jeonsworld / ViT-pytorch

Pytorch reimplementation of the Vision Transformer (An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale)
MIT License
1.95k stars 374 forks source link

train from scratch on cifar100 #34

Open ganyibo opened 3 years ago

ganyibo commented 3 years ago

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

xml94 commented 3 years ago

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

xiaoweidao commented 3 years ago

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

peylnog commented 1 year ago

the same question