Hugging Face's logo

cs-giung
/
vit-large-patch16-imagenet21k-augreg

Image Classification
Transformers
Safetensors
vit
Inference Endpoints
Model card Files Community
Edit model card

Vision Transformer

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 and further enhanced in the follow-up paper How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers. The weights were converted from the L_16-i21k-300ep-lr_0.001-aug_strong1-wd_0.1-do_0.0-sd_0.0.npz file in GCS buckets presented in the original repository.

Downloads last month
4
Safetensors
Model size
326M params
Tensor type
F32
·
Inference Examples
Image Classification
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Collection including cs-giung/vit-large-patch16-imagenet21k-augreg