tensorflow2.0学习笔记：多输入多输出

1. 多输入,对于一个wide and deep 模型，通常考虑输入不同的特征。（ tensorflow2.0学习笔记：wide and deep 模型）
2. 多输出，通常用于实现不同的任务。

import matplotlib as mpl
import matplotlib.pyplot as plt
%matplotlib inline
import numpy as np
import sklearn
import pandas as pd
import os
import sys
import time
import tensorflow as tf

from tensorflow import keras
print(tf.__version__)

2.0.0

from sklearn.datasets import fetch_california_housing
housing = fetch_california_housing()
# print(housing.DESCR)
# print(housing.data.shape)
# print(housing.target.shape)

from sklearn.model_selection import train_test_split

x_train_all, x_test, y_train_all, y_test = train_test_split(
    housing.data, housing.target, random_state = 7)
x_train, x_valid, y_train, y_valid, = train_test_split(
    x_train_all, y_train_all, random_state = 11)

from sklearn.preprocessing import StandardScaler

scaler = StandardScaler()
x_train_scaled = scaler.fit_transform(x_train)
x_valid_scaled = scaler.transform(x_valid)
x_test_scaled = scaler.transform(x_test)

多输入，多输出的实现

该模型只是一个例子，用来展示多输入，多输出的实现。

# 多输入，拆分输入 wide有5个特征(前5个)，deep有6个特征(后6个)，一共8个变量，有交集。
# 多输出，针对多个任务，这个例子中仅仅是作为一个展示用的还是房价预测。 


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

#deep model 的两个隐藏层
hidden1 = keras.layers.Dense(30,activation='relu')(input_deep)
hidden2 = keras.layers.Dense(30,activation='relu')(hidden1)

concat = keras.layers.concatenate([input_wide,hidden2]) # 拼接，输入和隐藏层
output = keras.layers.Dense(1)(concat)
output2 = keras.layers.Dense(1)(hidden2)

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

# input = [input_wide,input_deep],有两个输入
# outputs = [output,output2],有两个输出

model.summary()
model.compile(loss="mean_squared_error", optimizer="adam")
callbacks = [keras.callbacks.EarlyStopping(
    patience=5, min_delta=1e-2)]

#拆分数据，前5个input wide ，后6个input deep。
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:]

model.fit 以列表形式按顺序放好多个输入和输出

#model.fit 以列表形式按顺序放好多个输入和输出
history = model.fit([x_train_scaled_wide,x_train_scaled_deep], [y_train,y_train],
                   validation_data = ([x_valid_scaled_wide,x_valid_scaled_deep],[y_valid,y_valid]),
                   epochs = 10,
                   callbacks = callbacks)

def plot_learning_curves(history):
    pd.DataFrame(history.history).plot(figsize=(8, 5))
    plt.grid(True)
    plt.gca().set_ylim(0, 3)
    plt.show()
plot_learning_curves(history)