uzh-rpg/E-RAFT

Release the training code

boomboomluo opened this issue · 1 comments

Hi,Mathias
I want to train your network in other dataset, but I can't find the training code, could you please ralease it.

Hi @boomboomluo

We are planning to release the training code as part of an extension of this work but is unfortunately still a work in progress. In the meantime, is there a way I can help?
If you want to train the network on a different dataset, I would propose you train the non-recurrent version by taking the network and integrating it into your pipeline.