You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Thanks for your great job!
I encountered the error:
segmentation fault (core dumped)
while training the tiny model in two stages. This error ofen happened during my training. Do you know what caused this error? And how can I solve it?
Moreover, I am training by single GPU, so I decline the lr to 1e-5.
Looking forward to your early reply! Thanks again.
The text was updated successfully, but these errors were encountered:
Can you try to downgrade your numpy? I had same issue with numpy and other library compatibility. I have 1.19.5 now and it works for my experiments. This might not be the solution, but is worth a try.
Can you try to downgrade your numpy? I had same issue with numpy and other library compatibility. I have 1.19.5 now and it works for my experiments. This might not be the solution, but is worth a try.
Thanks for your advice! But my numpy version is already 1.19.5, the error still occurs frequently.
Thanks for your great job!
I encountered the error:
while training the tiny model in two stages. This error ofen happened during my training. Do you know what caused this error? And how can I solve it?
Moreover, I am training by single GPU, so I decline the lr to 1e-5.
Looking forward to your early reply! Thanks again.
The text was updated successfully, but these errors were encountered: