tf.keras.layers和tf.layers有什么区别? [英] What is the difference between tf.keras.layers versus tf.layers?

问题描述

tf.keras.layers与tf.layers有什么区别?
例如.他们两个都有Conv2d，它们提供不同的输出吗?
如果将它们混合使用(在一个隐藏层中像tf.keras.layers.Conv2d，在下一个隐藏层tf.layers.max_pooling2d之类的东西)会有好处吗?

What is the difference between tf.keras.layers versus tf.layers?
E.g. both of them have Conv2d, do they provide different outputs?
Is there any benefits if you mix them (something like a tf.keras.layers.Conv2d in one hidden layer and in the next, tf.layers.max_pooling2d)?

推荐答案

从TensorFlow 1.12开始，tf.layers只是围绕tf.keras.layers的包装.

Since TensorFlow 1.12, tf.layers are merely wrappers around tf.keras.layers.

一些例子:

卷积tf.layers只是从卷积tf.keras.layers继承而来，请参见源代码

Convolutional tf.layers just inherit from the convolutional tf.keras.layers, see source code here:

@tf_export('layers.Conv2D')
class Conv2D(keras_layers.Conv2D, base.Layer):

对于所有核心tf.layers ，例如:

The same is true for all core tf.layers, e.g.:

@tf_export('layers.Dense')
class Dense(keras_layers.Dense, base.Layer):

通过将Keras集成到TensorFlow中，维护几种不同的层实现几乎没有意义. tf.keras正在成为TensorFlow的实际高级API，因此tf.layers现在只是tf.keras.layers的包装.

With the integration of Keras into TensorFlow, it would make little sense to maintain several different layer implementations. tf.keras is becoming the de-facto high-level API for TensorFlow, therefore tf.layers are now just wrappers around tf.keras.layers.

这篇关于tf.keras.layers和tf.layers有什么区别?的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！