search

facebookresearch / mvit

Code Release for MViTv2 on Image Recognition.
Apache License 2.0
372 stars 43 forks source link

Would Mixed Precision Training Impact Performance? #9

Closed JunweiLiang closed 1 year ago

JunweiLiang commented 2 years ago

Hi,

Thanks for the great work. I have tried to train MViTv2 model on IN-1K but I got ~0.5 point Top-1 less than reported. I think the differences between my training procedure compared to the paper are just a smaller batch size (I used 1024 instead of 2048) and enabling mixed-precision training. Do you think these would cause the performance difference? Thanks!

Best, Junwei

lyttonhao commented 1 year ago

Hi, we didn't use different batch size and mixed-precision training. It's possible that affecting the results.