๐ Model card for vit_large_patch14_dinov2.lvd142m
This is a Vision Transformer (ViT) image feature model. It is pretrained on LVD-142M using the self-supervised DINOv2 method, which can effectively extract image features.
๐ Quick Start
This model can be used for image classification and feature extraction. You can refer to the following usage examples for operation.
โจ Features
- Model Type: Image classification / feature backbone
- Model Stats:
- Params (M): 304.4
- GMACs: 507.1
- Activations (M): 1058.8
- Image size: 518 x 518
- Papers:
- Original: https://github.com/facebookresearch/dinov2
- Pretrain Dataset: LVD-142M
๐ฆ Installation
The model uses the timm
library. You can install it through the following command:
pip install timm
๐ป 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_patch14_dinov2.lvd142m', pretrained=True)
model = model.eval()
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))
top5_probabilities, top5_class_indices = torch.topk(output.softmax(dim=1) * 100, k=5)
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_patch14_dinov2.lvd142m',
pretrained=True,
num_classes=0,
)
model = model.eval()
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 = model.forward_features(transforms(img).unsqueeze(0))
output = model.forward_head(output, pre_logits=True)
๐ Documentation
Explore the dataset and runtime metrics of this model in timm model results.
๐ License
This project is licensed under the Apache-2.0 license.
๐ Citation
@misc{oquab2023dinov2,
title={DINOv2: Learning Robust Visual Features without Supervision},
author={Oquab, Maxime and Darcet, Timothรฉe and Moutakanni, Theo and Vo, Huy V. and Szafraniec, Marc and Khalidov, Vasil and Fernandez, Pierre and Haziza, Daniel and Massa, Francisco and El-Nouby, Alaaeldin and Howes, Russell and Huang, Po-Yao and Xu, Hu and Sharma, Vasu and Li, Shang-Wen and Galuba, Wojciech and Rabbat, Mike and Assran, Mido and Ballas, Nicolas and Synnaeve, Gabriel and Misra, Ishan and Jegou, Herve and Mairal, Julien and Labatut, Patrick and Joulin, Armand and Bojanowski, Piotr},
journal={arXiv:2304.07193},
year={2023}
}
@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}}
}