May I ask the author, how should I choose different numbers of visual tokens to experiment with the impact of different visual tokens on the results? Is it setting a different number of clusters? As in the code below:
and I can modify kin the code to set a different number of visual tokens. Is my understanding correct? Hope to get the author's answer
_, cluster_indices = torch.topk(cos_sim_matrix, k=int(32), dim=2, largest=True)
May I ask the author, how should I choose different numbers of visual tokens to experiment with the impact of different visual tokens on the results? Is it setting a different number of clusters? As in the code below:
and I can modify
k
in the code to set a different number of visual tokens. Is my understanding correct? Hope to get the author's answer_, cluster_indices = torch.topk(cos_sim_matrix, k=int(32), dim=2, largest=True)