FeyNobg / README.md

FeyNobg: BiRefNet grown to depths [2,2,24,2] (262.8M) via from_origin from nobg/BiRefNet base; trained 5000 steps on a 28k balanced 12-source mix incl. matting sets; checkpoint-4500 (best mean S-measure 0.9350 over 8 benchmarks)

4be781f verified about 7 hours ago

preview code

Raw

History Blame Contribute Delete

1.21 kB

metadata

library_name: nobg
tags:
  - birefnet
  - model_hub_mixin
  - nobg
  - pytorch_model_hub_mixin

This model has been pushed to the Hub using the PytorchModelHubMixin integration.

Library: nobg

how to load

pip install nobg

use the AutoModel class

from nobg import AutoModel
model = AutoModel.from_pretrained("nobg/FeyNobg")

or you can use the model class directly

from nobg import BiRefNet
model = BiRefNet.from_pretrained("nobg/FeyNobg")

Citation

If you use this model, please cite the original paper (https://arxiv.org/abs/2401.03407):

@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},
  year={2024}
}

Contributions

Any contributions are welcome at https://github.com/feyninc/nobg