jeonsworld / ViT-pytorch

Pytorch reimplementation of the Vision Transformer (An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale)

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

train from scratch on cifar100

ganyibo opened this issue · comments

What is the accuracy of training from scratch on CIFAR100? Do you have tried?

Did you train from scratch on CIFAR10 and CIFAR100?
Could you please share the performance?

Hello, do you know how to train from scratch? Can you tell me? Thank you!

the same question