search

Tianxiaomo / Cultural_Inheritance-Recognizing_Chinese_Calligraphy_in_Multiple_Scenarios

文化传承—汉字书法多场景识别比赛
https://www.datafountain.cn/competitions/334/details
109 stars 21 forks source link

some files are not in thies repo #4

Open Teslaxhub opened 5 years ago

Teslaxhub commented 5 years ago

Hi, thanks for your sharing!

I have joined the competition, and learned a lot from your repo.

But I have found that there are some files do not in the CRNN part , can you complete the supplementary materials？

  1. from data_generator.generator import gen_data
  2. char_path = './util/char_gb2312.txt'
  3. ./fonts/ thank you very much！
Pythpnone commented 5 years ago

Hi, thanks for your sharing!

I joined the competition, too. Due to the part of CRNN is not complete, so i copy the cfg.py and data_generator.py in the EAST part. When i try to run the code of CRNN, some questions are as follow.

In addition to the questions mentioned by Teslaxub, there are also several questions in the CRNN part.

1.valfname = 'val%s.txt' % train_task_id 2.trainfname = 'train%s.txt' % train_task_id How can i find it? 3.do you sure 'img, text = gen_data(cfg.data_para)' in the part of CRNN's dataset.py?

Finally, i hope your can share another edition that there has code comments. Thank you very much!

lxx2844 commented 5 years ago

谢谢分享！ 能否请提供以下几个文件 from data_generator.generator import gen_data char_path = './util/char_gb2312.txt' ./fonts/

谢谢