batch size

[LXXXXR]

Hi,
Thank you for the work. May I ask, for ResNeSt-50, did you use batch size of 8192 (from paper) or 2048 (from pytorch-encoding)? How much will the performance change?
And I was also wondering the drop out was mentioned in the paper while set to 0 in the training script in pytorch-encoding. Does it mean the trick won’t have much of impact on the performance?
Thanks again for the time.

[zhanghang1989]

The models in the original paper were trained using MXNet implementation.

Typically, the larger the batch size is, the wore the performance will be. See "train ImageNet in 1 hr" paper for details.

The drop out only helps larger model.