Hugging Face's logo

nielsr
/
beit-base-patch16-224

Image Classification
Transformers
PyTorch
JAX
beit
Inference Endpoints
Model card Files Community
beit-base-patch16-224 / README.md
nielsr's picture
nielsr HF staff
Add model card
fe27937
preview code
|
raw
history blame contribute delete
816 Bytes
metadata
license: apache-2.0
tags:
  - image-classification
datasets:
  - imagenet
  - imagenet-21k

BEiT (base-sized model, fine-tuned on ImageNet-1k after being intermediately fine-tuned on ImageNet-22k)

BEiT (BERT pre-training of Image Transformers) model pre-trained in a self-supervised way on ImageNet-22k (14 million images, 21,841 classes) at resolution 224x224, and also fine-tuned on the same dataset at the same resolution. It was introduced in the paper BEiT: BERT Pre-Training of Image Transformers by Hangbo Bao, Li Dong and Furu Wei and first released in this repository.

Disclaimer: The team releasing BEiT did not write a model card for this model so this model card has been written by the Hugging Face team.