StandardE2E Documentation¶
A framework for unified end-to-end autonomous driving datasets processing
StandardE2E provides a consistent interface for preprocessing, loading, and training with multimodal data from various end-to-end autonomous driving datasets. It standardizes the complex process of working with different dataset formats, allowing researchers to focus on model development rather than data engineering.
Key Features¶
✨ Unified Data Format and API - Single representation and consistent interface for all datasets
🔄 Multimodal Support - Camera, LiDAR, HD maps, trajectories, detections, driving command, etc
⚙️ Parametrizable Pipelines - Configure programmatically or via YAML files
🚀 PyTorch Native - Seamless DataLoader integration
📦 Extensible - Add new datasets, adapters, augmentations, etc.
Getting Started¶
Install from PyPI (the training environment: StandardE2E with PyTorch):
pip install standard-e2e
Or for development:
git clone https://github.com/stepankonev/StandardE2E.git
cd StandardE2E
uv sync --all-extras
Each dataset is preprocessed in its own isolated environment, with a pipeline run by
stepix, e.g.
uvx stepix run datasets/waymo_e2e/README.md. Refer to the Quickstart guide
for detailed usage.
Documentation¶
Getting Started
API Reference
Community & Support¶
Reach out to the maintainers via GitHub issues or Discord.
GitHub Issues: https://github.com/stepankonev/StandardE2E/issues
Discord: https://discord.gg/vJnQNcQGQ8