Why not use SyncBN

[JingyangXiang]

Thanks for your amazing work!It converges fastly and get amazing accuracy on imagenet.
In your pth file, I found args.sync_bn is False.
In your train.py, I found the model in your code broadcast buffers about bn before each forward instead of SyncBN.
So, I have a small question, why don't you use SyncBN?
Thanks very much!

[MenghaoGuo]

Good question.

We ignored SyncBN and did not conduct this experiment.
I think it will improve the performance of the models.
I am going to try it now.

Thanks for your question and kind advice.

[JingyangXiang]

Thanks for your reply~
hoping SyncBN can achieve higher accuracy