Keras CuDNNLSTM隐式激活函数? [英] Keras CuDNNLSTM implicit activation function?

问题描述

在 tf.keras.layers.LSTM 有一个activation参数(默认为tanh)
CuDNNLSTM 没有任何内容，但具有activity_regularizer参数.
我想念什么吗?

CuDNNLSTM不是tf.keras.layers.LSTM包装器，而是独立的实体，那么如何为它设置激活功能?

While in tf.keras.layers.LSTM there is an activation parameter (default tanh)
the CuDNNLSTM doesn't have any, while having a activity_regularizer parameter.
Am I missing something?

CuDNNLSTM is not a tf.keras.layers.LSTM wrapper, but a standalone entity, so how do I set the activation function for it?

推荐答案

CuDNNLSTM具有硬编码的tanh激活.据我所知，这是无法更改的.如果需要其他激活，则可以使用常规LSTM层.

CuDNNLSTM has a hardcoded tanh activation. As far as I am aware, there is no way for this to be changed. If you need some other activation, you're stuck using a regular LSTM layer.

或者，如果您只需要为模型激活特定的输出，例如softmax，您可以粘贴在Dense层上，然后再进行激活.这是我针对特定情况的操作方式的摘要:

Alternately, if you only need a specific output activation for your model, e.g. softmax, you can stick on a Dense layer and then put the activation after that. Here's a snippet of how I'm doing that for my particular case:

x = CuDNNLSTM(256, return_sequences=True)(x)
x = TimeDistributed(Dense(8))(x)
x = Softmax(axis=2)(x)

进一步阅读:

• https://github.com/keras-team/keras/issues/8510
• https://devblogs.nvidia.com/optimizing- recurrent-neural-networks-cudnn-5/

• https://github.com/keras-team/keras/issues/8510
• https://devblogs.nvidia.com/optimizing-recurrent-neural-networks-cudnn-5/

这篇关于Keras CuDNNLSTM隐式激活函数?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！