wide_deep模型的多输入与输出实战

使用函数式API实现wide_deep模型的多输入:

关键代码展示：

# 多输入,使用函数式方法
input_wide = keras.layers.Input(shape=[5]) #取前5个feature做为wide模型的输入
input_deep = keras.layers.Input(shape=[6]) ##取后6个feature做为wide模型的输入
hidden1 = keras.layers.Dense(30, activation='relu')(input_deep)
hidden2 = keras.layers.Dense(30, activation='relu')(hidden1)
concat = keras.layers.concatenate([input_wide, hidden2])
output = keras.layers.Dense(1)(concat)
model = keras.models.Model(inputs = [input_wide, input_deep],
                           outputs = [output])
        
model.compile(loss="mean_squared_error", optimizer="sgd")
callbacks = [keras.callbacks.EarlyStopping(
    patience=5, min_delta=1e-2)]
model.summary()

模型层次结构展示： 

附完整代码：

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__)
print(sys.version_info)
for module in mpl, np, pd, sklearn, tf, keras:
    print(module.__name__, module.__version__)

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

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,使用函数式方法
input_wide = keras.layers.Input(shape=[5]) #取前5个feature做为wide模型的输入
input_deep = keras.layers.Input(shape=[6]) ##取后6个feature做为wide模型的输入
hidden1 = keras.layers.Dense(30, activation='relu')(input_deep)
hidden2 = keras.layers.Dense(30, activation='relu')(hidden1)
concat = keras.layers.concatenate([input_wide, hidden2])
output = keras.layers.Dense(1)(concat)
model = keras.models.Model(inputs = [input_wide, input_deep],
                           outputs = [output])
        

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

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:]

history = model.fit([x_train_scaled_wide, x_train_scaled_deep],
                    y_train,
                    validation_data = (
                        [x_valid_scaled_wide, x_valid_scaled_deep],
                        y_valid),
                    epochs = 100,
                    callbacks = callbacks)

def plot_learning_curves(history):
    pd.DataFrame(history.history).plot(figsize=(8, 5))
    plt.grid(True)
    plt.gca().set_ylim(0, 1)
    plt.show()
plot_learning_curves(history)

model.evaluate([x_test_scaled_wide, x_test_scaled_deep], y_test, verbose=0)

 使用函数式API实现wide_deep模型的多输出:

note：这种多输出并不是wide_deep模型所需要的，而是在现实问题中可能会遇到的一种形式，这种多输出的网络结构，主要是针对多任务学习的问题，例如想预测当前的房价，和一年后的房价，这样就有了两个预测任务。

下面的实现是：假设另外一个问题也是学习预测当前房价，（两个问题都是学习预测当前房价），第二个任务利用hidden2来实现。

关键代码展示：

# 多输出
input_wide = keras.layers.Input(shape=[5])
input_deep = keras.layers.Input(shape=[6])
hidden1 = keras.layers.Dense(30, activation='relu')(input_deep)
hidden2 = keras.layers.Dense(30, activation='relu')(hidden1)
concat = keras.layers.concatenate([input_wide, hidden2])
output = keras.layers.Dense(1)(concat)
output2 = keras.layers.Dense(1)(hidden2)
model = keras.models.Model(inputs = [input_wide, input_deep],
                           outputs = [output, output2])
        
model.compile(loss="mean_squared_error", optimizer="sgd")
callbacks = [keras.callbacks.EarlyStopping(
    patience=5, min_delta=1e-2)]
model.summary()

 

附完整代码：

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__)
print(sys.version_info)
for module in mpl, np, pd, sklearn, tf, keras:
    print(module.__name__, module.__version__)

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

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)

# 多输出
input_wide = keras.layers.Input(shape=[5])
input_deep = keras.layers.Input(shape=[6])
hidden1 = keras.layers.Dense(30, activation='relu')(input_deep)
hidden2 = keras.layers.Dense(30, activation='relu')(hidden1)
concat = keras.layers.concatenate([input_wide, hidden2])
output = keras.layers.Dense(1)(concat)
output2 = keras.layers.Dense(1)(hidden2)
model = keras.models.Model(inputs = [input_wide, input_deep],
                           outputs = [output, output2])
        

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

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:]

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 = 100,
                    callbacks = callbacks)

def plot_learning_curves(history):
    pd.DataFrame(history.history).plot(figsize=(8, 5))
    plt.grid(True)
    plt.gca().set_ylim(0, 1)
    plt.show()
plot_learning_curves(history)

model.evaluate([x_test_scaled_wide, x_test_scaled_deep],
               [y_test, y_test], verbose=0)