lukemelas / PyTorch-Pretrained-ViT

Vision Transformer (ViT) in PyTorch
782 stars 126 forks source link

B_16 return zeros #10

Open dinarkino opened 3 years ago

dinarkino commented 3 years ago

By some reason, the output of B_16 model is only zeros. I tested B_32 and L_32, seems like they work properly