Deep-Feature-Flow icon indicating copy to clipboard operation
Deep-Feature-Flow copied to clipboard

Published 20 hours ago • verified publisher icon msracver

How to train our own data set, and it is not included in the 30 category.

Open weilanShi opened this issue 6 years ago • 2 comments

How to train our own dataset（one category）? and it is not included in the 30 category.How to make the annotations ?

weilanShi avatar Nov 16 '18 11:11 weilanShi

I have tried it in my own dataset,2 labels making by labelImg You should change the .xml file like the VID dataset.Then ,following the VID trainning steps.

Jessespace avatar Nov 16 '18 12:11 Jessespace

@Jessespace In the XML file of VID, occluded and generated at the bottom are different from VOC data sets. How are they generated? Do you need to change the source file of labelImg?

weilanShi avatar Nov 21 '18 13:11 weilanShi