1,论文解读
论文采取的方案
网络设计
实验部分
修改结构
融合MAE和Conv
2、改进YOLOv8代码 + MAE
首先在ultralytics/nn文件夹下,创建一个convnextv2.py文件,新增以下代码
import torch
import torch.nn as nn
import torch.nn.functional as F
from timm.models.layers import trunc_normal_, DropPath
import numpy.random as random
class LayerNorm(nn.Module):""" LayerNorm that supports two data formats: channels_last (