在凯拉斯修剪 [英] Pruning in Keras
问题描述
我正在尝试使用优先考虑预测性能的Keras设计神经网络,并且通过进一步减少每层的层数和节点数,我无法获得足够高的精度.我注意到我的很大一部分权重实际上为零(> 95%).有没有一种方法可以修剪密集的层以减少预测时间?
I'm trying to design a neural network using Keras with priority on prediction performance, and I cannot get sufficiently high accuracy by further reducing the number of layers and nodes per layer. I have noticed that very large portion of my weights are effectively zero (>95%). Is there a way to prune dense layers in hope of reducing prediction time?
推荐答案
不是专用方法:(
目前,使用Keras尚无简便(专用)的方法.
There's currently no easy (dedicated) way of doing this with Keras.
https://groups.google.com上正在进行讨论. /forum/#!topic/keras-users/oEecCWayJrM .
您可能对本文也有兴趣: https://arxiv.org/pdf/1608.04493v1 .pdf .
You may also be interested in this paper: https://arxiv.org/pdf/1608.04493v1.pdf.
这篇关于在凯拉斯修剪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IT屋!