@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
db0
joined 2 years ago
@Val oh that's a good one!