LauncH

Low Linear-Prob accuracy

6

Dear author I have reproduced your code using 64 V100 GPUs. Every setting is the same as paper (batch size 4096), The end-to-end finetuning is almost the same as paper....

Strange output log

12

Hi authors, I have pretrianed your moby_swin_tiny model using 8 Tesla V100 GPU and reproduced your results in downstream task. I get 74.394% on linear evaluation and 43.1% on COCO...

Thanks for your work! As shown in the markdown file, we can now pretrain Transformer-SSL via 8 GPUs and 1 node. Do you have scripts for multi-machine training? I want...