wide&deep模型的多输入和多输出

wide&deep模型的多输入和多输出

在进行多输入与多输出的时候,一定要注意shape的类型要对应

下面给出一个多输入和多输出的示例:

import matplotlib as mpl
import matplotlib.pyplot as plt 
%matplotlib inline    
#为了能在notebook中显示图像
import numpy as np
import sklearn   
import pandas as pd 
import os 
import sys 
import time 
import tensorflow as tf 
from tensorflow import keras 
from sklearn.datasets import fetch_california_housing #从sklearn中引用加州的房价数据

housing = fetch_california_housing()
print(housing.DESCR)
print(housing.data.shape)
print(housing.target.shape)
#引用train_test_split对数据集进行拆分
# test_size 控制切分比例,默认切分比例3:1
from sklearn.model_selection import train_test_split  

#拆分数据集,加载数据集后返回训练集以及测试集
x_train_all, x_test, y_train_all, y_test = train_test_split(housing.data, housing.target, random_state = 1) 

#将训练集进行一次拆分为验证集和测试集
x_train, x_valid, y_train, y_valid = train_test_split(x_train_all, y_train_all, random_state=2)

print(x_train.shape, y_train.shape)
print(x_valid.shape, y_valid.shape)
print(x_test.shape, y_test.shape)

(11610, 8) (11610,)
(3870, 8) (3870,)
(5160, 8) (5160,)

from sklearn.preprocessing import StandardScaler

scaler = StandardScaler()
#对数据进行归一化处理

#由于transform处理处理数据时二维数组,所以要将数据转化一下
#x_train: [none, 28, 28] -> [none, 784]
#对于使用fit_transform 和transform 请参考我的TensorFlow中的博客
x_train_scaled = scaler.fit_transform(x_train)
x_valid_scaled = scaler.transform(x_valid)
x_test_scaled = scaler.transform(x_test)

#注意在归一化数据后,之后使用的数据要使用新的归一化数据

#这里由于是多输出,所以我们将归一化的数据在分为两个输出
x_train_scaled_wide = x_train_scaled[:, :5]
x_train_scaled_deep = x_train_scaled[:, 2:]
x_valid_scaled_wide = x_valid_scaled[:, :5]
x_valid_scaled_deep = x_valid_scaled[:, 2:]
x_test_scaled_wide = x_test_scaled[:, :5]
x_test_scaled_deep = x_test_scaled[:, 2:]
#函数式API实现wide&deep模型

#输入
input_wide = keras.layers.Input(shape = [5])
input_deep = keras.layers.Input(shape = [6])

#deep层构建
hidden1 = keras.layers.Dense(30, activation='relu')(input_deep)
hidden2 = keras.layers.Dense(30, activation= 'relu')(hidden1)

#拼接wide&deep结果
concat = keras.layers.concatenate([input_wide, hidden2])

#输出结果
output = keras.layers.Dense(1)(concat)
output2 = keras.layers.Dense(1)(hidden2)

#固化模型(Model)
model = keras.models.Model(inputs = [input_wide, input_deep],
                           outputs = [output, output2])

model.summary()
Model: "model"
__________________________________________________________________________________________________
Layer (type)                    Output Shape         Param #     Connected to                     
==================================================================================================
input_2 (InputLayer)            [(None, 6)]          0                                            
__________________________________________________________________________________________________
dense (Dense)                   (None, 30)           210         input_2[0][0]                    
__________________________________________________________________________________________________
input_1 (InputLayer)            [(None, 5)]          0                                            
__________________________________________________________________________________________________
dense_1 (Dense)                 (None, 30)           930         dense[0][0]                      
__________________________________________________________________________________________________
concatenate (Concatenate)       (None, 35)           0           input_1[0][0]                    
                                                                 dense_1[0][0]                    
__________________________________________________________________________________________________
dense_2 (Dense)                 (None, 1)            36          concatenate[0][0]                
__________________________________________________________________________________________________
dense_3 (Dense)                 (None, 1)            31          dense_1[0][0]                    
==================================================================================================
Total params: 1,207
Trainable params: 1,207
Non-trainable params: 0
__________________________________________________________________________________________________
#编译compile
model.compile(loss = "mean_squared_error",   #损失函数:使用均方根误差
             optimizer = "adam", #优化函数 
             ) 
#使用回调函数
callbacks = [
    keras.callbacks.EarlyStopping(patience=5, min_delta=1e-3),
]
#训练模型会,返回一个结果保存在history中
#注意shape要对应
history = model.fit([x_train_scaled_wide, x_train_scaled_deep],
                    (y_train,y_train),
                    epochs =10, 
                    validation_data = ([x_valid_scaled_wide, x_valid_scaled_deep], [y_valid, y_valid]), 
                    callbacks=callbacks) #使用回调函数
def plot_learning_curves(history):
    pd.DataFrame(history.history).plot(figsize=(8,5))
    plt.grid(True)
    plt.gca().set_ylim(0.2,2)
    plt.show
    
plot_learning_curves(history)
model.evaluate([x_test_scaled_wide, x_test_scaled_deep] ,[y_test, y_test])

你可能感兴趣的:(TensorFlow)