Performance on train from scratch

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

Performance on train from scratch #4

Open yyou1996 opened 3 years ago

yyou1996 commented 3 years ago

Thank you for your great work. I wonder what is the performance on train from scratch for cifar10 & cifar100? Seems this model heavily relies on the pretrained weights.

Hhhhhhao commented 3 years ago

the results on cifar10 & cifar100 are fine-tuned from the pretrained weights