TensorFlow 2.x入门与实战：Keras API与Eager Execution

TensorFlow 2.x入门与实战

TensorFlow 2.x是Google开源的机器学习平台。

Keras API

序贯模型

import tensorflow as tf
from tensorflow import keras
from tensorflow.keras import layers

model = keras.Sequential([
    layers.Dense(128, activation='relu'),
    layers.Dense(10)
])

model.compile(optimizer='adam', loss='sparse_categorical_crossentropy')
model.fit(x_train, y_train, epochs=5)
​

Eager Execution

即时执行

x = tf.constant([[1.0]])
y = x * 2
print(y)
​

自动求导

with tf.GradientTape() as tape:
    y = x * x
    dy_dx = tape.gradient(y, x)
​

AutoML

超参数搜索

import keras_tuner as kt

def build_model(hp):
    model = keras.Sequential()
    model.add(layers.Dense(units=hp.Int('units', 32, 512, 32)))
    return model

tuner = kt.RandomSearch(build_model, max_trials=5)
tuner.search(x_train, y_train)
​

TensorFlow 2.x简化了机器学习开发。