-
Notifications
You must be signed in to change notification settings - Fork 3.1k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Vertical Characters support #170
Comments
No quick solution yet. I will keep this problem in mind for future development. |
Just come up with an idea, there's one possible way to solve this without messy with inner code. It is to set |
Thank you for your response. I tried several values for text_threshold, low_text, link_threshold all the way down to 0.05. No luck. I'll keep trying other stuff and report here if any breakthrough. |
Hi, I came across the same issue. It cannot deal with vertical text. Is it in your plan that the model will support the vertical text? When will it be released? |
@cesarandreslopez Hi, have you solved your problem? I have similar dataset as yours (container numbers). Maybe you found another solution? |
Hi did you find solution please ? |
@rkcosmos any solution for this? |
My particular use case would benefit from vertical, character by character detection. So something like the following would work
Response for the above is ['','']
The following example does work:
Response for this is perfect, ['TRIU', '8625018']
Any tips on how to get the first example to work? I don't mind if the list returned is a character at a time.
The text was updated successfully, but these errors were encountered: