我应该在2020年使用tf.keras还是keras?
A while back I read this post on PyImageSearch and was satisfied enough to switch completely to tf.keras.
但是从那以后，我注意到 Keras网站进行了全面检查，并且似乎正在扩大其雄心.
But since then I noticed the Keras website got an overhaul and seems to be expanding on its ambitions.
所以我有点困惑.
- Is it still true that "the latest release of the keras package (v2.3.0) will be the last release to support multiple backends and feature updates. Moving forward, the keras package will receive only bug fixes." from PyImageSearch?
- If I stick with
tf.kerascould I miss out on anything? I'm talking about specific features (to make this a "fact based" question)
似乎在Datascience Stack Exchange网站上的答案回答这个问题.
An answer on the Datascience Stack Exchange site seems to answer this question.
Keras的创建者FrançoisChollet建议用户切换到tf.keras(源)
François Chollet, the creator of Keras, recommends that users switch to tf.keras (source)
多后端Keras的新版本:2.3.0
New release of multi-backend Keras: 2.3.0
https://github.com/keras-team/keras/releases/tag/2.3.0
https://github.com/keras-team/keras/releases/tag/2.3.0
- 首个全面支持TF 2的多后端Keras版本
- 继续支持Theano/CNTK
- 将成为多后端Keras的最后一个主要版本
我们建议您将Keras代码切换为tf.keras.
We recommend you switch your Keras code to tf.keras.
并有两个回复:
Theano和CNTK都在开发中.同时，作为Keras后端，它们仅占Keras使用量的不到4％.其余96％的用户(其中一半以上已经在tf.keras上)使用tf.keras可以更好地服务.
Both Theano and CNTK are out of development. Meanwhile, as Keras backends they represent less than 4% of Keras usage. The other 96% of users (of which more than half are already on tf.keras) are better served with tf.keras.
Keras的开发将重点放在tf.keras上.
Keras development will focus on tf.keras going forward.
重要的是，我们将寻求在keras-team/keras的独立GitHub存储库中开始开发tf.keras，以使第三方成员更容易地做出贡献.
Importantly, we will seek to start developing tf.keras in its own standalone GitHub repository at keras-team/keras in order to make it much easier for 3rd party folks to contribute.
Keras的移动速度从未比现在快:)
Keras has never been moving faster than now :)