Zebra Aurora Vision Studio for Machine Vision Engineers

Aurora Vision deep learning tool-chain has been switched to a brand new training engine (re-implemented from scratch). The interfaces look as before, but under the hood there is wholly new thing.

•     It is now based on a client-server architecture; it may be run both locally and the cloud (coming later).
•     It has improved memory management and batch size moderation, fixing some “out of memory” errors on nVidia GPUs.
•     It supports new, better mechanisms for training data balancing, leading to better training results, especially on low quality datasets.
•     It supports nVidia RTX 40-series GPU devices.
•     Training is faster.
•     Training is more repeatable (same results each time we re-train from scratch).
•     New Python-based training API (coming soon).
•     Password locked API access.