@arjen nice, curious to see how much that speed things up.
@hiemstra me too!
@hiemstra btw this made me want to try this myself: https://blog.usejournal.com/google-coral-edge-tpu-vs-nvidia-jetson-nano-a-quick-deep-dive-into-edgeai-performance-bc7860b8d87a
@hiemstra the idea was to add them to a spark cluster for fast inference in parallel using pretrained models (edge-tpu-s not suited for training). Use case in mind was Entity tagging.