how to support it for ICDAR2017

Masao-Taketani / FOTS_OCR

TensorFlow Implementation of FOTS, Fast Oriented Text Spotting with a Unified Network.

GNU General Public License v3.0

56 stars 15 forks source link

how to support it for ICDAR2017 #9

Closed wang-lei-cn closed 3 years ago

wang-lei-cn commented 3 years ago

Hi, I like your project and I trained it for ICDAR2017, but I met a problem.

reading file error: data\ICDAR17MLT\gts\gt_ICDAR17MLT_img_199.txt ثوار substring not found

ICDAR2017 DATA contains multi languages, such as Arabic, Korean. I know maybe I should modify the config.py, but I‘m not clear about how to do it. Could you please give me any suggestion? Thanks a lot.

Masao-Taketani commented 3 years ago

Hi, @wang-lei-cn Thank you for your interest for this project. Sorry that I just noticed your question. Yes, as you thought, for your case I think you just need to put every letter that you want to recognize in CHAR_VECTOR variable which is defined in config.py. Please try that.