Trained without data augmentation? about nfnets_pytorch

[nandi-zhang]

Got it. Just take your time and good luck on the exams. :))

[benjs]

The results were derived from the pretrained weights, provided by the authors in their original repo :)

As the data augmentation is not implemented yet, the training script should reach the baseline accuracy as provided in the paper (F0: 80%). This, however, is not tested yet. I am currently adding mutli gpu support (see branch distributed) and try to reach the baseline accuracy on AWS. This will unfortunatly take some time as I am writing exams the next weeks :/