search

Bartzi / see

Code for the AAAI 2018 publication "SEE: Towards Semi-Supervised End-to-End Scene Text Recognition"
GNU General Public License v3.0
574 stars 147 forks source link

Explanation of "ctc_char_map.json" #14

Closed gengkunling closed 6 years ago

gengkunling commented 6 years ago

In the file "ctc_char_map.json", I saw a dictionary like this in below, could you explain what is means?

Another questions is how many characters does the current text recognition model supports? Is it only supports ascii characters? Thanks!

{"0": 9250, "1": 48, "2": 49, "3": 50, "4": 51, "5": 52, "6": 53, "7": 54, "8": 55, "9": 56, "10": 57, "11": 97, "12": 98, "13": 99, ... }

rohit12 commented 6 years ago

You can reference this comment. Christian has explained what exactly is the reason behind the char_map and also how to extend it for other datasets.

gengkunling commented 6 years ago

Thanks! It's very clear now.

Bartzi commented 6 years ago

@rohit12 thanks for your help =)