YOLOV8对于classify分类任务更换resnet18主干网络

最新推荐文章于 2024-09-05 15:06:43 发布

西柚与蓝莓

最新推荐文章于 2024-09-05 15:06:43 发布

阅读量404

点赞数 6

分类专栏： yolo 机器学习 python 文章标签： YOLO 分类

本文链接：https://blog.csdn.net/m0_53291740/article/details/141254340

版权

python 同时被 3 个专栏收录

52 篇文章 0 订阅

订阅专栏

yolo

15 篇文章 0 订阅

订阅专栏

机器学习

15 篇文章 0 订阅

订阅专栏

1. 先定义残差18模块的网络

class Resnet18(nn.Module):
    def __init__(self):
        super().__init__()
        model = models.resnet18(pretrained=True)
        self.layer=nn.Sequential(
        model.conv1,
        model.bn1,
        model.relu,
        model.maxpool,
        model.layer1,
        model.layer2,
        model.layer3,
        model.layer4,
        model.avgpool
        )
    def forward(self, x):
        x=self.layer(x)
        return x

添加到conv.py末尾

注册模块

2.task.py更改

3.更改Yaml文件

# Ultralytics YOLO 🚀, AGPL-3.0 license
# YOLOv8-cls image classification model. For Usage examples see https://docs.ultralytics.com/tasks/classify

# Parameters
nc: 1000 # number of classes
scales: # model compound scaling constants, i.e. 'model=yolov8n-cls.yaml' will call yolov8-cls.yaml with scale 'n'
  # [depth, width, max_channels]
  n: [0.33, 0.25, 1024]
  s: [0.33, 0.50, 1024]
  m: [0.67, 0.75, 1024]
  l: [1.00, 1.00, 1024]
  x: [1.00, 1.25, 1024]

# 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, 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]]

# YOLOv8.0n head
head:
  - [-1, 1, Classify, [nc]] # Classify

4.最后训练测试一下

from ultralytics import YOLO


def main():  # 不加这句有时候就会报错
    model = YOLO(r"yolov8-cls-resnet18.yaml").load('yolov8n-cls.pt') 
    model.train(data=R'E:\python_code\ultralytics-8.2.74\datasets\DIP', imgsz=128,epochs=10)

if __name__ == '__main__':  # 不加这句就会报错
    main()  # 不加这句有时候就会报错