问题描述
我对Keras模型中使用的层数有些困惑.该文件在这件事上相当模糊.
I'm a bit confused about the number of layers that are used in Keras models. The documentation is rather opaque on the matter.
根据杰森·布朗利(Jason Brownlee)的说法，第一层在技术上包括两层，即由input_dim指定的输入层和一个隐藏层.请参阅他的博客上的第一个问题.
According to Jason Brownlee the first layer technically consists of two layers, the input layer, specified by input_dim and a hidden layer. See the first questions on his blog.
在所有Keras文档中，通常将第一层指定为model.add(Dense(number_of_neurons, input_dim=number_of_cols_in_input, activtion=some_activation_function)).
In all of the Keras documentation the first layer is generally specified asmodel.add(Dense(number_of_neurons, input_dim=number_of_cols_in_input, activtion=some_activation_function)).
因此，我们可以制作的最基本的模型是:
The most basic model we could make would therefore be:
model = Sequential()
model.add(Dense(1, input_dim = 100, activation = None))
此模型是由一个单层组成，其中100维输入通过单个输入神经元传递，还是由两层组成，第一层为100维输入层，第二层为一维隐藏层?
Does this model consist of a single layer, where 100 dimensional input is passed through a single input neuron, or does it consist of two layers, first a 100 dimensional input layer and second a 1 dimensional hidden layer?
此外，如果我要指定一个这样的模型，它有多少层?
Further, if I were to specify a model like this, how many layers does it have?
model = Sequential()
model.add(Dense(32, input_dim = 100, activation = 'sigmoid'))
model.add(Dense(1)))
这是一个具有1个输入层，1个隐藏层和1个输出层的模型吗?还是一个具有1个输入层和1个输出层的模型?
Is this a model with 1 input layer, 1 hidden layer, and 1 output layer or is this a model with 1 input layer and 1 output layer?
推荐答案
第一个问题，模型是:
1个输入层和1个输出层.
1 input layer and 1 output layer.
第二个问题:
1个输入层
1个隐藏层
1个激活层(乙状结肠)
1 activation layer (The sigmoid one)
1个输出层
对于输入层，这是Keras使用input_dim arg或input_shape进行抽象的，但是您可以在以下位置找到该层:
For the input layer, this is abstracted by Keras with the input_dim arg or input_shape, but you can find this layer in :
from keras.layers import Input
与激活层相同.
from keras.layers import Activation
这篇关于Keras关于层数的困惑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！