About AMP and batch size
Closed this issue · 2 comments
Hi,
I'm very impressed by your excellent work! Thanks for sharing your code.
I have questions about the training protocol.
In your paper,
"We train all models with a global batch size of 2048 with the NVIDIA Automatic Mixed Precision(AMP) enabled."
but the training script denotes the batch size of 256, instead of 2048.
I wonder two points from here.
-
Can I re-produce the result accuracy in this repo by using this command (batch size=256, instead of 2048)?
-
Does this repo contains AMP?
Thanks in advance :)
Hi @youngwanLEE, thank you for your interest in our work!
-
For your batch size concern, actually 256 means the batch size per GPU. The 8-GPU setting is used in the default training command and it has a total batch size 2048. You should be able to re-produce the result accuracy (similar to our reported ones) using the command provided in this repo.
-
Yes. The AMP is enabled at default.
@xwjabc Thanks for your quick reply :)