ECCV2020-FRELU

论文链接https://arxiv.org/pdf/2007.11824.pdf

官方代码GitHub - megvii-model/FunnelAct

paddle复现版本:FReLU:简单高效的新型激活函数 - 飞桨AI Studio

torch复现版本:GitHub - nekitmm/FunnelAct_Pytorch: pytorch implementation of Funnel Activation (FReLU)

import torch
import torch.nn as nn

class FReLU(nn.Module):
    r""" FReLU formulation. The funnel condition has a window size of kxk. (k=3 by default)
    """
    def __init__(self, in_channels):
        super().__init__()
        self.conv_frelu = nn.Conv2d(in_channels, in_channels, kernel_size = 3, stride = 1, padding = 1, groups = in_channels)
        self.bn_frelu = nn.BatchNorm2d(in_channels)
        
    def forward(self, x):
        y = self.conv_frelu(x)
        y = self.bn_frelu(y)
        x = torch.max(x, y)
        return x

这个图非常清晰的解释了ReLU、PReLU、FReLU三者的区别,所以论文可以不用看了

论文效果

 轻量网络对比

技巧

  • 1:目标检测任务

Apply FReLU to YOLOv5 · Issue #2 · megvii-model/FunnelAct · GitHub

  •  2:人脸识别任务

但也有反馈在人脸识别任务中效果不好:个人觉得应该多试试

如何评价旷视和港中大提出的FReLU(ECCV2020)? - 知乎

经验

  • 1:使用位置:网络的浅层

  • 2:逐步替换:直到overfitting

参考文献:

1:https://blog.csdn.net/m0_63642362/article/details/126236829 

猜你喜欢

转载自blog.csdn.net/lilai619/article/details/131421127
今日推荐