zoukankan      html  css  js  c++  java
  • Convolution 中 group 参数

    1. caffe 官方文档定义:

      group (g) [default 1]: If g > 1, we restrict the connectivity of each filter to a subset of the input. Specifically, the input and output channels are separated into g groups, and the i-th output group channels will be only connected to the i-th input group channels.

    2. Jia Yangqing 论坛回复:

      It was there to implement the grouped convolution in Alex Krizhevsky's paper: when group=2, the first half of the filters are only connected to the first half of the input channels, and the second half only connected to the second half.

      To group seems like a historical accident from the practical constraints of the time, but I don't know of a side-by-side comparison of group and no-group models. It could be nice to settle the question on the axes of task performance, speed + memory, and optimization time + hassle.

    3. Alex Krizhevsky's paper 中conv的定义:

      convolution_param {
      num_output: 256
      pad: 2
      kernel_size: 5
      group: 2
      weight_filler {
      type: "gaussian"
      std: 0.01
      }
      bias_filler {
      type: "constant"
      value: 1
      }

    结论:Alex文章中是多个显卡,可能基于并行内存等考虑。所以以后少用。。。

    reference:
    http://caffe.berkeleyvision.org/tutorial/layers.html
    https://github.com/BVLC/caffe/issues/778

  • 相关阅读:
    设置eclipse编码
    前端基础知识
    微信小程序
    jQuery下拉框
    Vue-cli的安装
    vue的数据交互形式
    node安装和小测试
    shui
    JQ-滚动条下拉无限的加载数据
    HTML-video全屏
  • 原文地址:https://www.cnblogs.com/penguins/p/5103360.html
Copyright © 2011-2022 走看看