-
Notifications
You must be signed in to change notification settings - Fork 120
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
Sometimes predict long, redundancy and repetitive chars, like 'parseqqqqqqqqqqqq'(ground truth is 'parseq') #56
Comments
Hello, please provide more details such as the model and weights used as well as the exact image you're using. |
I used the parseq trained on Chinese dataset, which contains about 6K chars, and used it for test dataset inference. |
Sorry but I can't help you since:
You might want to try increasing the number of decoder layers, or using a larger version of the model since the Chinese charset is much bigger than the Latin one. |
Thanks. I'll try your sollution. |
Does any chance you know the reason? Thank you for your talented work!
The text was updated successfully, but these errors were encountered: