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

Hyper-parameters for Fine-tuning CIFAR-100 #9

Open superctj opened 3 years ago

superctj commented 3 years ago

Is your feature request related to a problem? Please describe. Fine-tuning on CIFAR-100

Describe the solution you'd like Could you please provide hyper-parameters for fine-tuning CIFAR-100? Particularly, could you give a command-line instruction like the one for CIFAR-10 in README?

Describe alternatives you've considered Use the hyper-parameters of fine-tuning CIFAR-10

Additional context Add any other context or screenshots about the feature request here.