Closed Varat7v2 closed 2 years ago
I'm getting requests on how to train a model that fits usecase XY quite often. However, I don't have the time to do any personal consulting on these things.
@githubharald Thank you for your reply. I will have a look on that. Thank you for your time.
@githubharald Hello. I am trying to run SimpleHTR on handwritten text (involving both alphabetical and numeric characters along with other scientific symbols like ohm, omega, meu, pi etc.) Alphabetical characters are detected properly, but not able to identify numbers and symbols properly. What can I do improve the model accuracy on all types of character. I even looked for handwritten numbers datasets, but I didn't get other than MNIST datasets. Can you please suggest what can I do to improve the model accuracy on the problem I am working please?
Thank you for your time.