@fmstrat each tensor is small. The problem is when you have millions of them and you have to compare each image to each. You can't index this. It has to be one by one. And you still need to covert the new image to tensors as well,which still needs gpu. I just don't see anything useful here. The current system would be faster.
@coolcat1711@db0@lemmy.dbzer0.com I hope it won't work out for them as they expect. Investors are not (always) stupid and there's plenty of bad news about the impact of this decision.
