I have followed the generally-accepted methods in the tutorial, and created a set of positive and negative images to train the classifier against. The trouble is, that each time I run the command line script to create a .vec file, I get an error stating that creatsamples cannot read the text file containing the positive images data. I am at a complete loss as to what I'm doing wrong. Any ideas? I have tried with/without specifying directory address, I have tried fully-qualified addresses, and I have tried with/without specifying bg.txt address. I'm stuck. Nothing seems to work
