[英]Creating NN architecture with multiple inputs using Keras
I want to create a model with the following architecture: 我要创建一个具有以下架构的模型:
i_1 i_2 i_3 (3 input nodes)
h1_1 ..... h1_j ...... h1_n ('n' nodes in 1st hidden layer)
h2_1 ....... h2_j......... h2_m ('m' nodes in 2nd hidden layer)
o (1 output)
Further Details 更多详情
How can I achieve this in Keras? 如何在Keras中实现这一目标?
This looks like a basic feed-forward network: 这看起来像一个基本的前馈网络:
model = Sequential()
model.add(Dense(n, input_dim=3))
model.add(Dense(m))
model.add(Dense(1))
You can specify activation
parameters independently for each layer. 您可以为每个层独立指定activation
参数。
声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.