Push model using huggingface_hub.

README.md

@@ -0,0 +1,50 @@
+---
+library_name: nobg
+tags:
+- birefnet
+- model_hub_mixin
+- nobg
+- pytorch_model_hub_mixin
+---
+
+<p align="center">
+<img src="https://usefeyn.com/feyn/feyn_mark.svg"/>
+</p>
+
+This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) integration.
+
+Library: [nobg](https://github.com/feyninc/nobg)
+
+## how to load
+```
+pip install nobg
+```
+
+use the AutoModel class
+```python
+from nobg import AutoModel
+model = AutoModel.from_pretrained("feyninc/FeyNobg")
+```
+or you can use the model class directly
+```python
+from nobg import BiRefNet
+model = BiRefNet.from_pretrained("feyninc/FeyNobg")
+```
+
+
+## Citation
+If you use this model, please cite:
+```bibtex
+@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

config.json

@@ -0,0 +1,26 @@
+{
+  "dec_channels_inter": 64,
+  "depths": [
+    2,
+    2,
+    24,
+    2
+  ],
+  "drop_path_rate": 0.2,
+  "embed_dim": 192,
+  "image_size": 1024,
+  "mlp_ratio": 4.0,
+  "nobg_version": "0.2.0",
+  "num_heads": [
+    6,
+    12,
+    24,
+    48
+  ],
+  "num_layers": 4,
+  "patch_size": 4,
+  "use_gradient_attention": true,
+  "use_image_patch_injection": true,
+  "use_multi_scale_input": true,
+  "window_size": 12
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ee181389acf07c6dcf3d72caba2d169224caacdde8bb837ecf7aa3e22e0c3aa
+size 1051353168