Closed Gumpest closed 5 months ago
Hi @Gumpest , thanks for your attention to our work!
The performance may drop slightly. The reason is that the global batch size affects the performance of the contrastive learning. In our experiment, the global batch size is 1024 * 32 gpus.
There are two solutions to support large batch size in limited resource.
I recommend the latter. We may integrate it into TinyCLIP in the future.
Thanks @wkcn detailed reply!
I wonder if I utilize 8 A100 80GB to improve the batch size to 4*1024, can the result be reproduced? Thanks.