https://github.com/or4k2l/robust-vision

Production-ready framework for training robust computer vision models. Features multi-GPU support, EMA tracking, label smoothing, and comprehensive robustness evaluation across 4 noise types. Includes scalable TF.Data pipeline, automated testing, Docker support, and CLI tools. Install: pip install robust-vision

autonomous-driving computer-vision confidence-estimation deep-learning docker hardware-aware-ml implicit-regularization jax kitti-dataset machine-learning memristive-crossbar multi-gpu neuromorphic-computing neuromorphic-hardware noise-robustness pattern-recognition production-ml python robust-ml

Last synced: 22 Feb 2026