在 Keras 中修剪 [英] Pruning in Keras

问题描述

我正在尝试使用 Keras 设计一个优先考虑预测性能的神经网络，但我无法通过进一步减少层数和每层节点数来获得足够高的准确度.我注意到我的很大一部分权重实际上为零(> 95％).有没有办法修剪密集层以减少预测时间?

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

不是专用的方式 :(

目前没有简单(专用)的方式使用 Keras 来做到这一点.

There's currently no easy (dedicated) way of doing this with Keras.

正在https://groups.google.com 上进行讨论/forum/#!topic/keras-users/oEecCWayJrM.

您可能也对本文感兴趣: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 Keras 中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！