-
Notifications
You must be signed in to change notification settings - Fork 3.1k
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
training time is soo much #2066
Comments
i recommend this advice |
how about other thing??other thing can help to train faster? |
i set epoch on 100 and batch size on 30 but still not finish after 6 hours (every epoch take over 3 min ) |
the length of the audio is also linked to training time. more is better, but the recommended amount for a "decent" model is around 10 minutes. also, 6 hours isn't that long for training a machine learning model, could be alot longer |
make sure you are using your gpu not cpu. if you have done so then try the advices by @twl-surrogate mentioned above. |
how can do that? |
and what is this means "NO GPU DETECTED: falling back to CPU - this may take a while" ??? |
Install the CUDA toolkit from Nvidia. |
|
This is geforce experience not cuda toolkit. Install the cuda toolkit (see my last comment). |
I DOWNLOAD IT FROM THAT LINK U REPLY FOR ME... |
Please refer to this guide for detailed steps (for RTX30 series which yours is) |
hey everyone
.
my graphic card is rtx 3070 ti .
but when i want to train file with oneclick training...its take to much time (over 3h)...
can somebody tell me best setting for train ...and how get faster result...
The text was updated successfully, but these errors were encountered: