Skip to content
This repository was archived by the owner on Sep 25, 2024. It is now read-only.

Latest commit

 

History

History

Folders and files

NameName
Last commit message
Last commit date

parent directory

..
 
 

README.md

Lab 11


RNNs

Check:


Optimizing PyTorch pipelines

"Another benefit of striving for efficiency is that the process forces you to understand the problem in more depth. At the same time, this increased depth of understanding leads to more efficient implementations." - Alexander Stepanov, Three Algorithmic Journeys


Caution: Spending 5 hours to optimize a single pipeline that runs for only 1 hour is a waste of time.

Goals:

  • Optimize by default. Write a training and inference pipeline that is reasonably fast, from the beginning.
  • Do not do premature optimization.
  • Find a balance between accuracy and performance, depending on your problem.
  • Find a balance between the time spent for optimizing and the time spent for doing experiments.

Resources: