I am trying to train a roboflow model and i keep on getting this issue
“This training job did not complete successfully. This can happen for a few reasons but often means that the chosen model dimension (which corresponds to image size) was too large to fit into GPU memory.”
i have already trained 4 successful models which were all much larger than this and they worked perfectly but when i am training this one it keeps on having the same issue i tried over 5 times constantly reducing the number of images and the size but still the same issue please help
Hi there! I see you have successfully trained several models since this post. Have you been able to resolve this issue?
hey lake
yeah i was going through my data and there was one image which was causing the issue i deleted it and it worked fine after that, however i am not sure why that one image was causing the issue so maybe if you could help me identify that which would help for future models
Sure, we’d be happy to take a look. Can you post a link to the image, or email it to support@roboflow.com if you’d prefer to keep it private.
1 Like
