Double precision in deep learning
4 ビュー (過去 30 日間)
古いコメントを表示
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 件のコメント
Walter Roberson
2023 年 11 月 12 日
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.
採用された回答
Joss Knight
2022 年 12 月 18 日
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 件のコメント
Joss Knight
2023 年 11 月 12 日
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.
その他の回答 (0 件)
参考
カテゴリ
Help Center および File Exchange で Parallel and Cloud についてさらに検索
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!