-
Notifications
You must be signed in to change notification settings - Fork 36
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
About running the code #1
Comments
i used NVIDIA gtx 1050ti but this code(Atari one) is not memory efficient , memory overflows during training. I used 32 gb ram . For memory efficiency, you can look at |
OK! Thank you very much!
| |
阎钰天
|
|
邮箱:yytmail123@163.com
|
签名由 网易邮箱大师 定制
On 05/04/2020 17:32, Abhishek Suran wrote:
i used NVIDIA gtx 1050ti but this code(Atari one) is not memory efficient , memory overflows during training. I used 32 gb ram . For memory efficiency, you can look at
https://github.com/Huixxi/TensorFlow2.0-for-Deep-Reinforcement-Learning/blob/master/00_atari_dqn.py
—
You are receiving this because you authored the thread.
Reply to this email directly, view it on GitHub, or unsubscribe.
|
or you can use 32 gb ram :p . It looks like tf 2 is eager by default thats why it need custom model and training atleast thats what i think . I also posted the question stackoverflow but no reply :p , u can look ques at https://stackoverflow.com/questions/58270765/how-to-minimize-ram-usage-for-training-atari-deep-q-learning-model |
OK! Thank you for your help!
| |
阎钰天
|
|
邮箱:yytmail123@163.com
|
签名由 网易邮箱大师 定制
On 05/04/2020 17:42, Abhishek Suran wrote:
or you can use 32 gb ram :p . It looks like tf 2 is eager by default thats why it need custom model and training atleast thats what i think . I also posted the question stackoverflow but no reply :p , u can look ques at https://stackoverflow.com/questions/58270765/how-to-minimize-ram-usage-for-training-atari-deep-q-learning-model
—
You are receiving this because you authored the thread.
Reply to this email directly, view it on GitHub, or unsubscribe.
|
Hello! I wonder what gpu do you use to train the dqn on? How many of them?
Have you successfully trained the network? If so, could you tell me how long does it take and how is the result?
Thank you very much!!
The text was updated successfully, but these errors were encountered: