Update README.md and config.json and model.safetensors for second.kitti.mmdet3d

README.md

@@ -0,0 +1,129 @@
+---
+license: apache-2.0
+library_name: torch-pointcloud
+tags:
+- point-cloud
+- 3d
+- pytorch
+- torch-pointcloud
+- second
+- object-detection
+datasets:
+- kitti
+model-index:
+- name: second.kitti.mmdet3d
+  results:
+  - task:
+      type: 3d-object-detection
+    dataset:
+      name: KITTI
+      type: kitti
+    metrics:
+    - name: mAP
+      type: map
+      value: 65.55
+    - name: AP/Pedestrian
+      type: map
+      value: 52.94
+    - name: AP/Cyclist
+      type: map
+      value: 66.32
+    - name: AP/Car
+      type: map
+      value: 77.39
+---
+
+# Model card for second.kitti.mmdet3d
+
+A SECOND 3D object detection model (sparse convolutional voxel detector). Trained on KITTI.
+
+## Model Details
+
+- **Model Type:** 3D object detection
+- **Model Stats:**
+  - Params (M): 5.3
+  - Input channels: 4
+  - Classes: 3
+  - Features: 512
+- **Dataset:** KITTI
+- **Metrics:** mAP 65.55, AP/Pedestrian 52.94, AP/Cyclist 66.32, AP/Car 77.39
+- **Paper:** [SECOND: Sparsely Embedded Convolutional Detection](https://www.mdpi.com/1424-8220/18/10/3337)
+- **Converted from:** [open-mmlab/mmdetection3d](https://github.com/open-mmlab/mmdetection3d) (Apache-2.0)
+- **Library:** [torch-pointcloud](https://github.com/arthurdjn/pytorch-pointcloud)
+
+## Install
+
+```bash
+pip install torch-pointcloud
+```
+
+This checkpoint also needs `spconv`, which needs a build matching your torch and CUDA: see the [installation guide](https://pytorch-pointcloud.org/latest/installation/).
+
+## Usage
+
+```python
+import torch
+import torch_pointcloud as tp
+from torch_pointcloud.utils.data import collate
+
+model, info = tp.create_model(
+    "second.kitti.mmdet3d",
+    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),
+    "intensity": torch.rand(num_points, 1),
+}
+data = info["transform"](sample)
+data = collate([data], batch_from="pos_voxel")
+data = {key: value.cuda() for key, value in data.items()}
+
+with torch.no_grad():
+    out = model(data["voxel"], data["pos_voxel"], data["voxel_num_points"], data["batch"])
+```
+
+## Feature extraction
+
+```python
+with torch.no_grad():
+    features = model.forward_features(
+        data["voxel"],
+        data["pos_voxel"],
+        data["voxel_num_points"],
+        data["batch"],
+    )  # 512 channels
+```
+
+## Citation
+
+```bibtex
+@article{yan2018second,
+  title   = {{SECOND}: Sparsely Embedded Convolutional Detection},
+  author  = {Yan, Yan and Mao, Yuxing and Li, Bo},
+  journal = {Sensors},
+  volume  = {18},
+  number  = {10},
+  pages   = {3337},
+  year    = {2018}
+}
+
+@inproceedings{geiger2012kitti,
+  title     = {Are we ready for Autonomous Driving? The {KITTI} Vision Benchmark Suite},
+  author    = {Geiger, Andreas and Lenz, Philip and Urtasun, Raquel},
+  booktitle = {CVPR},
+  year      = {2012}
+}
+
+@software{dujardin2026pytorchpointcloud,
+  author  = {Arthur Dujardin},
+  title   = {PyTorch PointCloud},
+  year    = {2026},
+  doi     = {10.5281/zenodo.22159632},
+  url     = {https://github.com/arthurdjn/pytorch-pointcloud},
+}
+```

config.json

@@ -0,0 +1,70 @@
+{
+  "library_name": "torch-pointcloud",
+  "name": "second.kitti.mmdet3d",
+  "task": "detection",
+  "hparams": {
+    "in_channels": 4,
+    "num_classes": 3,
+    "voxel_size": [
+      0.05,
+      0.05,
+      0.1
+    ],
+    "point_cloud_range": [
+      0.0,
+      -40.0,
+      -3.0,
+      70.4,
+      40.0,
+      1.0
+    ],
+    "anchor_sizes": [
+      [
+        0.8,
+        0.6,
+        1.73
+      ],
+      [
+        1.76,
+        0.6,
+        1.73
+      ],
+      [
+        3.9,
+        1.6,
+        1.56
+      ]
+    ],
+    "anchor_bottom_heights": [
+      -0.6,
+      -0.6,
+      -1.78
+    ],
+    "feature_map_stride": 8,
+    "dir_offset": -1.5707963267948966,
+    "norm_kwargs": {
+      "eps": 0.001,
+      "momentum": 0.01
+    }
+  },
+  "input_keys": [
+    "voxel",
+    "pos_voxel",
+    "voxel_num_points",
+    "batch_pos_voxel"
+  ],
+  "dataset": "kitti",
+  "metrics": {
+    "mAP": 65.55,
+    "AP/Pedestrian": 52.94,
+    "AP/Cyclist": 66.32,
+    "AP/Car": 77.39
+  },
+  "classes": [
+    "Pedestrian",
+    "Cyclist",
+    "Car"
+  ],
+  "author": "mmdet3d",
+  "license": "Apache-2.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c7171e9d9271b435a8d4ba002c85f0fa3b9eb29e0fd9425457b6be5947c3f51
+size 21346712