keras中的默认kernel_initializer是什么 [英] what is the default kernel_initializer in keras

问题描述

在用户手册中，下面显示了不同的kernel_initializer

In the user manual, it shows the different kernel_initializer below

https://keras.io/initializers/

主要目的是初始化神经网络中的权重矩阵.

the main purpose is to initialize the weight matrix in the neural network.

有人知道默认的初始值设定项是什么吗?该文档未显示默认值.

Anyone knows what the default initializer is? the document didn't show the default.

推荐答案

通常，默认情况下为glorot_uniform.不同的图层类型可能具有不同的默认kernel_initializer.如有疑问，只需查看源代码代码.例如，对于Dense层:

Usually, it's glorot_uniform by default. Different layer types might have different default kernel_initializer. When in doubt, just look in the source code. For example, for Dense layer:

class Dense(Layer):
...
    def __init__(self, units,
                 activation=None,
                 use_bias=True,
                 kernel_initializer='glorot_uniform',
                 bias_initializer='zeros',
                 kernel_regularizer=None,
                 bias_regularizer=None,
                 activity_regularizer=None,
                 kernel_constraint=None,
                 bias_constraint=None,
                 **kwargs):

这篇关于keras中的默认kernel_initializer是什么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！