In many tensorflow tutorials (example) "towers" are mentioned without a definition. What is meant by that?


According to tensorflow documentation about CNN,

The first abstraction we require is a function for computing inference and gradients for a single model replica. In the code we term this abstraction a "tower".

To get the relevant context and more, check this.

  • 1
    $\begingroup$ The linked page does not mention "tower" anymore :/ $\endgroup$
    – aviator
    Apr 7 '20 at 15:17
  • $\begingroup$ To keep it simple, a "Tower" is a copy of your model. In a multi-GPU case, if you have 8 GPUs, then you will get 8 Towers. $\endgroup$
    – Begoodpy
    Jul 26 '20 at 13:13

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

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