This forum is disabled, please visit https://forum.opencv.org
 | 1 | initial version |
for 7 billions of images ( and probably a billion of labels ), you might want to run several (lbp-like) facerecognizers in parallel, and do a nn-search again on their results.
sure, you can hack it, to have a vector<guid> instead of a vector<int> as your labels, but a (local) lookup-table int-label <-> GUID will work as well without modding it.
| | 2 | No.2 Revision |
for 7 billions of images ( and probably a billion of labels ), you might want to run several (lbp-like) facerecognizers in parallel, and do a nn-search again on their results.
sure, you can hack it, to have a vector<guid> vector<GUID> instead of a vector<int> vector<int> as your labels, but a (local) lookup-table int-label int_label <-> GUID will work as well without modding it.
