yolov5主干网络换残差18

目录

1.网络结构

​编辑 1.1 三层如下定义

1.2 在common.py后面加入如下刚刚定义的网络，就是上面的代码的一部分

2.  如此修改网络的yaml文件，yolov5n_res18.yaml

3.  修改yolo网络并运行

---

1.网络结构

残差18网络如下

可做出如下修改

 1.1 三层如下定义

import torch
from torch import nn
from torchvision import models
from torchinfo import summary


class resnet18(nn.Module):
    def __init__(self,n):
        super().__init__()
        model = models.resnet18(pretrained=True)
        if n==1:
            layer=[]
            layer+=[model.conv1]
            layer+=[model.bn1]
            layer+=[model.relu]
            layer+=[model.maxpool]
            layer+=[model.layer1]
            layer+=[model.layer2]
            self.model=nn.Sequential(*layer)
        if n==2:
            self.model=model.layer3
        if n==3:
            self.model=model.layer4
    def forward(self, x):
        return self.model(x)
if __name__ == '__main__':
    x=torch.randn(1,3,640,640)#torch.Size([1, 128, 80, 80])
    x=torch.randn(1, 128, 80, 80)#torch.Size([1, 256, 40, 40]
    x=torch.randn(1, 256, 40, 40)#torch.Size([1, 512, 20, 20])
    net=resnet18(3)#
    out=net(x)
    print(out.shape)
    # summary(net,(1,3,640,640))

1.2 在common.py后面加入如下刚刚定义的网络，就是上面的代码的一部分

 

2.  如此修改网络的yaml文件，yolov5n_res18.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, resnet18, [ 128, 1 ] ],  # 0-P1/2
    [ -1, 1, resnet18, [ 256,2 ] ],  # 1-P2/4
    [ -1, 1, resnet18, [ 512,3 ] ],
  ]
# 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 ] ],  # 13

    [ -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 ] ],  # 17 (P3/8-small)

    [ -1, 1, Conv, [ 256, 3, 2 ] ],
    [ [ -1, 7 ], 1, Concat, [ 1 ] ],  # cat head P4
    [ -1, 3, C3, [ 512, False ] ],  # 20 (P4/16-medium)

    [ -1, 1, Conv, [ 512, 3, 2 ] ],
    [ [ -1, 3 ], 1, Concat, [ 1 ] ],  # cat head P5
    [ -1, 3, C3, [ 1024, False ] ],  # 23 (P5/32-large)

    [ [ 10, 13, 16 ], 1, Detect, [ nc, anchors ] ],  # Detect(P3, P4, P5)
  ]

3.  修改yolo网络并运行

需要导包的可以自己导一下

更换网络后run一下yolo.py的参数如下