rmsalinas/DBow3

Problem with the size of vocabulary

joegeng opened this issue · 3 comments

Hi, I am trying to use SIFT to create vocabulary what I need. There is a problem, when I use the dataset (NYU DataSet), the size of vocabulary result is 3KB, but when I use the one-tenth of the dataset, the size of result is 968KB. This made me very confused. Sincerely hope for your reply, Thank you!

I first use "create_voc_step0.cpp" to generate all feature vector in *.txt, then use the "create_voc_step1.cpp" to load the txt and create the vocabulary.

Keep the default parameters of k and L, I get my result

Hi. I moved long time ago to fbow. Does it not fits your needs?