PhotoPrism uses TensorFlow for the image classification / ML stuff (to add labels to your images), but it can be completely disabled via a flag (or toggle under advanced settings) before you begin indexing if you don't need it.
PhotoPrism's ML object detection is no doubt not as powerful as Google's, but it seems to work pretty well based on the demo, and I know the devs are working on improving it frequently.
I have just about finished setting this up on my own home lab- the documentation isn't as comprehensive as I would like but it has ingested my 52GB of photos and is serving them up nicely!
Splittable (Seed) | London (Shoreditch), UK | Full-time | ONSITE
Splittable is a web, iOS and Android app helping the world's growing population of young renters manage their shared expenses. https://www.splittable.co/
Built at the Open Data Institute in 2014, the company is run by young property enthusiasts with a collective passion for improving the lives of householders.
We're looking for a Junior Full Stack Developer to join our small but growing team, with some experience in Rails and HTML/CSS, perhaps a bit of iOS (Swift2) or Angular + Ionic Framework as a bonus.
PhotoPrism's ML object detection is no doubt not as powerful as Google's, but it seems to work pretty well based on the demo, and I know the devs are working on improving it frequently.