Keras函数式 API

Keras 函数式 API 是定义复杂模型（如多输出模型、有向无环图，或具有共享层的模型）的方法。

• 非函数式api

import tensorflow as tf
import numpy as np
from tensorflow import keras
from tensorflow.keras import Sequential
from tensorflow.keras.layers import Dense

model = Sequential()
model.add(Dense(units=1, input_shape=[1]))

model.compile(optimizer='sgd', loss='mean_squared_error')

xs = np.array([1.0, 2.0, 3.0, 4.0, 5.0, 6.0], dtype=float)
ys = np.array([1.0, 1.5, 2.0, 2.5, 3.0, 3.5], dtype=float)

model.fit(xs, ys, epochs=1000)

print(model.predict([7.0]))

• 函数式api

import tensorflow as tf
import numpy as np
from tensorflow import keras
from tensorflow.keras.models import Model 
from tensorflow.keras.layers import Dense, Input

house = Input(shape=[1])
price = Dense(1)(house)
model = Model(inputs=house, outputs=price)

model.compile(loss='mse', optimizer='sgd')
xs = np.array([1.0, 2.0, 3.0, 4.0, 5.0, 6.0], dtype=float)
ys = np.array([1.0, 1.5, 2.0, 2.5, 3.0, 3.5], dtype=float)

model.fit(xs, ys, epochs=1000)

print(model.predict([7.0]))

【参考资料】
函数式 API 指引