nutonomy/nuscenes-devkit

Health v2 · maintenance only

Flags: no_license

Adoption not part of the score

2796 stars · 714 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

The official Python devkit for the nuScenes dataset, a large-scale autonomous driving dataset from Motional. It provides dataset loading, visualization, and evaluation code for detection, tracking, segmentation, prediction, and map-expansion tasks.

Use cases

• load and explore nuScenes sensor data in Python
• evaluate 3D object detection results on nuScenes
• visualize lidar point clouds with camera images
• run nuScenes tracking or segmentation evaluation metrics
• work with nuImages annotations
• query nuScenes map expansion data

When to choose

• you are working with the nuScenes or nuImages datasets
• you need official evaluation code for nuScenes challenges
• you want to visualize autonomous driving sensor data

When to avoid

• you need a general-purpose lidar or dataset toolkit unrelated to nuScenes
• you want a training framework rather than a dataset devkit

Facets

library · maturity stable

data-science machine-learning computer-vision data-visualization sdk autonomous-vehicles computer-vision machine-learning python nuscenes dataset-devkit lidar 3d-object-detection autonomous-driving evaluation-metrics datasets linux macos

Member repositories

For agents

markdown · JSON · MCP: product_card(name="nutonomy/nuscenes-devkit")