google/vit-large-patch16-224-in21k

Vision Transformer (ViT) model pre-trained on ImageNet-21k (14 million images, 21,843 classes) at resolution 224x224 . It was introduced in the paper An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale by Dosovitskiy et al. It is a transformer encoder model (BERT-like) pretrained on a large collection of images in a supervised fashion . The model was trained on TPUv3 hardware (8 cores) with a batch size of 4096 and learning rate warmup of 10k steps . The team releasing ViT did not write a model card for this model so this model card,