SasikaA073/vit_base_patch14_reg4_dinov2.lvd142m_sp_ft_in1k

import torch
import timm
from PIL import Image

# Load model
model_id = "vit_base_patch14_reg4_dinov2.lvd142m"
model = timm.create_model(model_id, pretrained=False)
model.head = torch.nn.Linear(768, 1000, bias=True)

# Load weights
checkpoint = torch.load("pytorch_model.bin")
model.load_state_dict(checkpoint['model_state_dict'])
model.eval()

# Inference
data_config = timm.data.resolve_data_config(model.pretrained_cfg)
transforms = timm.data.create_transform(**data_config)

image = Image.open("your_image.jpg")
input_tensor = transforms(image).unsqueeze(0)

with torch.no_grad():
    output = model(input_tensor)
    probabilities = torch.nn.functional.softmax(output[0], dim=0)

@article{oquab2023dinov2,
  title={DINOv2: Learning Robust Visual Features without Supervision},
  author={Oquab, Maxime and Darcet, Timothée 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}
}