Tensorflow_SceneText_Oriented_Box_Predictor icon indicating copy to clipboard operation
Tensorflow_SceneText_Oriented_Box_Predictor copied to clipboard

Published 20 hours ago • verified publisher icon dafanghe

What type of annotations to use

Open ajinkya933 opened this issue 6 years ago • 1 comments

@dafanghe What annotations did you use to train your dataset.

  1. Did you draw boxes for multiple text lines in images.
  2. Or did you draw boxes like its done in ctpn (https://github.com/ajinkya933/text-detection-ctpn)

I want to know which method to follow when annotating text?

ajinkya933 avatar Aug 26 '19 12:08 ajinkya933

@ajinkya could you please tell me how to directly evalute using pretrained model on custom images.

balajihosur avatar Nov 03 '21 06:11 balajihosur