Template

Quick Links

Paper

Download

Code

License

Available splits

Available Modalities

Name

Available

Description

Ego Vehicle

✓ / (✓) / X

…, see EgoStateSE3.

Map

✓ / (✓) / X

…, see MapAPI.

Bounding Boxes

✓ / (✓) / X

…, see BoxDetectionWrapper.

Traffic Lights

✓ / (✓) / X

…, see TrafficLightDetectionWrapper.

Pinhole Cameras

✓ / (✓) / X

…, see PinholeCamera.

Fisheye Cameras

✓ / (✓) / X

…, see FisheyeCamera.

LiDARs

✓ / (✓) / X

…, see LiDAR.

Download

The 123D conversion expects the following directory structure:

Installation

For Template, additional installation that are included as optional dependencies in py123d are required. You can install them via:

pip install py123d[template]

Or if you are installing from source:

pip install -e .[template]

Dataset Specific

Box Detection Labels
class py123d.conversion.registry.DefaultBoxDetectionLabel[source]

Default box detection labels used in 123D. Common labels across datasets.

EGO = 0
VEHICLE = 1
TRAIN = 2
BICYCLE = 3
PERSON = 4
ANIMAL = 5
TRAFFIC_SIGN = 6
TRAFFIC_CONE = 7
TRAFFIC_LIGHT = 8
BARRIER = 9
GENERIC_OBJECT = 10
to_default()[source]

Inherited, see superclass.

Return type:

DefaultBoxDetectionLabel

LiDAR Index
class py123d.conversion.registry.DefaultLiDARIndex[source]

Default LiDAR indices for XYZ point clouds.

X = 0
Y = 1
Z = 2

Dataset Issues

[Document any known issues, limitations, or considerations when using this dataset]

  • Issue 1: Description

  • Issue 2: Description

  • Issue 3: Description

Citation

If you use Template in your research, please cite:

@article{AuthorYearConference,
  title={Template: Some Dataset for Autonomous Driving},
  author={},
  booktitle={},
  year={}
}