如何在Keras中实现平均池化层 [英] How to implement a Mean Pooling layer in Keras

问题描述

在Keras中似乎没有内置支持RNN的平均池化层.有人知道如何包装吗?

There seems no built-in support for Mean Pooling layer for RNN in Keras. Anyone knows how to wrap one?

http://deeplearning.net/tutorial/lstm.html

推荐答案

Keras为此提供了一层AveragePooling1D.如果使用图谱API，则应该能够执行以下操作:

Keras has a layer AveragePooling1D for that. If you use the graph API, you should be able to do something like:

model.add_node(AveragePooling1D(...), 
               inputs=['h0', 'h1', ..., 'hn'], 
               merge_mode='concat', ...)

这篇关于如何在Keras中实现平均池化层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！