tf.keras指南翻译——Overview

Import tf.keras

tf.keras is TensorFlow's implementation of the Keras API specification. This is a high-level API to build and train models that includes first-class support for TensorFlow-specific functionality, such as eager execution, tf.data pipelines, and Estimators. tf.keras makes TensorFlow easier to use without sacrificing flexibility and performance.

为了能够更好地应用TensorFlow中各种功能——如eager execution、tf.data管道和Estimators——构建、训练模型，TensorFlow根据Keras API的说明对其进行了封装和实现，将其命名为tf.keras。tf.keras是keras更高级的API封装，这使得TensorFlow在兼顾灵活性和高效性的同时，操作起来更加简单。

To get started, import tf.keras as part of your TensorFlow program setup:

from __future__ import absolute_import, division, print_function, unicode_literals
#Python3.X可以不用输入上面这句
import tensorflow as tf
from tensorflow import keras

tf.keras can run any Ker