Я пытался запустить train_object_detector.cpp в библиотеке dlib, чтобы обучить его обнаружению пешеходов. Я использую набор данных INRIA, и когда я пытался его использовать, возникло исключение:
exception thrown!
Error! An impossible set of object boxes was given for training. All
the boxes
need to have a similar aspect ratio and also not be smaller than about
1600
pixels in area. The following images contain invalid boxes:
crop001002.png
crop001027.png
crop001038.png
crop001160.png
crop001612.png
crop001709.png
Try the -h option for more information.
когда я удалил эти фотографии, он запустился и загрузил все фотографии, но затем было выбрано другое исключение
exception thrown!
An impossible set of object labels was detected. This is happening
because none
of the object locations checked by the supplied image scanner is a
close enough
match to one of the truth boxes. To resolve this you need to either
lower the
match_eps or adjust the settings of the image scanner so that it hits
this truth box. Or you could adjust the offending truth rectangle so
it can be matched by the current image scanner. Also, if you are using
the scan_image_pyramid object then you could try using a finer image
pyramid or adding more detection templates. E.g. if one of your
existing detection templates has a matching width/height ratio and
smaller area than the offending rectangle then a finer image pyramid
would probably help.
пожалуйста, помогите мне справиться с этим.
