Image resolution for training

asyml / vision-transformer-pytorch

Pytorch version of Vision Transformer (ViT) with pretrained models. This is part of CASL (https://casl-project.github.io/) and ASYML project.

https://asyml.io/

Apache License 2.0

342 stars 58 forks source link

Closed a-maiti closed 3 years ago

a-maiti commented 3 years ago

What was the image resolution used for training on ImageNet? On paper, it's written 224, but it seems 384 was used for this code?

a-maiti commented 3 years ago

Nevermind, got it. It is correct.