Vit Large Patch16 224.orig In21k

🚀 vit_large_patch16_224.orig_in21k

A Vision Transformer (ViT) image classification model. Pretrained on ImageNet-21k in JAX by paper authors, ported to PyTorch by Ross Wightman. This model is useful for feature extraction and fine - tuning without a classification head.

🚀 Quick Start

This is a Vision Transformer (ViT) image classification model. It was pretrained on ImageNet - 21k in JAX by the paper authors and then ported to PyTorch by Ross Wightman. The model lacks a classification head, making it suitable only for feature extraction and fine - tuning.

✨ Features

• Model Type: Image classification / feature backbone
• Model Stats:
  • Params (M): 303.3
  • GMACs: 59.7
  • Activations (M): 43.8
  • Image size: 224 x 224
• Papers:
  • An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
• Dataset: ImageNet - 21k
• Original: https://github.com/google - research/vision_transformer

📦 Installation

Since the code uses the timm library, you can install it via the following command:

pip install timm

💻 Usage Examples

Basic Usage

Image Classification

from urllib.request import urlopen
from PIL import Image
import timm

img = Image.open(urlopen(
    'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))

model = timm.create_model('vit_large_patch16_224.orig_in21k', pretrained=True)
model = model.eval()

# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)

output = model(transforms(img).unsqueeze(0))  # unsqueeze single image into batch of 1

top5_probabilities, top5_class_indices = torch.topk(output.softmax(dim=1) * 100, k=5)

Advanced Usage

Image Embeddings

from urllib.request import urlopen
from PIL import Image
import timm

img = Image.open(urlopen(
    'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))

model = timm.create_model(
    'vit_large_patch16_224.orig_in21k',
    pretrained=True,
    num_classes=0,  # remove classifier nn.Linear
)
model = model.eval()

# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)

output = model(transforms(img).unsqueeze(0))  # output is (batch_size, num_features) shaped tensor

# or equivalently (without needing to set num_classes=0)

output = model.forward_features(transforms(img).unsqueeze(0))
# output is unpooled, a (1, 197, 1024) shaped tensor

output = model.forward_head(output, pre_logits=True)
# output is a (1, num_features) shaped tensor

📚 Documentation

Explore the dataset and runtime metrics of this model in timm model results.

📄 License

This project is licensed under the Apache - 2.0 license.

📄 Citation

@article{dosovitskiy2020vit,
  title={An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale},
  author={Dosovitskiy, Alexey and Beyer, Lucas and Kolesnikov, Alexander and Weissenborn, Dirk and Zhai, Xiaohua and Unterthiner, Thomas and  Dehghani, Mostafa and Minderer, Matthias and Heigold, Georg and Gelly, Sylvain and Uszkoreit, Jakob and Houlsby, Neil},
  journal={ICLR},
  year={2021}
}

@misc{rw2019timm,
  author = {Ross Wightman},
  title = {PyTorch Image Models},
  year = {2019},
  publisher = {GitHub},
  journal = {GitHub repository},
  doi = {10.5281/zenodo.4414861},
  howpublished = {\url{https://github.com/huggingface/pytorch-image-models}}
}