How to use double precision in deep learning toolbox?

Question

Rohan Mahala 2023-11-12

1
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/2046145-how-to-use-double-precision-in-deep-learning-toolbox

评论： Rohan Mahala 2023-12-26

It seems like deep learning toolbox has defalut set single precision. I want double precision in my neural network, how to achieve this? Please Help!

2 个评论
显示无隐藏无

Matt J 2023-11-12

Are you saying you want to train in double precision, or just do inference in double precision?

Rohan Mahala 2023-11-13

Both actually, train as well as inference in double precision.

请先登录，再进行评论。

请先登录，再回答此问题。

Answer 1

Angelo Yeo 2023-11-14

0
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/2046145-how-to-use-double-precision-in-deep-learning-toolbox#answer_1352047

在 MATLAB Online 中打开

I understand that you want to use trainNetwork and trainnet to train and predict in double precision This is currently not possible in MATLAB R2023b. Internally, 'trainnet' defaults to single precision and hence cannot be used in this case. This functionality is something the developers are actively working on for a future release.

A workaround is to use a custom training loop. You can refer the following example for a general reference -

https://www.mathworks.com/help/deeplearning/ug/train-network-using-custom-training-loop.html

1. Once the learnable network parameters are initialized, they must be converted to type double by using 'dlupdate'

net = dlupdate(@double, net);

2. Ensure data is double precision. This can be set using the 'OutputCast' of 'minibatchqueue' to 'double'. Note that this parameter is read-only. It cannot be modified after construction of 'minibatchqueue'.

Please also note that it is not possible to train in double precision if you are using DAGNetwork or SeriesNetwork.

1 个评论
显示 -1更早的评论隐藏 -1更早的评论

Rohan Mahala 2023-12-26

I am not using 'trainnet', instead I am using acclerated custom training loop.

For reference :- https://in.mathworks.com/help/deeplearning/ug/solve-partial-differential-equations-using-deep-learning.html

I did the OutputCast of 'minibatchqueue' to 'double' and now I am getting the predictions in double cast, However i am not able to achieve the desired accuracy.

Can you please suggest me some other pointers to keep in mind so that the training happens correctly in 'double' precision mode only.

请先登录，再进行评论。