Shortcuts

VisionTransformer

The VisionTransformer model is based on the An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale paper.

Model builders

The following model builders can be used to instantiate a VisionTransformer model, with or without pre-trained weights. All the model builders internally rely on the torchvision.models.vision_transformer.VisionTransformer base class. Please refer to the source code for more details about this class.

vit_b_16(*[, weights, progress])

Constructs a vit_b_16 architecture from An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale.

vit_b_32(*[, weights, progress])

Constructs a vit_b_32 architecture from An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale.

vit_l_16(*[, weights, progress])

Constructs a vit_l_16 architecture from An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale.

vit_l_32(*[, weights, progress])

Constructs a vit_l_32 architecture from An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale.

vit_h_14(*[, weights, progress])

Constructs a vit_h_14 architecture from An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale.

Docs

Access comprehensive developer documentation for PyTorch

View Docs

Tutorials

Get in-depth tutorials for beginners and advanced developers

View Tutorials

Resources

Find development resources and get your questions answered

View Resources