Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets new
  • Docs
  • Enterprise
  • Pricing

  • Log In
  • Sign Up

google
/
vit-base-patch16-224-in21k

Image Feature Extraction
Transformers
PyTorch
google-tensorflow TensorFlow
JAX
Safetensors
vit
vision
Model card Files Files and versions
xet
Community
17

Instructions to use google/vit-base-patch16-224-in21k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • Transformers

    How to use google/vit-base-patch16-224-in21k with Transformers:

    # Use a pipeline as a high-level helper
    from transformers import pipeline
    
    pipe = pipeline("image-feature-extraction", model="google/vit-base-patch16-224-in21k")
    # Load model directly
    from transformers import AutoImageProcessor, AutoModel
    
    processor = AutoImageProcessor.from_pretrained("google/vit-base-patch16-224-in21k")
    model = AutoModel.from_pretrained("google/vit-base-patch16-224-in21k")
  • Notebooks
  • Google Colab
  • Kaggle
New discussion
Resources
  • PR & discussions documentation
  • Code of Conduct
  • Hub documentation

🚩 Report: Copyright infringement

#17 opened 5 months ago by
fwp2025

Request: DOI

#16 opened 5 months ago by
sarakabariti

Request: DOI

#15 opened 11 months ago by
VlZKrypton

gradcam

#14 opened over 1 year ago by
Jessystein

Request: DOI

#13 opened over 1 year ago by
Stamo

Unknown error related to channel dimensions

#12 opened over 1 year ago by deleted

Create Flame

#11 opened over 1 year ago by
Flammyjack

Why the embedding on CPU is far faster than GPU?

2
#10 opened almost 2 years ago by
ViGeng

How can I get the model checkpoint loaded in different epoch? Such as epoch800.pt, epoch1000.pt and so on.

#9 opened about 2 years ago by
Aboooo

Potential discrepancy between the weights between Huggingface and Timm for google/vit-base-patch16-224-in21k

7
#7 opened over 2 years ago by
turtleman

This will not work with Pytorch 2.0

1
#5 opened about 3 years ago by
HimeshaAkalanka

How to replicate CIFAR100 fine-tuning performance?

1
#3 opened over 3 years ago by
HuBot2020

How to register custom object for the TFViTMainLayer in this model?

#2 opened over 3 years ago by
mbluetail

Saving the model with jit script

1
#1 opened almost 4 years ago by
i9like9music
Company
TOS Privacy About Careers
Website
Models Datasets Spaces Pricing Docs