but doesn't it break the assumption that it should ideally be able to reproduce your original results
IMO it would be hard to reproduce the results using autoresearch setup.
To get CLIP to work properly we typically need large batch sizes. So the experiments in the original paper were quite heavy, and ran parallel across 8 GPUs.
alt Hacker News
IMO it would be hard to reproduce the results using autoresearch setup.
To get CLIP to work properly we typically need large batch sizes. So the experiments in the original paper were quite heavy, and ran parallel across 8 GPUs.