Model card for vit_small_patch14_dinov2.lvd142m

A Swin-V image feature model. Superwisely pre-trained on animal re-identification datasets.

Model Details

• Model Type: Animal re-identification / feature backbone
• Model Stats:
  • Params (M): ??
  • GMACs: ??
  • Activations (M): ??
  • Image size: 224 x 224
• Papers:
  • Swin Transformer: Hierarchical Vision Transformer using Shifted Windows --> https://arxiv.org/abs/2103.14030
• Original: ??
• Pretrain Dataset: ??

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/wildlife-mega", pretrained=True)
model = model.eval()

train_transforms = T.Compose([T.Resize(224), 
                              T.ToTensor(), 
                              T.Normalize([0.5, 0.5, 0.5], [0.5, 0.5, 0.5])]) 

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

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

Model Comparison

???

Citation

@article{?????,
  title={?????},
  author={????},
  journal={????},
  year={????}
}