yizt/crnn.pytorch

Issues

• 字符集中有的字符例如\u3000在python下没法显示报错，怎么去掉？微信nlanguage

  #32 opened 2 years ago by nissansz
  0

• win10直接运行train.py 报错。微信nlanguage ForkingPickler(file, protocol).dump(obj) TypeError: cannot pickle 'Font' object

  #31 opened 2 years ago by nissansz
  1

• 用自己的字典替换你的all_word.txt文件，训练报错

  #15 opened 4 years ago by daixiangzi
  11

• 我在all words.txt里放了10个汉字，尝试运行generator.py，报了以下错误，怎么解决？微信nlanguage Traceback (most recent call last): File "F:/pycharm2020.2/crnn.pytorch_generator/generator.py", line 227, in <module> test_image_gen('horizontal') File "F:/pycharm2020.2/crnn.pytorch_generator/generator.py", line 207, in test_image_gen im, indices, target_len = gen.gen_image() File "F:/pycharm2020.2/crnn.pytorch_generator/generator.py", line 158, in gen_image text = np.random.choice(FONT_CHARS_DICT[font_path], target_len) File "mtrand.pyx", line 908, in numpy.random.mtrand.RandomState.choice ValueError: 'a' cannot be empty unless no samples are taken

  #30 opened 2 years ago by nissansz
  0

• 我尝试用cpu训练。报错了，怎么解决？微信nlanguage 。 py -3 train.py --direction horizontal

  #29 opened 2 years ago by nissansz
  0

• 这个不可以转ONNX测试吧

  #28 opened 3 years ago by iwanggp
  0

• 接着预训练模型接着训练一直是inf?

  #27 opened 3 years ago by RobertXiaobinW
  3

• 是否可以修改预训练模型的输出层后进行迁移学习呢？

  #26 opened 3 years ago by RobertXiaobinW
  0

• number of dims don't match in permute

  #25 opened 3 years ago by RobertXiaobinW
  1

• 印刷体纯数字识别效果不是太好，有解决办法吗？

  #24 opened 3 years ago by lttxws
  0

• 单卡和多卡设置问题

  #23 opened 4 years ago by wutheringcoo
  1

• training data generation

  #21 opened 4 years ago by wayneszq
  3

• result output confidence

  #22 opened 4 years ago by wayneszq
  0

• 请教*2

  #20 opened 4 years ago by kaixinbaba
  2

• 请教

  #19 opened 4 years ago by kaixinbaba
  15

• 训练数据怎么生成的？

  #18 opened 4 years ago by stephonjou
  11

• hi，thank you for the great codes. But I have met some problems. I just download the code, and run using distribute training mode,

  #17 opened 4 years ago by yangsuhui
  7

•  下载目录无权限

  #16 opened 4 years ago by lmolhw5252
  2

• How could I use it for Latin characters?

  #1 opened 4 years ago by JoelUser
  4

• 问下，你验证集上，acc可以大概达到多少

  #14 opened 4 years ago by daixiangzi
  4

• 请教一下如何训练自己的数据集，数据格式以及存放目录怎么配置

  #13 opened 4 years ago by zltgo
  2

• 遇到一个问题，就是用 fontutils.py中对我的字体做并集

  #12 opened 4 years ago by daixiangzi
  3

• 请问可以用什么函数判断繁体啊

  #10 opened 4 years ago by daixiangzi
  2

• 模型下载地址打不开

  #11 opened 4 years ago by YusyuanLiu
  0

• 请问下，你data下面的三个txt字典文件有啥区别

  #8 opened 4 years ago by daixiangzi
  5

• 请问有的字体绘制不出来是怎么解决的

  #9 opened 4 years ago by daixiangzi
  4

• 有比较过使用GRU和LSTM的效果吗

  #7 opened 4 years ago by deep-practice
  1

• How to obtain semantic information between texts by using the randomly generated data set for training？

  #6 opened 4 years ago by rockychan724
  0

• 如何使用自己的训练样本

  #5 opened 4 years ago by wuhuanlin08
  2

• about trained model

  #4 opened 4 years ago by zcswdt
  7

• Can the horizontal and vertical text in a picture be detected at the same time？

  #3 opened 4 years ago by zengchan
  2

• what's your train envriment?

  #2 opened 4 years ago by JoyLuo
  1