hugpadhugpad

timm / vit_small_patch16_224.augreg_in21k_ft_in1k

Vision22M318.9K4Updated Jan 21, 2025
Hugging Face

Downloads

318.9K

Likes

4

Last updated

Jan 21, 2025

License

apache-2.0

A Vision Transformer (ViT) image classification model. Trained on ImageNet-21k and fine-tuned on ImageNet-1k (with additional augmentation and regularization) in JAX by paper authors, ported to PyTorch by Ross Wightman.

Tasks & library

  • image classification
  • timm

Tags

  • timm
  • pytorch
  • image-classification
  • transformers

Technical specifications

Parameters22M
Librarytimm
LanguagesNot available
Licenseapache-2.0