回归问题的wide and deep模型--函数式API和子类PI、多输入和多输出

对于图像分类中，由于图像价值都是一样的，所以对图像进行wide&deep模型分类没有太大的意义。
由于wide&deep模型不是严格意义上的层级结构，而是由两部分组成，所以就不能用sequential，用函数式API。像使用函数一样调用层次。
下面修改模型那块代码

# 函数式API 功能API
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))
#将深层网络和wide网络拼接起来
concat = keras.layers.concatenate([input, hidden2])
output = keras.layers.Dense(1)(concat)
#下面把model固化下来
model = keras.models.Model(inputs = [input],
                           outputs = [output])

model.summary()
lr = 1e-4
optimizer = keras.optimizers.SGD(lr)
model.compile(loss="mean_squared_error", optimizer=optimizer)
callbacks = [keras.callbacks.EarlyStopping(
    patience=5, min_delta=1e-2)]

history = model.fit(x_train_scaled, y_train,
                    validation_data = (x_valid_scaled, y_valid),
                    epochs = 10,
                    callbacks = callbacks)

下面用子类（subclass）API实现同样功能
同样，我只改写模型部分：

# 子类API 定义一个类，它的父类是keras.models.Model
class WideDeepModel(keras.models.Model):
    def __init__(self):
    #承载初始化函数
    #调用父类初始化函数
        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()
lr = 1e-4
optimizer = keras.optimizers.SGD(lr)
model.compile(loss="mean_squared_error", optimizer=optimizer)
callbacks = [keras.callbacks.EarlyStopping(
    patience=5, min_delta=1e-2)]

history = model.fit(x_train_scaled, y_train,
                    validation_data = (x_valid_scaled, y_valid),
                    epochs = 10,
                    callbacks = callbacks)

我们继续修改模型。进行多输入模型分析

# 多输入，前五个给wide，后6个给deep，二者还有交集
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])

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)

多输出

# 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])

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)
model.evaluate([x_test_scaled_wide, x_test_scaled_deep],
               [y_test, y_test])