c++ - DLib : train_shape_predictor_ex.cpp -


i trying train shape predictor of dlib executing train_dlib_shape_predictor_ex.cpp on helen dataset described in code, place test images in face folder in current directory of shape predictor. when run code throws following exception:

c:\train_shape_predictor_ex\release>train_shape_predictor_ex test  exception thrown! error: unable open test/training_with_face_landmarks.xml reading. 

as no training_with_face_landmarks.xml , testing_with_face_landmarks.xml files available in helen dataset on following page : link

there folder named annotation contains 1 text file containing 194 landmark points location each , every image in dataset. how convert file training_with_face_landmarks.xml.

open 'training_with_face_landmarks.xml' file , observe structure.

now, ask yourself:

  1. what changes between files? (hint: point data)
  2. what stays same? (hint: generic 'boiler plate' top , tail)

open helen data - ask same again...

your task parse data helen set temporary data-structure/variable , write file required top , tail. it'll kludge , annoying write loops inside loops inside loops etc. you'll there.

'c++ i/o streams' search string started.


Comments

Popular posts from this blog

Ansible - ERROR! the field 'hosts' is required but was not set -

customize file_field button ruby on rails -

SoapUI on windows 10 - high DPI/4K scaling issue -