Should I migrate to TensorFlow 2.0?
I heard about new version of TensorFlow and that it is more simple, like 'keras'. But does it lose it terms of performance and flexibility to tf1? If not, are there any benefits to tf1 right now?
Answers
First of all, you should know tf1 will not be further developed. All the development is now going on in tf2. Secondly, no, tf2 is in no way worse than tf1 in terms of performance or flexibility. Moreover, you can easily migrate your tf1 code to tf2. Any code. All you need is 'disablev2behavior()' function to use namespace names from tf1. There are practically no benefits in staying on tf1 code.
Where can I read about differences in tf2?
If you want to find out about benefits and main differences of tf2 check this article: https://towardsdatascience.com/everything-you-need-to-know-about-tensorflow-2-0-b0856960c074
What are the benefits of using tf.keras over the vanilla Keras package?
You can easily use pure Tensorflow features where needed. Also, tf 2.0 is supported by Google, which is a large and reliable organization. You can expect that bugs and issues will be faster eliminated in Tensorflow 2.0.
Are there some other good packages for neural networks building worth learning?
Yes, try to learn PyTorch from Facebook. It is developing extremely fast and at the moment PyTorch is the main competitor of Tensorflow and Keras.
Thanks a lot.
Are you shure you want to close this post?
Are you shure you want to pin this post?
Report comment
Thank you for reporting this comment, the Imaginghub Community Management will verify your request.
Log in with Google