VOC.yaml

[ZCzzzzzz]

Search before asking

• [X] I have searched the YOLOv5 issues and discussions and found no similar questions.

Question

Hello, I am now encountering a problem, the size of each picture in my dataset is too large, the training time is too long, and I found that the accuracy and recall rate of epoch is less than 10 can reach more than 90%, the speed of fitting is too fast, I want to ask is there any way to automatically modify the label file while modifying the image size of the dataset, without the need to label the modified picture again?

Additional

No response

[glenn-jocher]

@ZCzzzzzz hello,

One way to modify the label file while changing the image size of the dataset is by using a tool like LabelImg. With LabelImg, you can modify the image size and then save the annotations in YOLO format. Another option is to use a script to modify the annotations automatically based on the new image size.

Regarding the training time, you can try reducing the image size to further reduce the training time while maintaining a good accuracy and recall rate.

Hope this helps! Let us know if you have any further questions.

Best, Glenn Jocher, Ultralytics team

[ZCzzzzzz]

Hello, are you saying that I need to reproduce the annotation of the new image using labelimg?

[glenn-jocher]

@ZCzzzzzz hi there,

If you are planning on modifying the image size of your dataset and you want to preserve the labels of the objects in the images, you will need to update the annotations of your dataset to reflect the new image size.

One way to do this is to use a tool like LabelImg to manually modify the annotations for each image in your dataset. Another option is to use a script to automatically update the annotations based on the new image size.

I hope that helps! If you have any further questions, please don't hesitate to ask.

Thanks, Glenn Jocher, Ultralytics team.

[github-actions[bot]]

👋 Hello there! We wanted to give you a friendly reminder that this issue has not had any recent activity and may be closed soon, but don't worry - you can always reopen it if needed. If you still have any questions or concerns, please feel free to let us know how we can help.

For additional resources and information, please see the links below:

• Docs: https://docs.ultralytics.com
• HUB: https://hub.ultralytics.com
• Community: https://community.ultralytics.com

Feel free to inform us of any other issues you discover or feature requests that come to mind in the future. Pull Requests (PRs) are also always welcomed!

Thank you for your contributions to YOLO 🚀 and Vision AI ⭐