Giters

serizba / salad

Optimal Transport Aggregation for Visual Place Recognition

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

DINOV2-Netvlad

pQWQq opened this issue · comments

commented

Hello, I want to reproduce the experiment in the paper, but cannot find the corresponding parameters. Can you provide the training code of DINOV2-Netvlad?

commented

Hi @pQWQq , you can use the same hyperparameters for training. Just append a NetVLAD aggregator.