Double precision in deep learning
10 Ansichten (letzte 30 Tage)
Ältere Kommentare anzeigen
bah
am 28 Nov. 2022
Kommentiert: Walter Roberson
am 12 Nov. 2023
Hello guys,
i want to train my LSTM using double precision but the deep learning toolbox only allows single precision. Can i change that to double precision or how do i train my neural network using double precision ?
Thanks.
5 Kommentare
Walter Roberson
am 12 Nov. 2023
A lot of Nvidia models have double precision at 1/32 of single precision rates. Some improve to 1/24. And a few uncommon models more intended for server improve to 1/8: you have to examine the models carefully to determine the best for your purposes.
Akzeptierte Antwort
Joss Knight
am 18 Dez. 2022
This is possible with a dlnetwork but it is (currently) more of a workaround than anything else. Once your dlnetwork is ready to go, convert it to double precision:
net = dlupdate(@double, net);
net.State = dlupdate(@double, net.State);
Then make sure your input data to the network is always in double precision. Everything should then remain in double as you train and use the network.
Let me know if this doesn't work for you.
2 Kommentare
Joss Knight
am 12 Nov. 2023
To do this without a dlnetwork you will need to implement your network in functional form. Either way, to train it will require use of automatic differentiation and a custom training loop.
Weitere Antworten (0)
Siehe auch
Kategorien
Mehr zu Parallel and Cloud finden Sie in Help Center und File Exchange
Produkte
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!