Model card for tr3d.sunrgbd.mmdet3d

A TR3D 3D object detection model (fast fully convolutional sparse voxel detector). Trained on SUN RGB-D.

Model Details

Model Type: 3D object detection
Model Stats:
- Params (M): 14.7
- Input channels: 3
- Classes: 10
- Features: 128
Dataset: SUN RGB-D
Metrics: mAP@0.25 66.67, mAP@0.5 50.37
Paper: TR3D: Towards Real-Time Indoor 3D Object Detection
Converted from: open-mmlab/mmdetection3d (Apache-2.0)
Library: torch-pointcloud

Install

pip install torch-pointcloud

This checkpoint also needs spconv, which needs a build matching your torch and CUDA: see the installation guide.

Usage

import torch
import torch_pointcloud as tp
from torch_pointcloud.utils.data import collate

model, info = tp.create_model(
    "tr3d.sunrgbd.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),
    "color": torch.rand(num_points, 3) * 255,
    "normal": torch.randn(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])
data = {key: value.cuda() for key, value in data.items()}

with torch.no_grad():
    out = model(data.get("x"), data["pos"], data["batch"])

Feature extraction

with torch.no_grad():
    features = model.forward_features(data.get("x"), data["pos"], data["batch"])  # 128 channels

Citation