deep learning toolbox: how to change precision to double?

9 ビュー (過去 30 日間)
John Smith
John Smith 2020 年 1 月 20 日
コメント済み: John Smith 2020 年 1 月 20 日
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

回答 (1 件)

Bhaskar R
Bhaskar R 2020 年 1 月 20 日
MATLAB is by default double precision floating point(double) i.e. 64-bit.
This answer can help you
  1 件のコメント
John Smith
John Smith 2020 年 1 月 20 日
Yes, but DLT is not. In the code there're hardcoded casts to single precision.

サインインしてコメントする。

カテゴリ

Find more on Deep Learning with Time Series and Sequence Data in Help Center and File Exchange

製品


リリース

R2019b

Community Treasure Hunt

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

Start Hunting!

Translated by