AlexGranger-scn comments

Repositories
Issues
Comments

Results 3 comments of


                                            AlexGranger-scn

Shouldn't Prototypical loss use torch.cdist instead of F.pairwise_distance?

Same confusion..... Have you solved this problem now? Thanks for your reply!

Abnormal data output and training period

> Did you fix this? As far as I can tell the main issue is that training is taking too long -- only seeing two points is normal for how...

Abnormal data output and training period

> I'm not totally sure -- there have been a few reports of similar problems from other users, and I haven't been able to replicate it. I think it's likely...