google/vit-large-patch16-384

The Vision Transformer (ViT) is a transformer encoder model (BERT-like) pretrained on a large collection of images in a supervised fashion . The model was fine-tuned on ImageNet-21k (14 million images, 21,843 classes) at resolution 224x224 . Images are presented to the model as a sequence of fixed-size patches (resolution 16x16), which are linearly embedded. One also adds a [CLS] token to the beginning of a sequence to use it for classification tasks. The exact details of preprocessing of images during training/validation can be found here . Both the feature extractor and model support PyTor,