Vit Small Patch14 224.dinobloom

🚀 vit_small_patch14_224.dinobloom

This model is a feature backbone for image classification and feature extraction, offering efficient performance with relatively few parameters.

🚀 Quick Start

This model, vit_small_patch14_224.dinobloom, is a feature backbone model designed for image classification and feature extraction. It can be easily integrated into your projects using the timm library.

✨ Features

• Feature Backbone: Ideal for extracting features from images.
• Small Model Size: With only 22M parameters, it's lightweight and efficient.
• Specific Image and Patch Sizes: Works best with 224x224x3 images and 14x14x3 patches.

📦 Installation

To use this model, you need to have the timm library installed. You can install it using the following command:

pip install timm

💻 Usage Examples

Basic Usage

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

# get example histology image
img = Image.open(
  urlopen(
    "https://raw.githubusercontent.com/zxaoyou/segmentation_WBC/master/Dataset%201/001.bmp"
  )
)

# load model from the hub
model = timm.create_model(
  model_name="hf-hub:1aurent/vit_small_patch14_224.dinobloom",
  pretrained=True,
).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)

data = transforms(img).unsqueeze(0) # input is a (batch_size, num_channels, img_size, img_size) shaped tensor
output = model(data)  # output is a (batch_size, num_features) shaped tensor

📚 Documentation

Model Details

📄 License

This model is released under the Apache License 2.0.

📝 Citation

@misc{koch2024dinobloom,
  title         = {DinoBloom: A Foundation Model for Generalizable Cell Embeddings in Hematology}, 
  author        = {Valentin Koch and Sophia J. Wagner and Salome Kazeminia and Ece Sancar and Matthias Hehr and Julia Schnabel and Tingying Peng and Carsten Marr},
  year          = {2024},
  eprint        = {2404.05022},
  archivePrefix = {arXiv},
  primaryClass  = {cs.CV}
}