enhancing-transformers icon indicating copy to clipboard operation
enhancing-transformers copied to clipboard

Published 20 hours ago • verified publisher icon thuanz123

Could anyone reproduce the rFID scores from the small-large enc-dec version?

Open shashankg7 opened this issue 5 months ago • 0 comments

Hi,

I am running the model on ImageNet data from scratch, using the best config from the paper (small encoder and large decoder), training on a cluster of 56 A100 GPUs for more than a week's time, but the rFID (reconstruction FID on validation) I am getting so far is around 21, which is far from the number reported in the paper.

Could anyone get close to the rFID reported in the paper (around 1.6)?

shashankg7 avatar Sep 16 '24 15:09 shashankg7