metadata

tags:
  - timm
  - feature-extraction
  - image-classification
library_name: timm
license: apache-2.0

Model card for vit_giant_patch14_224.dinobloom

Model Details

Model Type: Feature backbone
Model Stats:
- Params: 1136M (giant)
- Image size: 224 x 224 x 3
- Patch size: 14 x 14 x 3
Repository: github.com:marrlab/DinoBloom
Original Weights: Zenodo
License: Apache License 2.0
Papers:
- DinoBloom: A Foundation Model for Generalizable Cell Embeddings in Hematology

Model Usage

Image Embeddings

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_giant_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

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}
}