爆改YOLOv8|利用MobileNetV4 的UIB改进C2f模块-yolov8改进

最新推荐文章于 2025-04-22 07:09:32 发布

原创

最新推荐文章于 2025-04-22 07:09:32 发布

· 1.9k 阅读

23 ·

版权

文章标签：

#YOLO #yolov8 #目标检测 #python #pytorch

1，本文介绍

本文介绍了在 MobileNetV4 的 UIB 模块基础上进行的改进，即创新性地应用 C2f 模块。UIB 模块最早出现在 2024 年 5 月发布的 MobileNetV4 网络中，这是一种为移动设备高度优化的神经网络架构。其主要改进包括：引入了通用反向瓶颈（UIB）结构，以及针对移动加速器优化的全新 Mobile MQA 注意力模块。

关于UIB 的详细介绍可以看论文：[2404.10518] MobileNetV4 - Universal Models for the Mobile Ecosystem

本文将讲解如何将UIB 融合进yolov8

话不多说，上代码！

2，将UIB融合进yolov8

2.1 步骤一

找到如下的目录'ultralytics/nn/modules'，然后在这个目录下创建一个UIB.py文件，文件名字可以根据你自己的习惯起，然后将UIB的核心代码复制进去

import torch.nn as nn
from typing import Optional
import torch
 
__all__ = ['C2f_UIB']
 
 
def make_divisible(
        value: float,
        divisor: int,
        min_value: Optional[float] = None,
        round_down_protect: bool = True,
) -> int:
    """
    This function is copied from here
    "https://github.com/tensorflow/models/blob/master/official/vision/modeling/layers/nn_layers.py"
    This is to ensure that all layers have channels that are divisible by 8.
    Args:
        value: A `float` of original value.
        divisor: An `int` of the divisor that need to be checked upon.
        min_value: A `float` of  minimum value threshold.
        round_down_protect: A `bool` indicating whether round down more than 10%
        will be allowed.
    Returns:
        The adjusted value in `int` that is divisible against divisor.
    """
    if min_value is None:
        min_value = divisor
    new_value = max(min_value, int(value + divisor / 2) // divisor * divisor)
    # Make sure that round down does not go down by more than 10%.
    if round_down_protect and new_value < 0.9 * value:
        new_value += divisor
    return int(new_value)
 
def conv_2d(inp, oup, kernel_size=3