Add simple TARGO-Net model card

README.md

@@ -1,3 +1,70 @@
 ---
 license: mit
+language:
+- en
+tags:
+- robotics
+- grasping
+- 3d-vision
+- shape-completion
+- pytorch
+library_name: pytorch
 ---
+
+# TARGO-Net
+
+TARGO-Net is a PyTorch checkpoint release for target-oriented robotic grasping in cluttered scenes. This repository currently provides the model weights needed by the cleaned TARGO inference and training code.
+
+## Files
+
+| File | Description |
+| --- | --- |
+| `checkpoints/targonet.pt` | TARGO grasp prediction network checkpoint. |
+| `checkpoints/adapointr.pth` | AdaPoinTr shape completion checkpoint used by the TARGO inference pipeline. |
+
+## Usage
+
+Download the checkpoints with `huggingface_hub`:
+
+```python
+from huggingface_hub import snapshot_download
+
+snapshot_download(
+    repo_id="randing2000/TARGO-Net",
+    local_dir="checkpoints_hf",
+    allow_patterns=["checkpoints/targonet.pt", "checkpoints/adapointr.pth"],
+)
+```
+
+For the cleaned TARGO code, place or link the downloaded files as:
+
+```text
+checkpoints/targonet.pt
+checkpoints/adapointr.pth
+```
+
+Then run inference with the processed VGN-format test data:
+
+```bash
+python inference_targo.py   --model checkpoints/targonet.pt   --sc_model_path checkpoints/adapointr.pth   --test_root /path/to/processed_vgn/test_set_gaussian_0.002
+```
+
+The `--test_root` directory should contain:
+
+```text
+scenes/
+mesh_pose_dict/
+occ_level_dict.json
+```
+
+## Training / Evaluation Data
+
+The checkpoints are intended for the TARGO/VGN-style data pipeline. The processed dataset is not included in this model repository.
+
+## Limitations
+
+These weights are research artifacts and are intended for offline robotics research workflows. Real-robot deployment requires additional calibration, safety checks, and environment-specific validation.
+
+## License
+
+MIT.