V
ViT-CIFAR
PyTorch implementation for Vision Transformer[Dosovitskiy, A.(ICLR'21)] modified to obtain over 90% accuracy FROM SCRATCH on CIFAR-10 with small number of parameters (= 6.3M, originally ViT-B has 86M).
To receive notifications about scheduled maintenance, please subscribe to the mailing-list gitlab-operations@sympa.ethz.ch. You can subscribe to the mailing-list at https://sympa.ethz.ch
Billing FAQ at https://unlimited.ethz.ch/display/itkb/GitLab+Billing+FAQ
PyTorch implementation for Vision Transformer[Dosovitskiy, A.(ICLR'21)] modified to obtain over 90% accuracy FROM SCRATCH on CIFAR-10 with small number of parameters (= 6.3M, originally ViT-B has 86M).