问题描述
构建卷积神经网络时，如何确定每个卷积层中使用的过滤器数量.我知道关于过滤器的数量没有硬性规定，但是根据您的经验/阅读过的论文等，是否有关于使用的过滤器数量的直觉/观察?
When building a convolutional neural network, how do you determine the number of filters used in each convolutional layer. I know that there is no hard rule about the number of filters, but from your experience/ papers you have read, etc. is there an intuition/observation about number of filters used?
例如(我仅以此为例):
For instance (I'm just making this up as example):
-
随着网络的深入，使用更多/更少的过滤器.
use more/less filters as the network gets deeper.
使用内核大小较大/较小的过滤器
use larger/smaller filter with large/small kernel size
推荐答案
正如您所说，对此没有硬性规定.
As you said, there are no hard rules for this.
例如，您可以从VGG16那里获得启发.
But you can get inspiration from VGG16 for example.
它使每个转换层之间的过滤器数量增加了一倍.对于内核大小，我通常保持3x3或5x5.
It double the number of filters between each conv layers.For the kernel size, I usually keep 3x3 or 5x5.
但是，您也可以看看Google的Inception.他们使用不同的内核大小，然后合并它们.非常有趣.
But, you can also take a look at Inception by Google.They use varying kernel size, then concat them. Very interesting.
这篇关于如何选择每个卷积层中的滤波器数量?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！