Liwei Peng

@NielsRogge, @addf400 I used the same way in NielsRogge's notebook to use BEiT Model inference. I ran his notebook code multiple times, each time with a different bool_masked_pos. Among the...

> @LiweiPeng @NielsRogge @addf400 Have any of you been able to figure this out? I am getting similar results, the predictions for the masked areas are wrong and as a...

Sorry I am not clear in my previous post. In my case, I am using linear probing for final class prediction. And linear probing result is not good compared to...

where to set these env variables? When I set them on the console like below. the output still has colors export ANSIBLE_NOCOLOR=1 export NO_COLOR=1 sb run -f local.ini -c debug/run1.yaml...

fixed with latest PR.

will use one by setting the config file

For Tesla K80 GPU, after I manually created nvidia-uvm, NVIDIA GPU is detected and used. executor.py failed because the GPU type is not supported. Again, 'sb' script didn't fail but...

Because K80 GPU is not supported by superbench, it is OK not to support it.

Ping. Any comments on this issue? thanks.

facing same issue. can someone share some answers for this?