deeplearning Matlab is not compatible with graphics card

1 view (last 30 days)
i use parallel.gpu.enableCUDAForwardCompatiblity function. but i found when network input size is 1*400*1,train samples number is 16800.batchsize even 1000,i can train,and get a good result.but the other network,input is 1*60*1,when batchsize maybe over 256,than network be very wrose.acc is 1/(number of class).ie i have 4 clsass,then is 25%.batchsize lower 256,nertwork works very well. when input is 50*64*1,then any batchsize is wrose.
my matlab is 2020b.graphics card is 3090.
  2 Comments
Rik
Rik on 7 Jan 2021
It is not clear to me what exactly is you question. Have a read here and here. It will greatly improve your chances of getting an answer.
Also, given the current availability (or rather the lack thereof) of the RTX 3090 I doubt many people will be able to replicate specific hardware-related issues.
bob james
bob james on 7 Jan 2021
the question maybe :the same network,same train data,the same model parameters,i use cpu can get very good results.buy when using gpu, the results was very wrose.

Sign in to comment.

Answers (1)

Joss Knight
Joss Knight on 10 Jan 2021
As explained in the documentation, both for CUDA support and for the enableForwardCompatibility function, "Enabling forward compatibility can result in wrong answers and unexpected behavior during GPU computations".

Categories

Find more on Get Started with GPU Coder in Help Center and File Exchange

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!