Upload octformer-base.modelnet40.octree-nn

README.md

@@ -0,0 +1,112 @@
+---
+license: mit
+library_name: torch-pointcloud
+tags:
+- point-cloud
+- 3d
+- pytorch
+- torch-pointcloud
+- octformer
+- classification
+datasets:
+- modelnet40
+model-index:
+- name: octformer-base.modelnet40.octree-nn
+  results:
+  - task:
+      type: point-cloud-classification
+    dataset:
+      name: ModelNet40
+      type: modelnet40
+    metrics:
+    - name: OA
+      type: accuracy
+      value: 89.02
+---
+
+# Model card for octformer-base.modelnet40.octree-nn
+
+An OctFormer point cloud classification model (octree-based windowed transformer). Trained on ModelNet40.
+
+## Model Details
+
+- **Model Type:** Point cloud classification
+- **Model Stats:**
+  - Params (M): 4.0
+  - Input channels: 4
+  - Classes: 40
+  - Features: 192
+- **Dataset:** ModelNet40
+- **Metrics:** OA 89.02 (reference 92.7)
+- **Paper:** [OctFormer: Octree-based Transformers for 3D Point Clouds](https://arxiv.org/abs/2305.03045)
+- **Converted from:** [octree-nn/octformer](https://github.com/octree-nn/octformer) (MIT)
+- **Library:** [torch-pointcloud](https://github.com/arthurdjn/pytorch-pointcloud)
+
+## Install
+
+```bash
+pip install torch-pointcloud
+```
+
+## Usage
+
+```python
+import torch
+import torch_pointcloud as tp
+from torch_pointcloud.utils.data import collate
+
+model, info = tp.create_model(
+    "octformer-base.modelnet40.octree-nn",
+    task="classification",
+    pretrained=True,
+    return_info=True,
+)
+model = model.cuda().eval()  # GPU-only kernels
+
+# synthetic sample with the keys a dataset provides
+num_points = 8192
+sample = {
+    "pos": torch.randn(num_points, 3),
+    "normal": torch.randn(num_points, 3),
+    "face": torch.randint(0, num_points, (2 * num_points, 3)),
+}
+data = info["transform"](sample)
+data = collate([data])
+data = {key: value.cuda() for key, value in data.items()}
+
+with torch.no_grad():
+    logits = model(data.get("x"), data["octree"], data["octree"].depth)
+```
+
+## Feature extraction
+
+```python
+with torch.no_grad():
+    embeddings = model.forward_features(data.get("x"), data["octree"], data["octree"].depth)
+
+model.reset_classifier(num_classes=0)
+with torch.no_grad():
+    embeddings = model(data.get("x"), data["octree"], data["octree"].depth)  # (B, 192)
+```
+
+## Citation
+
+```bibtex
+@article{wang2023octformer,
+  title   = {OctFormer: Octree-based Transformers for 3D Point Clouds},
+  author  = {Peng-Shuai Wang},
+  journal = {ACM Transactions on Graphics},
+  volume  = {42},
+  number  = {4},
+  year    = {2023}
+}
+```
+
+```bibtex
+@inproceedings{wu2015modelnet,
+  title   = {3D ShapeNets: A Deep Representation for Volumetric Shapes},
+  author  = {Zhirong Wu and Shuran Song and Aditya Khosla and Fisher Yu and Linguang Zhang and Xiaoou Tang and Jianxiong Xiao},
+  booktitle = {CVPR},
+  year    = {2015}
+}
+```

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a00060b63cac7d8148d0a40c680810c5625e7fa62f019454cc1d1bac923bbdcc
+size 15964496