metadata
library_name: nobg
tags:
- nobg-birefnet
- model_hub_mixin
- nobg
- pytorch_model_hub_mixin
license: apache-2.0
This model has been pushed to the Hub using the PytorchModelHubMixin integration.
Library: nobg
Blog : feynobg blogpost HF blogpost
how to use the model
pip install nobg>=0.2.5
import torch
from loadimg import load_img
from nobg import AutoModel, AutoProcessor
model = AutoModel.from_pretrained("feyninc/FeyNobg").eval()
processor = AutoProcessor.from_pretrained("feyninc/FeyNobg")
image = load_img("input.jpg").convert("RGB")
inputs = processor(image, return_tensors="pt")
with torch.no_grad():
outputs = model(pixel_values=inputs["pixel_values"])
alpha = processor.post_process_alpha_matting(
outputs, target_sizes=[(image.height, image.width)]
)[0]
processor.cutout(image, alpha).save("output.png")
Citation
If you use this model, please cite:
@article{zheng2024birefnet,
title={Bilateral Reference for High-Resolution Dichotomous Image Segmentation},
author={Zheng, Peng and Gao, Dehong and Fan, Deng-Ping and Liu, Li and Laaksonen, Jorma and Ouyang, Wanli and Sebe, Nicu},
journal={CAAI Artificial Intelligence Research},
volume={3},
pages={9150038},
year={2024},
url={https://arxiv.org/abs/2401.03407},
}
Contributions
Any contributions are welcome at https://github.com/feyninc/nobg