Double precision in deep learning
조회 수: 10 (최근 30일)
이전 댓글 표시
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.
댓글 수: 5
Walter Roberson
2023년 11월 12일
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.
채택된 답변
Joss Knight
2022년 12월 18일
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.
댓글 수: 2
Joss Knight
2023년 11월 12일
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.
추가 답변 (0개)
참고 항목
카테고리
Help Center 및 File Exchange에서 Parallel and Cloud에 대해 자세히 알아보기
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!