google / vit-base-patch16-224
Vision87M15.7M1KUpdated Sep 5, 2023
Downloads
15.7M
Likes
1K
Last updated
Sep 5, 2023
License
apache-2.0
Vision Transformer (ViT) model pre-trained on ImageNet-21k (14 million images, 21,843 classes) at resolution 224x224, and fine-tuned on ImageNet 2012 (1 million images, 1,000 classes) at resolution 224x224. It was introduced in the paper An Image is Worth 16x16 Words: Transfor…
Tasks & library
- image classification
- transformers
Tags
- transformers
- pytorch
- tf
- jax
- vit
- image-classification
Technical specifications
Parameters87M
Librarytransformers
LanguagesNot available
Licenseapache-2.0