如何在Keras中设置内核初始化程序(glorot_uniform)的种子值 [英] How to set seed value of kernel initializer (glorot_uniform) in Keras

问题描述

我想在Keras中设置glorot_uniform内核初始化程序的种子值.

I'd like to set seed value of glorot_uniform kernel initializer in Keras.

model.add(Dense(50, input_dim=self.state_size, activation='relu', kernel_initializer='glorot_uniform(seed=0)'))

当我使用上面的代码时，错误消息在下面.

When I use above code, error message is below.

ValueError: Unknown initializer: glorot_uniform(seed=0)

如果我如下删除(seed = 0)"

If I remove "(seed=0)" like as below

 model.add(Dense(50, input_dim=self.state_size, activation='relu', kernel_initializer='glorot_uniform'))

在不设置种子值的情况下效果很好.

It works well without setting a seed value.

如何设置种子值?

推荐答案

Keras可以将字符串和函数用作初始化程序的参数.这些字符串仅使用初始化程序的默认选项. 为您的FC层尝试以下代码:

Keras can use strings and functions as arguments for initilizers. The strings just use the default options for initializers. Try this line of code for your FC layer:

from keras import initializers
model.add(Dense(50, input_dim=self.state_size, activation='relu', kernel_initializer=initializers.glorot_uniform(seed=0)))

这里您具有初始化程序的文档: https://keras.io/initializers

Here you have the documentation for the initializers: https://keras.io/initializers

这篇关于如何在Keras中设置内核初始化程序(glorot_uniform)的种子值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！