简体繁体 English

tensorflow.keras.layers 和 keras.layers 有什么区别？

[英]What is the difference between tensorflow.keras.layers and keras.layers?

原文 2020-11-10 14:13:42 8 1 python/ tensorflow/ keras/ deep-learning

I have read a related question's answer about this on stackoverflow which explains the difference between tensorflow.keras.layers and tensorflow.layers , link:我在 stackoverflow 上阅读了一个相关问题的答案，它解释了tensorflow.keras.layers和tensorflow.layers之间的区别，链接：

What is the difference between tf.keras.layers versus tf.layers? tf.keras.layers 与 tf.layers 有什么区别？

But, it doesn't answer the difference between tensorflow.keras.layers and keras.layers , whereas I noticed I can import them also.但是，它没有回答tensorflow.keras.layers和keras.layers之间的区别，而我注意到我也可以导入它们。

So, what is the difference between them?那么，它们之间有什么区别呢？

1 个解决方案

Keras used to be able to support different backends (tensorflow, theano and CNTK). Keras 曾经能够支持不同的后端（tensorflow、theano 和 CNTK）。 Since keras 2.3, there is no difference between keras and tf.keras .从 keras 2.3 开始， keras和tf.keras之间没有区别。

An excerpt from the Readme of the keras repository on github : github 上 keras 存储库自述文件的摘录：

Multi-backend Keras and tf.keras多后端 Keras 和 tf.keras

Multi-backend Keras has been discontinued.多后端 Keras 已停产。 At this time, we recommend that Keras users who use multi-backend Keras with the TensorFlow backend switch to tf.keras in TensorFlow 2.0.此时，我们建议使用多后端 Keras 和 TensorFlow 后端的 Keras 用户切换到 TensorFlow 2.0 中的 tf.keras。

Keras 2.2.5 was the last release of Keras implementing the 2.2.* API. Keras 2.2.5 是实现 2.2.* API 的最后一个 Keras 版本。 It was the last release to only support TensorFlow 1 (as well as Theano and CNTK).这是最后一个仅支持 TensorFlow 1（以及 Theano 和 CNTK）的版本。

The current release is Keras 2.4.0, which simply redirects to tf.keras.当前版本是 Keras 2.4.0，它只是重定向到 tf.keras。