Upload pointnext-lg.s3dis-area3.openpoints

README.md

@@ -0,0 +1,98 @@
+---
+license: mit
+library_name: torch-pointcloud
+tags:
+- point-cloud
+- 3d
+- pytorch
+- torch-pointcloud
+- pointnext
+- segmentation
+datasets:
+- s3dis
+---
+
+# Model card for pointnext-lg.s3dis-area3.openpoints
+
+A PointNeXt point cloud segmentation model (scaled PointNet++ with inverted residual blocks). Trained on S3DIS (Area 3).
+
+## Model Details
+
+- **Model Type:** Point cloud semantic segmentation
+- **Model Stats:**
+  - Params (M): 7.1
+  - Input channels: 4
+  - Classes: 13
+  - Features: 32
+- **Dataset:** S3DIS (Area 3)
+- **Paper:** [PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategies](https://arxiv.org/abs/2206.04670)
+- **Converted from:** [guochengqian/PointNeXt](https://github.com/guochengqian/PointNeXt) (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(
+    "pointnext-lg.s3dis-area3.openpoints",
+    task="segmentation",
+    pretrained=True,
+    return_info=True,
+)
+model = model.eval()
+
+# synthetic sample with the keys a dataset provides
+num_points = 8192
+sample = {
+    "pos": torch.randn(num_points, 3),
+    "color": torch.rand(num_points, 3) * 255,
+    "norm_pos": torch.rand(num_points, 3),
+    "segment": torch.zeros(num_points, dtype=torch.long),
+    "instance": torch.zeros(num_points, dtype=torch.long),
+}
+data = info["transform"](sample)
+data = collate([data])
+
+with torch.no_grad():
+    logits = model(data.get("x"), data["pos"], data["batch"])
+```
+
+## Feature extraction
+
+```python
+with torch.no_grad():
+    features = model.forward_features(data.get("x"), data["pos"], data["batch"])
+
+model.reset_classifier(num_classes=0)
+with torch.no_grad():
+    features = model(data.get("x"), data["pos"], data["batch"])  # (N, 32)
+```
+
+## Citation
+
+```bibtex
+@inproceedings{qian2022pointnext,
+  title   = {PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategies},
+  author  = {Guocheng Qian and Yuchen Li and Houwen Peng and Jinjie Mai and Hasan Abed Al Kader Hammoud and Mohamed Elhoseiny and Bernard Ghanem},
+  booktitle = {NeurIPS},
+  year    = {2022}
+}
+```
+
+```bibtex
+@inproceedings{armeni2016s3dis,
+  title     = {{3D} Semantic Parsing of Large-Scale Indoor Spaces},
+  author    = {Armeni, Iro and Sener, Ozan and Zamir, Amir R. and Jiang, Helen and Brilakis, Ioannis and Fischer, Martin and Savarese, Silvio},
+  booktitle = {CVPR},
+  year      = {2016}
+}
+```

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00f4c62a8a605cbe29334d4cc7c5e62528f1c90ef21e354e17528ad898fa54b0
+size 28716628