I do not really understand the difference between Keras backend (when you use tensorflow as backend) and tensorflow. I saw some posts where people were trying to modify a Keras loss function and to do so, they were using keras.backend functions.

Is it possible to use directly functions from tensorflow ? Because on tensorflow, there are many more function available than on keras.backend.


closed as off-topic by Sycorax, Firebug, Ferdi, kjetil b halvorsen, Jan Kukacka Sep 27 '18 at 7:42

This question appears to be off-topic. The users who voted to close gave this specific reason:

  • "This question appears to be off-topic because EITHER it is not about statistics, machine learning, data analysis, data mining, or data visualization, OR it focuses on programming, debugging, or performing routine operations within a statistical computing platform. If the latter, you could try the support links we maintain." – Sycorax, Firebug, Ferdi, kjetil b halvorsen, Jan Kukacka
If this question can be reworded to fit the rules in the help center, please edit the question.


Simply put, Keras is easier to use. See this post on Medium: TensorFlow or Keras? Which one should I learn?.

Simplicity comes at the cost of flexibility, but allows faster implementation for prototyping.


Not the answer you're looking for? Browse other questions tagged or ask your own question.