Closed BIGBALLON closed 2 months ago
Is there any dataset analyse for CommonPool(small / medium/ large /xlarge), especially the average caption length?
Hi @BIGBALLON, check out Appendix I of the paper for statistics: https://arxiv.org/abs/2304.14108. The average caption length for the small pool is 19.60 tokens. Hope this helps!
Is there any dataset analyse for CommonPool(small / medium/ large /xlarge), especially the average caption length?