Startup founder – decided to leave VC and start my own company EduDo. We're building a video-based discussions platform allowing folks to share insights and opinions in an interactive an engaging way. We've already released an MVP, became a Mobile App of the year by Product Hunt, raised $500k, came through a pivot, and now are soft launching the new concept;. Source: over 2 years ago

Reminds me of Machine Box (http://machinebox.io). Source: over 1 year ago

Thank you :) I did that to teach dog’s breed to an AI. If you don’t know machine box yet : Https://machinebox.io It seems really cool and easy to use. Source: almost 2 years ago

I think you should go 5 Pi X 5 Jetson Nano’s I haven’t seen many people offloading the Nano’s GPU functionality for ML similar to this Serverless style of product. https://machinebox.io/. Source: almost 3 years ago

For face recognition - CompreFace. Disclaimer - I created it, as an alternative you can use MachineBox, but it's not open source and has limits. Also, I think, you will use some software to control the system, e.g. Frigate or Home Assistant, I think this repository can be useful for you. Source: almost 3 years ago

If you have a really simple application, you can just save the encodings into the files. If not - it's better to use a database. SQL is ok. But for the best results, I would suggest using milvus.io, as it was created for saving vectors and finding the distances (I haven't tried it, though). If your final goal is not to learn face recognition basics, you can just use free ready to use solutions like CompreFace... Source: almost 3 years ago