内核大小等于1的Conv1D做什么

内核大小等于1的Conv1D做什么

本文介绍了内核大小等于1的Conv1D做什么?的处理方法,对大家解决问题具有一定的参考价值,需要的朋友们下面随着小编来一起学习吧!

问题描述

我读了一个将 LSTM CONV1 一起使用的示例。
(摘自:)

I read an example of using LSTM with CONV1.(Took it from: CNN LSTM)

Conv1D(filters=64, kernel_size=1, activation='relu')



  • 我知道卷积的维数是1(大小为1的一个暗角)


    1. 卷积的值是多少? (矩阵1 * 1的值是多少?)

    2. 我不知道什么是 filters = 64 ?是什么意思?

    3. relu 激活函数是否对卷积的输出起作用? (根据我的读物,似乎是这样,但我不确定)

    4. 使用 kernel_size = 1 ,就像我们在这里所做的一样?

    1. what is the value of the convolution ? (what is the value of the matrix 1*1 ?)
    2. I can't figure out what is the filters=64 ? what does it mean ?
    3. Is the relu activation function work on the output of the convolutional ? (from what I read it seems like that, but I'm not sure)
    4. what is the motivation to use convolutional with kernel_size = 1, as we do here ?


    推荐答案

    过滤器


    filters = 64 表示使用的单独过滤器数为64。
    每个过滤器将输出1个通道。也就是说,这里有64个滤波器对输入进行运算,以产生64个不同的通道(或矢量)。因此 filters 参数确定输出通道的数量。

    filters

    filters = 64 means number of separate filters used is 64.Each filter will output 1 channel. i.e. here 64 filters operate on input to produce 64 different channels(or vectors). Hence filters parameter determines number of output channels.

    kernel_size 确定卷积窗口的大小。假设 kernel_size = 1 ,则每个内核的维度将为 in_channels x 1 。因此,每个内核权重将是 in_channels x 1 维张量。

    kernel_size determines the size of the convolution window. Suppose kernel_size = 1 then each kernel will have dimension of in_channels x 1. Hence each kernel weight will be in_channels x 1 dimension tensor.

    这意味着 relu 激活将应用于卷积运算的输出。

    That means relu activation will be applied on the output of convolution operation.

    用于通过应用非线性来减少深度通道。

    Used to reduce depth channels with applying non-linearity. It will do something like weighted average across the channels while keeping receptive field.

    在您的示例中,例如: filters = 64,kernel_size = 1,激活= relu
    假设输入要素地图的大小为 100 x 10 (100个通道)。然后,图层权重将为 64 x 100 x 1 。输出大小将为 64 x 10

    In your eg: filters = 64, kernel_size = 1, activation = reluSuppose input feature map has size of 100 x 10(100 channels). Then the layer weight will of dimension 64 x 100 x 1. The output size will be 64 x 10.

    这篇关于内核大小等于1的Conv1D做什么?的文章就介绍到这了,希望我们推荐的答案对大家有所帮助,也希望大家多多支持!

08-15 18:08