snca.pytorch

snca.pytorch copied to clipboard

what would be the best way to do multi-gpu training for snca?

3

Shall I do nn.parallel.DistributedDataParallel for for both "model" and "lemniscate" and mannually sync each lemniscate memory per epoch? I think a better solution might be use a single GPU for...

pallashadow

The following links are not working : http://zhirongw.westus2.cloudapp.azure.com/models/snca_resnet18.pth.tar http://zhirongw.westus2.cloudapp.azure.com/models/snca_resnet34.pth.tar http://zhirongw.westus2.cloudapp.azure.com/models/snca_resnet50.pth.tar Please update.

ac20

It is possible that the 30-nearest neighbors share same labels (only 1 prediction). Therefore, it is impossible to calculate the top-5 acc. Please re-evaluate the scripts. Thank you.

kaleidoscopical

Comparison with proxy-NCA

1

Hi authors, How does this method compare to this paper from Google research? https://arxiv.org/pdf/1703.07464.pdf Pankesh

pbamotra

Hi there, I really like the paper and was wondering if you tried training a linear SVM on your 128 dim feature space - and if so how will did...

macaodha

# This GitHub repository has been identified as a candidate for archival This repository has had no activity for more than 2 years. Long periods of inactivity present security and...

microsoft-github-policy-service[bot]