-
Notifications
You must be signed in to change notification settings - Fork 188
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
"Is it possible to add my own text detector model trained from YOLO?" #634
Comments
Compare metrics with CTD and provide them here. If it's better, I'll add it |
"I’m not sure if these are reliable enough with the model. The new model is marked with red boxes, and the initial model with blue boxes."
|
#508 |
"Wow, that's really awesome! I really want this model to be updated. It will significantly improve performance. I hope to use it very soon." |
I mainly trained on full-color artist/illustrator CG images in this category. |
"I see the great effort put into this development, which is something that should be supported. I just hope the developer can integrate this model into the program. |
Currently, the training is not complete yet, so I cannot share it at the moment. You should be able to tell from the two random images I shared. There are still issues where the rectangular boxes don't fully encompass the text - I'm still fine-tuning it. |
@lhj5426 @KorawitP |
yolov11 yolo11x |
还有obb 旋转矩形的目标检测模型 |
|
No description provided.
The text was updated successfully, but these errors were encountered: