wuqun-tju
wuqun-tju
Besides， I found the result is multiple when runs inference_demo.py multitimes with the same inputs。Is there some config to set ? like seed?
Thank you for your reply！ The difference is significant among multi results of probabilistic solver. If the output of the network is same, the results of probabilistic solver may diff...
Besides, In the paper map-free_reloc， it is mentioned that Orthogonal Procrustes solver is worse, right? Lookforward your reply!
Thank you for your reply ! Sorry for confusions as follows 1. “We saw that when running the network over a large test set (Map-free test images), the results were...
OK， thank you for your quick reply. About the top 50% strategy, you mean this strategy is applied to other solver like pnp， rather than probabilistic solver.
> Hi, > > 1. not sure what you mean here. > 2. That's normal, it's because of the confidence loss > 3. the validation loss is a bit different,...
> yes, Waymo was replaced by an internal dataset for the checkpoints we released and the training commands reflect that. It was used to train the models we used in...
Thank you for your reply! I try to fintune unidepthv2 on my own datasets, I found in sequence datasets, there is a decode_fileds, I wonder wether "flow_fwd", "flow_fwd_mask" is necessary...