Hello, thank you very much for your team's excellent work. When I reproduced your code, I obtained metrics lower than those in your paper. One possible reason is that the CLIP features I used may not be the best. I would like to ask, at which iteration was the best CLIP model you used trained?
Hello, thank you very much for your team's excellent work. When I reproduced your code, I obtained metrics lower than those in your paper. One possible reason is that the CLIP features I used may not be the best. I would like to ask, at which iteration was the best CLIP model you used trained?