deep learning toolbox: how to change precision to double?

3 visualizzazioni (ultimi 30 giorni)
John Smith
John Smith il 20 Gen 2020
Commentato: John Smith il 20 Gen 2020
Hello,
It seems that the Deep Learning Toolbox uses the single precision and that it's hard coded.
Is there a way to change the precision to doube?
Thx,
D

Accedi per rispondere a questa domanda.

Risposte (1)

Bhaskar R
Bhaskar R il 20 Gen 2020
MATLAB is by default double precision floating point(double) i.e. 64-bit.
This answer can help you
  1 Commento
John Smith
John Smith il 20 Gen 2020
Yes, but DLT is not. In the code there're hardcoded casts to single precision.

Accedi per commentare.

Categorie

Scopri di più su Deep Learning Toolbox in Help Center e File Exchange

Tag

Prodotti


Release

R2019b

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by