#184184th of 214 in ML frameworks and librariesFor science, health and research, robotics
nuscenes-devkit
Python devkit for loading and evaluating the nuScenes and nuImages driving datasets
Documentation ↗
(opens in a new tab)Website ↗
(opens in a new tab)Repository on GitHub ↗
(opens in a new tab)
- Stars
- 2.8k
- License
- custom license
- Last commit
- Aug 2026
- Last release
- Apr 2021
- Language
- Python
Missed the latest GitHub check; these facts may be older.
Overview
Python SDK for the nuScenes and nuImages autonomous-driving datasets from Motional. It provides database classes, lidar/radar/camera tooling, map expansion APIs, and evaluation code for detection, tracking, prediction, lidarseg and panoptic tasks. Datasets are downloaded separately after account registration and acceptance of the Terms of Use.
Who it is for: Autonomous driving researchers working with nuScenes or nuImages data
Strengths
- Covers detection, tracking, prediction, lidarseg and panoptic evaluation code in one package
- Installable with pip install nuscenes-devkit; tested on Python 3.9 and 3.12
- Jupyter tutorials for nuScenes, nuImages, maps, CAN bus, prediction and lidarseg/panoptic
- Map expansion API with 11 semantic layers and lane connectivity for prediction
Weaknesses
- Datasets require account registration and Terms of Use acceptance; they are not bundled
- nuScenes needs all archives downloaded for the devkit to work
- Last tagged release is from 2021 per repo metadata, though the README lists v1.2.0
- License is reported as NOASSERTION, so terms need manual checking
What it needs
- no GPU
- Needs nuScenes or nuImages dataset download, Jupyter (for tutorials)
Also in ML frameworks and libraries
See all 214| Rank | Project | Score |
|---|---|---|
| 1 | transformersPython library defining open models for text, vision, audio and multimodal tasks | 94 out of 100 |
| 2 | ultralyticsPython library and CLI for training and running YOLO vision models | 94 out of 100 |
| 3 | pytorch-image-modelsPyTorch library of image models, pretrained weights and training scripts | 94 out of 100 |
| #4 | pytorchPython tensor library with GPU support and tape-based autograd | 93 out of 100 |
| #5 | supervisionPython toolkit for loading, annotating and counting computer vision detections | 92 out of 100 |