About img size in Distillation
Eric-YuanL opened this issue · comments
Hi,
May i ask why img = torch.randn(1, 3, 256, 256) in ViT Usage, but img = torch.randn(2, 3, 256, 256) in Distillation Usage?
What's the difference while 1 changing to 2?
lucidrains / vit-pytorch
Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch