Double precision in deep learning

9 次查看（过去 30 天）

bah 2022-11-28

1
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/1865748-double-precision-in-deep-learning

评论： Walter Roberson 2023-11-12

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 个评论
显示 3更早的评论隐藏 3更早的评论

bah 2022-11-29

Thanks a lot for the information.

Walter Roberson 2023-11-12

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.

请先登录，再进行评论。

请先登录，再回答此问题。

采纳的回答

Joss Knight 2022-12-18

0
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/1865748-double-precision-in-deep-learning#answer_1130607

在 MATLAB Online 中打开

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 个评论
显示无隐藏无

Rohan Mahala 2023-11-12

Hi Joss, can you please tell how to do this without a dlnetwork

Joss Knight 2023-11-12

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.

请先登录，再进行评论。