Why peepholeLSTMLayer implemented in a tutorial is much slower than built-in lstmlayer?
3 Ansichten (letzte 30 Tage)
Ältere Kommentare anzeigen
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 Kommentare
Antworten (1)
Hiro Yoshino
am 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.
1 Kommentar
Siehe auch
Kategorien
Mehr zu Image Data Workflows finden Sie in Help Center und File Exchange
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!