Why peepholeLSTMLayer implemented in a tutorial is much slower than built-in lstmlayer?
1 view (last 30 days)
Show older comments
Why this implementation of peepholeLSTMLayer https://au.mathworks.com/help/deeplearning/ug/define-custom-recurrent-deep-learning-layer.html is much slower than built-in lstmlayer?
What can be done to speed it up? For example, can it be compiled into a binary code?
0 Comments
Answers (1)
Hiro Yoshino
on 31 Aug 2023
I suppose that is because the implementation of interest is a custom model while the built-in LSTM is optimized for computation.
MATLAB has kept improving its performance over the years (see this). So I guess this is also the case with the buil-in capabilities in MATLAB.
Hope these help you.
See Also
Categories
Find more on Image Data Workflows in Help Center and File Exchange
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!