本文共 13949 字，大约阅读时间需要 46 分钟。

本文将介绍：

• wide_deep模型
• 函数API实现wide&deep模型
• 子类API实现wide&deep模型
• wide&deep模型的多输入
• wide&deep模型的多输出

一，wide_deep模型简介

二，函数API实现wide&deep模型

1，函数API实现wide&deep代码如下

input = keras.layers.Input(shape=x_train.shape[1:])hidden1 = keras.layers.Dense(30, activation='relu')(input)hidden2 = keras.layers.Dense(30, activation='relu')(hidden1)# 复合函数: f(x) = h(g(x))concat = keras.layers.concatenate([input, hidden2])output = keras.layers.Dense(1)(concat)model = keras.models.Model(inputs = [input], outputs = [output])model.summary()model.compile(loss="mean_squared_error",optimizer = keras.optimizers.SGD(0.001))

2，总结代码如下

#!/usr/bin/env python3# -*- coding: utf-8 -*-import matplotlib as mplimport matplotlib.pyplot as pltimport numpy as npimport sklearnimport pandas as pdimport osimport sysimport timeimport tensorflow as tffrom tensorflow import keras# 1,打印使用的python库的版本信息print(tf.__version__)print(sys.version_info)for module in mpl, np, pd, sklearn, tf, keras:    print(module.__name__, module.__version__)    # 2,下载并使用sklearn中的“fetch_california_housing”数据集from sklearn.datasets import fetch_california_housinghousing = fetch_california_housing()print(housing.DESCR)print(housing.data.shape)print(housing.target.shape)# 3,拆分数据集中的数据为 训练数据、验证数据、测试数据from sklearn.model_selection import train_test_splitx_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)# 4,在将数据带入到模型之前，先进行预处理-训练、验证、测试数据标准化from sklearn.preprocessing import StandardScalerscaler = StandardScaler()x_train_scaled = scaler.fit_transform(x_train)x_valid_scaled = scaler.transform(x_valid)x_test_scaled = scaler.transform(x_test)# 5,构建wide_deep回归模型、模型层级图、编译模型（添加损失函数、优化器）、添加回调函数# 函数式API 功能APIinput = keras.layers.Input(shape=x_train.shape[1:])hidden1 = keras.layers.Dense(30, activation='relu')(input)hidden2 = keras.layers.Dense(30, activation='relu')(hidden1)# 复合函数: f(x) = h(g(x))concat = keras.layers.concatenate([input, hidden2])output = keras.layers.Dense(1)(concat)model = keras.models.Model(inputs = [input], outputs = [output])model.summary()model.compile(loss="mean_squared_error",optimizer = keras.optimizers.SGD(0.001))# 定义 callbacks logdir = './dnn-bn-callbacks'if not os.path.exists(logdir):    os.mkdir(logdir)output_model_file = os.path.join(logdir,"fashion_mnist_model.h5")callbacks = [    keras.callbacks.TensorBoard(logdir),    keras.callbacks.ModelCheckpoint(output_model_file,save_best_only = True),    keras.callbacks.EarlyStopping(patience=5, min_delta=1e-3)]# 6,训练构建的模型history = model.fit(x_train_scaled, y_train,                    validation_data = (x_valid_scaled, y_valid),                    epochs = 200,                    callbacks = callbacks) # 7,得到训练曲线图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)# 8,调用估计器print(model.evaluate(x_test_scaled, y_test, verbose=0))

三，子类API实现wide&deep模型

1，子类API实现wide&deep代码如下

# 子类APIclass WideDeepModel(keras.models.Model):    def __init__(self):        super(WideDeepModel, self).__init__()        """定义模型的层次"""        self.hidden1_layer = keras.layers.Dense(30, activation='relu')        self.hidden2_layer = keras.layers.Dense(30, activation='relu')        self.output_layer = keras.layers.Dense(1)        def call(self, input):        """完成模型的正向计算"""        hidden1 = self.hidden1_layer(input)        hidden2 = self.hidden2_layer(hidden1)        concat = keras.layers.concatenate([input, hidden2])        output = self.output_layer(concat)        return output# model = WideDeepModel()model = keras.models.Sequential([    WideDeepModel(),])model.build(input_shape=(None, 8))        model.summary()model.compile(loss="mean_squared_error",              optimizer = keras.optimizers.SGD(0.001))callbacks = [keras.callbacks.EarlyStopping(    patience=5, min_delta=1e-2)]

2，总结代码如下

#!/usr/bin/env python3# -*- coding: utf-8 -*-import matplotlib as mplimport matplotlib.pyplot as pltimport numpy as npimport sklearnimport pandas as pdimport osimport sysimport timeimport tensorflow as tffrom tensorflow import keras# 1,打印使用的python库的版本信息print(tf.__version__)print(sys.version_info)for module in mpl, np, pd, sklearn, tf, keras:    print(module.__name__, module.__version__)    # 2,下载并使用sklearn中的“fetch_california_housing”数据集from sklearn.datasets import fetch_california_housinghousing = fetch_california_housing()print(housing.DESCR)print(housing.data.shape)print(housing.target.shape)# 3,拆分数据集中的数据为 训练数据、验证数据、测试数据from sklearn.model_selection import train_test_splitx_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)# 4,在将数据带入到模型之前，先进行预处理-训练、验证、测试数据标准化from sklearn.preprocessing import StandardScalerscaler = StandardScaler()x_train_scaled = scaler.fit_transform(x_train)x_valid_scaled = scaler.transform(x_valid)x_test_scaled = scaler.transform(x_test)# 5,构建wide_deep 子类API 回归模型、模型层级图、编译模型（添加损失函数、优化器）、添加回调函数# 子类APIclass WideDeepModel(keras.models.Model):    def __init__(self):        super(WideDeepModel, self).__init__()        """定义模型的层次"""        self.hidden1_layer = keras.layers.Dense(30, activation='relu')        self.hidden2_layer = keras.layers.Dense(30, activation='relu')        self.output_layer = keras.layers.Dense(1)        def call(self, input):        """完成模型的正向计算"""        hidden1 = self.hidden1_layer(input)        hidden2 = self.hidden2_layer(hidden1)        concat = keras.layers.concatenate([input, hidden2])        output = self.output_layer(concat)        return output# model = WideDeepModel()model = keras.models.Sequential([    WideDeepModel(),])model.build(input_shape=(None, 8))        model.summary()model.compile(loss="mean_squared_error",              optimizer = keras.optimizers.SGD(0.002))callbacks = [keras.callbacks.EarlyStopping(    patience=5, min_delta=1e-4)]# 6,训练构建的模型history = model.fit(x_train_scaled, y_train,                    validation_data = (x_valid_scaled, y_valid),                    epochs = 200,                    callbacks = callbacks)# 7,得到训练曲线图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)# 8,调用估计器model.evaluate(x_test_scaled, y_test, verbose=0)

四，wide&deep模型的多输入

1，实现多输入的代码如下

# 5,构建wide_deep 子类API 回归模型、模型层级图、编译模型（添加损失函数、优化器）、添加回调函数# 多输入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)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-3)]model.summary()# 6,训练构建的模型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 = [x_train_scaled_wide, x_train_scaled_deep],                    y = y_train,                    validation_data = (                        [x_valid_scaled_wide, x_valid_scaled_deep],                        y_valid),                    epochs = 100,                    callbacks = callbacks)

2，总结代码如下

#!/usr/bin/env python3# -*- coding: utf-8 -*-import matplotlib as mplimport matplotlib.pyplot as pltimport numpy as npimport sklearnimport pandas as pdimport osimport sysimport timeimport tensorflow as tffrom tensorflow import keras# 1,打印使用的python库的版本信息print(tf.__version__)print(sys.version_info)for module in mpl, np, pd, sklearn, tf, keras:    print(module.__name__, module.__version__)    # 2,下载并使用sklearn中的“fetch_california_housing”数据集from sklearn.datasets import fetch_california_housinghousing = fetch_california_housing()print(housing.DESCR)print(housing.data.shape)print(housing.target.shape)# 3,拆分数据集中的数据为 训练数据、验证数据、测试数据from sklearn.model_selection import train_test_splitx_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)# 4,在将数据带入到模型之前，先进行预处理-训练、验证、测试数据标准化from sklearn.preprocessing import StandardScalerscaler = StandardScaler()x_train_scaled = scaler.fit_transform(x_train)x_valid_scaled = scaler.transform(x_valid)x_test_scaled = scaler.transform(x_test)# 5,构建wide_deep 子类API 回归模型、模型层级图、编译模型（添加损失函数、优化器）、添加回调函数# 多输入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)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-3)]model.summary()# 6,训练构建的模型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 = [x_train_scaled_wide, x_train_scaled_deep],                    y = y_train,                    validation_data = (                        [x_valid_scaled_wide, x_valid_scaled_deep],                        y_valid),                    epochs = 100,                    callbacks = callbacks)# 7,得到训练曲线图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)# 8,调用估计器print(model.evaluate([x_test_scaled_wide, x_test_scaled_deep], y_test, verbose=0))

五，wide&deep模型的多输出

1，实现多输出的代码如下

# 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])

2，总结代码如下

#!/usr/bin/env python3# -*- coding: utf-8 -*-import matplotlib as mplimport matplotlib.pyplot as pltimport numpy as npimport sklearnimport pandas as pdimport osimport sysimport timeimport tensorflow as tffrom tensorflow import keras# 1,打印使用的python库的版本信息print(tf.__version__)print(sys.version_info)for module in mpl, np, pd, sklearn, tf, keras:    print(module.__name__, module.__version__)    # 2,下载并使用sklearn中的“fetch_california_housing”数据集from sklearn.datasets import fetch_california_housinghousing = fetch_california_housing()print(housing.DESCR)print(housing.data.shape)print(housing.target.shape)# 3,拆分数据集中的数据为 训练数据、验证数据、测试数据from sklearn.model_selection import train_test_splitx_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)# 4,在将数据带入到模型之前，先进行预处理-训练、验证、测试数据标准化from sklearn.preprocessing import StandardScalerscaler = StandardScaler()x_train_scaled = scaler.fit_transform(x_train)x_valid_scaled = scaler.transform(x_valid)x_test_scaled = scaler.transform(x_test)# 5,构建wide_deep 子类API 回归模型、模型层级图、编译模型（添加损失函数、优化器）、添加回调函数# 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()# 6,训练构建的模型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)# 7,得到训练曲线图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)# 8,调用估计器print(model.evaluate([x_test_scaled_wide, x_test_scaled_deep],               [y_test, y_test], verbose=0))

转载地址：http://rpili.baihongyu.com/