This forum is disabled, please visit https://forum.opencv.org
 | 1 | initial version |
won't work. though your PxlbleDbl are double, they don't form a "metric space"
| | 2 | No.2 Revision |
won't work. though your yolur PxlbleDbl are double, they don't form a "metric space"
(same problem with "hex" like 0xa0dde2f3, already -- you can't do proper maths on it)
finding a nice "embedding" for your classification task is indeed a hard problem, that's why nowadays mostly convolutional nns are used, which learn the embedding in an "end-to-end" fashion.
| | 3 | No.3 Revision |
your idea won't work. work.
though yolur PxlbleDbl are double, they don't form a "metric space"
(same problem with "hex" like 0xa0dde2f3, already -- you can't do proper maths on it)
finding a nice "embedding" for your classification task is indeed a hard problem, that's why nowadays mostly convolutional nns are used, which learn the embedding in an "end-to-end" fashion.
| | 4 | No.4 Revision |
your idea won't work.
though yolur PxlbleDbl are double, they don't form a "metric space"
(same problem with "hex" like 0xa0dde2f3, already -- you can't do proper maths on it)it, as long as you keep it in a single number)
finding a nice "embedding" for your classification task is indeed a hard problem, that's why nowadays mostly convolutional nns are used, which learn the embedding in an "end-to-end" fashion.
