (1): BatchNorm2d(24, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) ) ) ) (4): InvertedResidual( (block): Sequential( (0): Conv2dNormActivation( (0): Conv2d(24, 96, kernel_size=(1, 1), stride=(1, 1), bias=False) (1): BatchNorm2d(96, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (2): Hardswish() ) (1): Conv2dNormActivation( (0): Conv2d(96, 96, kernel_size=(5, 5), stride=(2, 2), padding=(2, 2), groups=96, bias=False) (1): BatchNorm2d(96, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (2): Hardswish() ) (2): SqueezeExcitation( (avgpool): AdaptiveAvgPool2d(output_size=1) (fc1): Conv2d(96, 24, kernel_size=(1, 1), stride=(1, 1)) (fc2): Conv2d(24, 96, kernel_size=(1, 1), stride=(1, 1)) (activation): ReLU() (scale_activation): Hardsigmoid() ) (3): Conv2dNormActivation( (0): Conv2d(96, 40, kernel_size=(1, 1), stride=(1, 1), bias=False) (1): BatchNorm2d(40, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) ) ) ) (5): InvertedResidual( (block): Sequential( (0): Conv2dNormActivation( (0): Conv2d(40, 240, kernel_size=(1, 1), stride=(1, 1), bias=False) (1): BatchNorm2d(240, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (2): Hardswish() ) (1): Conv2dNormActivation( (0): Conv2d(240, 240, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), groups=240, bias=False) (1): BatchNorm2d(240, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (2): Hardswish() ) (2): SqueezeExcitation( (avgpool): AdaptiveAvgPool2d(output_size=1) (fc1): Conv2d(240, 64, kernel_size=(1, 1), stride=(1, 1)) (fc2): Conv2d(64, 240, kernel_size=(1, 1), stride=(1, 1)) (activation): ReLU() (scale_activation): Hardsigmoid() ) (3): Conv2dNormActivation( (0): Conv2d(240, 40, kernel_size=(1, 1), stride=(1, 1), bias=False) (1): BatchNorm2d(40, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) ) ) ) (6): InvertedResidual( (block): Sequential( (0): Conv2dNormActivation( (0): Conv2d(40, 240, kernel_size=(1, 1), stride=(1, 1), bias=False) (1): BatchNorm2d(240, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (2): Hardswish() ) (1): Conv2dNormActivation( (0): Conv2d(240, 240, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), groups=240, bias=False) (1): BatchNorm2d(240, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (2): Hardswish() ) (2): SqueezeExcitation( (avgpool): AdaptiveAvgPool2d(output_size=1) (fc1): Conv2d(240, 64, kernel_size=(1, 1), stride=(1, 1)) (fc2): Conv2d(64, 240, kernel_size=(1, 1), stride=(1, 1)) (activation): ReLU() (scale_activation): Hardsigmoid() ) (3): Conv2dNormActivation( (0): Conv2d(240, 40, kernel_size=(1, 1), stride=(1, 1), bias=False) (1): BatchNorm2d(40, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) ) ) ) (7): InvertedResidual( (block): Sequential( (0): Conv2dNormActivation( (0): Conv2d(40, 120, kernel_size=(1, 1), stride=(1, 1), bias=False) (1): BatchNorm2d(120, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (2): Hardswish() ) (1): Conv2dNormActivation( (0): Conv2d(120, 120, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), groups=120, bias=False) (1): BatchNorm2d(120, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (2): Hardswish() ) (2): SqueezeExcitation( (avgpool): AdaptiveAvgPool2d(output_size=1) (fc1): Conv2d(120, 32, kernel_size=(1, 1), stride=(1, 1)) (fc2): Conv2d(32, 120, kernel_size=(1, 1), stride=(1, 1)) (activation): ReLU() (scale_activation): Hardsigmoid() ) (3): Conv2dNormActivation( (0): Conv2d(120, 48, kernel_size=(1, 1), stride=(1, 1), bias=False) (1): BatchNorm2d(48, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) ) ) ) (8): InvertedResidual( (block): Sequential( (0): Conv2dNormActivation( (0): Conv2d(48, 144, kernel_size=(1, 1), stride=(1, 1), bias=False) (1): BatchNorm2d(144, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (2): Hardswish() ) (1): Conv2dNormActivation( (0): Conv2d(144, 144, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), groups=144, bias=False) (1): BatchNorm2d(144, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (2): Hardswish() ) (2): SqueezeExcitation( (avgpool): AdaptiveAvgPool2d(output_size=1) (fc1): Conv2d(144, 40, kernel_size=(1, 1), stride=(1, 1)) (fc2): Conv2d(40, 144, kernel_size=(1, 1), stride=(1, 1)) (activation): ReLU() (scale_activation): Hardsigmoid() ) (3): Conv2dNormActivation( (0): Conv2d(144, 48, kernel_size=(1, 1), stride=(1, 1), bias=False) (1): BatchNorm2d(48, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) ) ) ) (9): InvertedResidual( (block): Sequential( (0): Conv2dNormActivation( (0): Conv2d(48, 288, kernel_size=(1, 1), stride=(1, 1), bias=False) (1): BatchNorm2d(288, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (2): Hardswish() ) (1): Conv2dNormActivation( (0): Conv2d(288, 288, kernel_size=(5, 5), stride=(2, 2), padding=(2, 2), groups=288, bias=False) (1): BatchNorm2d(288, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (2): Hardswish() ) (2): SqueezeExcitation( (avgpool): AdaptiveAvgPool2d(output_size=1) (fc1): Conv2d(288, 72, kernel_size=(1, 1), stride=(1, 1)) (fc2): Conv2d(72, 288, kernel_size=(1, 1), stride=(1, 1)) (activation): ReLU() (scale_activation): Hardsigmoid() ) (3): Conv2dNormActivation( (0): Conv2d(288, 96, kernel_size=(1, 1), stride=(1, 1), bias=False) (1): BatchNorm2d(96, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) ) ) ) (10): InvertedResidual( (block): Sequential( (0): Conv2dNormActivation( (0): Conv2d(96, 576, kernel_size=(1, 1), stride=(1, 1), bias=False) (1): BatchNorm2d(576, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (2): Hardswish() ) (1): Conv2dNormActivation( (0): Conv2d(576, 576, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), groups=576, bias=False) (1): BatchNorm2d(576, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (2): Hardswish() ) (2): SqueezeExcitation( (avgpool): AdaptiveAvgPool2d(output_size=1) (fc1): Conv2d(576, 144, kernel_size=(1, 1), stride=(1, 1)) (fc2): Conv2d(144, 576, kernel_size=(1, 1), stride=(1, 1)) (activation): ReLU() (scale_activation): Hardsigmoid() ) (3): Conv2dNormActivation( (0): Conv2d(576, 96, kernel_size=(1, 1), stride=(1, 1), bias=False) (1): BatchNorm2d(96, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) ) ) ) (11): InvertedResidual( (block): Sequential( (0): Conv2dNormActivation( (0): Conv2d(96, 576, kernel_size=(1, 1), stride=(1, 1), bias=False) (1): BatchNorm2d(576, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (2): Hardswish() ) (1): Conv2dNormActivation( (0): Conv2d(576, 576, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), groups=576, bias=False) (1): BatchNorm2d(576, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (2): Hardswish() ) (2): SqueezeExcitation( (avgpool): AdaptiveAvgPool2d(output_size=1) (fc1): Conv2d(576, 144, kernel_size=(1, 1), stride=(1, 1)) (fc2): Conv2d(144, 576, kernel_size=(1, 1), stride=(1, 1)) (activation): ReLU() (scale_activation): Hardsigmoid() ) (3): Conv2dNormActivation( (0): Conv2d(576, 96, kernel_size=(1, 1), stride=(1, 1), bias=False) (1): BatchNorm2d(96, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) ) ) ) (12): Conv2dNormActivation( (0): Conv2d(96, 576, kernel_size=(1, 1), stride=(1, 1), bias=False) (1): BatchNorm2d(576, eps=0.001, momentum=0.01, affine=True, track_running_stats=True) (2): Hardswish() ) )

