Icon

Basic_​Example_​Iris_​Dataset

Simple Example for Multiclass Classification with Keras

This workflow trains a fully connected feedforward neural network with 4-8-3 units per layers to classify iris flowers.

定义网络结构并训练网络

读取和预处理鸢尾花数据
应用训练好的网络并提取预测结果
标准化
Normalizer
读取数据
Table Reader
extract prediction
Rule Engine
评估模型性能
Scorer
apply normaliz. function
Normalizer (Apply)
create collection cell of indices
Create Collection Column
数字编码,以适应神经网络的分类任务。
Rule Engine
输入层4 units
Keras Input Layer
神经网络应用
Keras Network Executor
输出层3 unitssoftmax
Keras Dense Layer
隐藏层8 unitsReLU
Keras Dense Layer
75% for 训练集25 % for测试集
Partitioning
RMSProp50 epochs
Keras Network Learner

Nodes

Extensions

Links