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
In infer_vos.py, Line 211 and 237, I've got the TypeError: forward() missing 1 required positional argument: 'frames' , after I change them as keyward arguments (frames=frames[:1]), the error solved. Is it a bug or something related to my environment? I haven't found the reason yet since the frames is not a keyward arguments in framework.py
By the way, does your evaluation script support Multi-GPU inference? It seems that inference on YouTube-VOS will take a very long time ?
Best,
The text was updated successfully, but these errors were encountered:
Hi and sorry for a very late reply.
Did you make any changes to the original code prior to getting this error? Otherwise it's hard say.
Regarding the YouTube-VOS evaluation -- it is indeed quite time consuming. Currently implementation is only single GPU, but could be potentially extended. You'd only need to be careful with i/o throughput, especially if you're saving visualisations.
In
infer_vos.py
, Line 211 and 237, I've got theTypeError: forward() missing 1 required positional argument: 'frames'
, after I change them as keyward arguments (frames=frames[:1]), the error solved. Is it a bug or something related to my environment? I haven't found the reason yet since the frames is not a keyward arguments inframework.py
By the way, does your evaluation script support Multi-GPU inference? It seems that inference on YouTube-VOS will take a very long time ?
Best,
The text was updated successfully, but these errors were encountered: