KaihongLi

Results 2 issues of KaihongLi

How can I perform mixed training with DET and VID datasets, considering that the DET dataset does not consist of consecutive frames? In your code, you mentioned performing only a...

def match_embds(self, ref_embds, cur_embds): # embeds (q, b, c) ref_embds, cur_embds = ref_embds.detach()[:, 0, :], cur_embds.detach()[:, 0, :] ref_embds = ref_embds / (ref_embds.norm(dim=1)[:, None] + 1e-6) cur_embds = cur_embds /...