-
Notifications
You must be signed in to change notification settings - Fork 97
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Performance on GPUs #3
Comments
I found that the problem can be solved by changing the optimizer from Adamoptimizer to Momentum optimizer. |
Hi @LaceyChen17 , Thank you for your comments, actually I have a PC with only one GPU "NVIDIA Geforce 720M", so I was not able to try the code with multiple GPUs. About the convergence I just tried to run the code with a few number of epochs "as my GPU device is old and its capabilities are limited", but you are right I realized that using the Momentum optimizer can solve that issue. Thank you very much |
Hi @LaceyChen17 @mhjabreel I changed the optimizer from Adamoptimizer to Momentum optimizer. Finally,I run the python training.py for about 3000 steps. Could you tell me more details of the way to deal with that? |
@LaceyChen17 |
@renzhe0009 You are welcome ^_^ |
only after 33000 steps (~2days) did I see the validation accuracy climb from ~30% to ~70% and eventually 88% eventually. |
simply change the base rate to 1e-3 and use adam, you will see accuracy climb to 80% in less than 1000 steps |
I just tried changing the base rate and kept Adam Optimizer, but I didn't get best results, my neural network couldn't pass 30% of accuracy in test data.
|
Hi,
I am trying to run CharCNN on 4 GeForce GTX 1080.I am struggling with 2 problems.
nvidia-smi
,the result is shown as followingwhat can I do to make full use of all GPUs?
python training.py
without any change to your code.The current status is shown as following:Do I have to change some parameters or the type of optimizer? Have you ever tried to run CharCNN with better performance?
Thank you very much!
The text was updated successfully, but these errors were encountered: