【问题标题】:I am confused with the kernel or filter我对内核或过滤器感到困惑
【发布时间】:2020-07-31 08:01:03
【问题描述】:

我读了一篇文章,作者使用 CNN 的方案如下:

-----------------

Input image 30*30 => Feature maps => Feature maps =>  Feature maps => Feature maps
                       28 * 28          14*14            12*12            6*6
-----------------
            Filtring 5*3*3   downsampling 2*2    Filtring 5*3*3   downsampling 2*2 

根据我的理解,我们有两个过滤器 5 * 3,最后一个 3 对应于通道 RGB 所以 3,对吗?

【问题讨论】:

    标签: machine-learning image-processing deep-learning computer-vision conv-neural-network


    【解决方案1】:

    这意味着您有 5 个 3x3 的通道(意味着 5 个过滤器/内核)。

    【讨论】:

    • 感谢您的回复
    【解决方案2】:
    What they are trying to say is that:
    
    First:
    the conv is being done using 5 different 3x3 2d kernels
    input 30x30 ==> output 5 different 28x28
    
    Second:
    max pool 2x2 ie the output dim becomes halved
    input 28x28 ==> output 14x14
    
    Third:
    the conv is being done using 5 different 3x3 2d kernels
    input 14x14 ==> output 5 different 12x12
    
    Lastly:
    max pool 2x2 ie the output dim becomes halved
    input 12x12 ==> output 6x6
    

    【讨论】:

      猜你喜欢
      • 2015-11-15
      • 1970-01-01
      • 2016-11-18
      • 1970-01-01
      • 1970-01-01
      • 1970-01-01
      • 2011-01-14
      • 2013-07-28
      • 1970-01-01
      相关资源
      最近更新 更多