@Draconic_NEO @div0 I can see the post from mastodon
@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.
@amazing_Yasuke @immibis @piracy @kariboka I heard that too. Might be some issues with 0.18 hopefully will be fixed soon
@immibis @piracy @amazing_Yasuke @kariboka Are you in this blacklist? https://lemmy.dbzer0.com/instances
@immibis @piracy @amazing_Yasuke @kariboka You don't need to start an instance to do that, you can do it anonymously as well. The whitelisting is to prepare against spammers. Anyway whoever doesn't want to use it, doesn't have to.
@Draconic_NEO @div0
After refresh