hyp_metric

hyp_metric copied to clipboard

Distributed training cannot achieve ideal accuracy

1

some codes in `train.py` is like: ```python if world_size > 1: with torch.no_grad(): all_z = [torch.zeros_like(z) for _ in range(world_size)] torch.distributed.all_gather(all_z, z) all_z[cfg.local_rank] = z z = torch.cat(all_z) ``` I'm...

Cathy0908

Thank you for your commendable efforts in your work. I have a question regarding the split of the Stanford Cars dataset, which comprises 16,185 images representing 196 car models, in...

ppanzx

How can I get the visualization results as in Fig. 2 in the paper

1

Looking forward to your reply. Thanks.

ChengHan111