Update README.md

README.md

@@ -1,89 +1,89 @@
----
-license: bsd-3-clause
-pipeline_tag: robotics
-tags:
-  - necknet
-  - prosoro
-  - omnineck
-  - multimodal
-  - onnx
-  - pytorch
-library_name: transformers
-datasets:
-  - han-xudong/prosoro-100k
----
-
-# Model Card for NeckNet
-
-## Table of Contents
-
-- [Model Card for NeckNet](#model-card-for-necknet)
-  - [Table of Contents](#table-of-contents)
-  - [Model Description](#model-description)
-  - [Intended Use](#intended-use)
-  - [Training Data](#training-data)
-  - [Citation](#citation)
-
-## Model Description
-
-NeckNet is an MLP model designed for the OmniNeck. It can predict both 6D force and 3D shape (mesh nodes) from the 6D motion of the ball.
-
-Try it out on the [Spaces demo](https://huggingface.co/spaces/han-xudong/necknet-demo).
-
-- Developer: Xudong Han, Tianyu Wu, Fang Wan, and Chaoyang Song.
-- Model type: MLP
-- License: BSD-3-Clause
-
-## Intended Use
-
-This model is intended for researchers and developers working in robotics and tactile sensing. It can be used to enhance the capabilities of robotic systems by providing accurate predictions of force and shape based on tactile data.
-
-To load the model:
-
-```python
-from transformers import AutoModel
-
-model = AutoModel.from_pretrained("han-xudong/necknet", trust_remote_code=True)
-x = torch.zeros((1, 6))  # Example input: batch size of 1, 6D motion
-output = model(x)
-```
-
-Or to load the ONNX version:
-
-```python
-# Example code to load onnx
-import onnxruntime as ort
-import numpy as np
-from huggingface_hub import hf_hub_download
-
-onnx_model_path = hf_hub_download("han-xudong/necknet", filename="model.onnx")
-ort_session = ort.InferenceSession(onnx_model_path)
-
-# Example input
-x = np.zeros((1, 6), dtype=np.float32)  # Batch size of 1, 6D motion
-output = ort_session.run(None, {"motion": x})
-```
-
-## Training Data
-
-The model was trained on the [NeckNet-100K](https://huggingface.co/datasets/han-xudong/necknet-100k) dataset, which includes a variety of motion, force, and shape data collected by finite element simulations.
-
-## Citation
-
-If you use this model in your research, please cite the following papers:
-
-```bibtex
-@article{liu2024proprioceptive,
-  title={Proprioceptive learning with soft polyhedral networks},
-  author={Liu, Xiaobo and Han, Xudong and Hong, Wei and Wan, Fang and Song, Chaoyang},
-  journal={The International Journal of Robotics Research},
-  volume = {43},
-  number = {12},
-  pages = {1916-1935},
-  year = {2024},
-  publisher={SAGE Publications Sage UK: London, England},
-  doi = {10.1177/02783649241238765}
-}
-```
-
-[](https://arxiv.org/abs/2308.08538)
+---
+license: bsd-3-clause
+pipeline_tag: robotics
+tags:
+  - necknet
+  - prosoro
+  - omnineck
+  - multimodal
+  - onnx
+  - pytorch
+library_name: transformers
+datasets:
+  - han-xudong/prosoro-100k
+---
+
+<p align="center">
+  <img src="https://cdn-uploads.huggingface.co/production/uploads/670336f25ce58dd0c33e32e3/EC3s3yVe3mLlq6t6QxQGL.jpeg"
+       style="width:100%; max-width:1000px; height:auto;">
+</p>
+
+
+![banner](https://cdn-uploads.huggingface.co/production/uploads/670336f25ce58dd0c33e32e3/UC5ubSs7dBMU_y4YwUOMZ.jpeg)
+
+# NeckNet
+
+## Model Description
+
+NeckNet is an MLP model designed for the OmniNeck. It can predict both 6D force and 3D shape (mesh nodes) from the 6D motion of the ball.
+
+Try it out on the [Spaces demo](https://huggingface.co/spaces/han-xudong/necknet-demo).
+
+- Developer: Xudong Han, Fang Wan, and Chaoyang Song.
+- Model type: MLP
+- License: BSD-3-Clause
+- Github: [https://github.com/han-xudong/necknet](https://github.com/han-xudong/necknet)
+
+## Intended Use
+
+This model is intended for researchers and developers working in robotics and tactile sensing. It can be used to enhance the capabilities of robotic systems by providing accurate predictions of force and shape based on tactile data.
+
+To load the model:
+
+```python
+from transformers import AutoModel
+
+model = AutoModel.from_pretrained("han-xudong/necknet", trust_remote_code=True)
+x = torch.zeros((1, 6))  # Example input: batch size of 1, 6D motion
+output = model(x)
+```
+
+Or to load the ONNX version:
+
+```python
+# Example code to load onnx
+import onnxruntime as ort
+import numpy as np
+from huggingface_hub import hf_hub_download
+
+onnx_model_path = hf_hub_download("han-xudong/necknet", filename="model.onnx")
+ort_session = ort.InferenceSession(onnx_model_path)
+
+# Example input
+x = np.zeros((1, 6), dtype=np.float32)  # Batch size of 1, 6D motion
+output = ort_session.run(None, {"motion": x})
+```
+
+## Training Data
+
+The model was trained on the [ProSoRo-100K](https://huggingface.co/datasets/han-xudong/prosoro-100k) dataset, which includes a variety of motion, force, and shape data collected by finite element simulations.
+
+## Citation
+
+If you use this model in your research, please cite the following papers:
+
+```bibtex
+@article{liu2024proprioceptive,
+  title={Proprioceptive learning with soft polyhedral networks},
+  author={Liu, Xiaobo and Han, Xudong and Hong, Wei and Wan, Fang and Song, Chaoyang},
+  journal={The International Journal of Robotics Research},
+  volume = {43},
+  number = {12},
+  pages = {1916-1935},
+  year = {2024},
+  publisher={SAGE Publications Sage UK: London, England},
+  doi = {10.1177/02783649241238765}
+}
+```
+
+[](https://arxiv.org/abs/2308.08538)