yizt crnn.pytorch issues

yizt / crnn.pytorch

crnn实现水平和垂直方向中文文字识别, 提供在3w多个中文字符训练的水平识别和垂直识别的预训练模型; 欢迎关注,试用和反馈问题... ...

Apache License 2.0

242 stars 52 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

demo.py直接预测出现中文乱码怎么解决

#33 965935916xu opened 3 months ago
0
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 nissansz opened 2 years ago
0
win10直接运行train.py 报错。微信nlanguage ForkingPickler(file, protocol).dump(obj) TypeError: cannot pickle 'Font' object

#31 nissansz opened 2 years ago
1
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 nissansz opened 2 years ago
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 nissansz opened 2 years ago
0
这个不可以转ONNX测试吧

#28 iwanggp opened 3 years ago
0
接着预训练模型接着训练一直是inf?

#27 RobertXiaobinW opened 3 years ago
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 RobertXiaobinW closed 3 years ago
0
number of dims don't match in permute

#25 RobertXiaobinW opened 3 years ago
1
印刷体纯数字识别效果不是太好，有解决办法吗？

#24 lttxws opened 3 years ago
0
单卡和多卡设置问题

#23 wutheringcoo opened 3 years ago
1
result output confidence

#22 wayneszq opened 3 years ago
0
training data generation

#21 wayneszq opened 3 years ago
3
请教*2

#20 kaixinbaba closed 4 years ago
2
请教

#19 kaixinbaba closed 4 years ago
15
训练数据怎么生成的？

#18 stephonjou opened 4 years ago
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 yangsuhui opened 4 years ago
7
下载目录无权限

#16 lmolhw5252 opened 4 years ago
2
用自己的字典替换你的all_word.txt文件，训练报错

#15 daixiangzi closed 4 years ago
11
问下，你验证集上，acc可以大概达到多少

#14 daixiangzi closed 4 years ago
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 zltgo opened 4 years ago
2
遇到一个问题，就是用 fontutils.py中对我的字体做并集

#12 daixiangzi closed 4 years ago
3
模型下载地址打不开

#11 YusyuanLiu closed 4 years ago
0
请问可以用什么函数判断繁体啊

#10 daixiangzi closed 4 years ago
2
请问有的字体绘制不出来是怎么解决的

#9 daixiangzi closed 4 years ago
4
请问下，你data下面的三个txt字典文件有啥区别

#8 daixiangzi closed 4 years ago
5
有比较过使用GRU和LSTM的效果吗

#7 deep-practice opened 4 years ago
1
How to obtain semantic information between texts by using the randomly generated data set for training？

#6 rockychan724 closed 4 years ago
0
如何使用自己的训练样本

#5 wuhuanlin08 closed 4 years ago
2
about trained model

#4 zcswdt opened 4 years ago
7
Can the horizontal and vertical text in a picture be detected at the same time？

#3 zengchan opened 4 years ago
2
what's your train envriment?

#2 JoyLuo opened 4 years ago
1
How could I use it for Latin characters?

#1 JoelUser opened 4 years ago
4