BVRA / MegaDescriptor-CLIP-336

Model card

A CLIP based image feature model. Supervisely pre-trained on animal re-identification datasets. Original model: timm/vit_large_patch14_clip_336.openai_ft_in12k_in1k

Model Details

• Model Type: Animal re-identification / feature backbone
• Model Stats:
• Params (M): 304.5
• GMACs: 174.7
• Activations (M): 128.2
• Image size: 336 x 336

Model Usage

Image Embeddings

import timm
import torch
import torchvision.transforms as T

from PIL import Image
from urllib.request import urlopen

model = timm.create_model("hf-hub:BVRA/MegaDescriptor-CLIP-336", pretrained=True)
model = model.eval()

transforms = T.Compose([T.Resize(336), 
                              T.ToTensor(), 
                              T.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])]) 

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

output = model(transforms(img).unsqueeze(0))  # output is (batch_size, num_features) shaped tensor
# output is a (1, num_features) shaped tensor

Citation

@inproceedings{vcermak2024wildlifedatasets,
  title={WildlifeDatasets: An open-source toolkit for animal re-identification},
  author={{\v{C}}erm{\'a}k, Vojt{\v{e}}ch and Picek, Lukas and Adam, Luk{\'a}{\v{s}} and Papafitsoros, Kostas},
  booktitle={Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision},
  pages={5953--5963},
  year={2024}
}