修改代码

先写一下common.py中的MobileNet函数

class MobileNet(nn.Module): def __init__(self, *args) -> None: super().__init__() model = models.mobilenet_v3_small(pretrained=True) modules = list(model.children()) modules = modules[0][args[1]:args[2]] self.model = nn.Sequential(*modules) def forward(self, x): return self.model(x)

*args传入的是前面我们数的模型块

然后修改yolov5.yaml中的backbone














，注意第一个的output channel是第4个模型块的输出channel；第二个的output channel是第9个模型块的输出channel；第三个的output channel是第13个也就是最后一个模型块的输出channel          ，

# YOLOv5 v6.0 backbone backbone: # [from, number, module, args] [[-1, 1, MobileNet, [24, 0, 4]], # 0 [-1, 1, MobileNet, [48, 4, 9]], # 1 [-1, 1, MobileNet, [576, 9, 13]], # 2 [-1, 1, SPPF, [1024, 5]], # 3 ]

然后是改yolo.py中的parse_model 函数 
  
 
  
 
  
 
  
 
  
，很简单









，在后面加一个

elif m is MobileNet: c2 = args[0]

同理修改efficientnet_b0

class effb0(nn.Module): def __init__(self, *args) -> None: super().__init__() model = models.efficientnet_b0(pretrained=True) modules = list(model.children()) modules = modules[0][args[1]:args[2]] self.model = nn.Sequential(*modules) def forward(self, x): return self.model(x)

然后修改yaml

# YOLOv5 🚀 by Ultralytics, GPL-3.0 license # Parameters nc: 80 # number of classes depth_multiple: 0.33 # model depth multiple width_multiple: 0.25 # 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, effb0, [40,0,4]], # 0 [-1, 1, effb0, [112,4,6]], # 1 [-1, 1, effb0, [1280,6,9]], # 2 [-1, 1, SPPF, [1024, 5]], # 3 ] # YOLOv5 v6.0 head head: [[-1, 1, Conv, [512, 1, 1]], [-1, 1, nn.Upsample, [None, 2, nearest]], [[-1, 1], 1, Concat, [1]], # cat backbone P4 [-1, 3, C3, [512, False]], # 7 [-1, 1, Conv, [256, 1, 1]], [-1, 1, nn.Upsample, [None, 2, nearest]], [[-1, 0], 1, Concat, [1]], # cat backbone P3 [-1, 3, C3, [256, False]], # 11 (P3/8-small) [-1, 1, Conv, [256, 3, 2]], [[-1, 7], 1, Concat, [1]], # cat head P4 [-1, 3, C3, [512, False]], # 14 (P4/16-medium) [-1, 1, Conv, [512, 3, 2]], [[-1, 3], 1, Concat, [1]], # cat head P5 [-1, 3, C3, [1024, False]], # 17 (P5/32-large) [[11, 14, 17], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5) ]

添加parse_model

elif m is effb0: c2 = args[0]

其他的可以看看resnet
   
   
   
   
   、shufflenet 
  
  
  
  
 ，与上面两个有些许差别 
  
  
  
  
 ，我没弄出来 

 
 

 
 

 
 

 
 

 
。