Yolov5: Training images without objects

[ZhengfengLee]

❔Question

hi, in my custom dataset, i have some images without objects, thus there are no annotations relate to those images. should i need to make an empty '.txt' label file to refer to it?

Additional context

[github-actions[bot]]

Hello @ZhengfengLee, thank you for your interest in our work! Please visit our Custom Training Tutorial to get started, and see our Jupyter Notebook , Docker Image, and Google Cloud Quickstart Guide for example environments.

If this is a bug report, please provide screenshots and minimum viable code to reproduce your issue, otherwise we can not help you.

If this is a custom model or data training question, please note Ultralytics does not provide free personal support. As a leader in vision ML and AI, we do offer professional consulting, from simple expert advice up to delivery of fully customized, end-to-end production solutions for our clients, such as:

• Cloud-based AI systems operating on hundreds of HD video streams in realtime.
• Edge AI integrated into custom iOS and Android apps for realtime 30 FPS video inference.
• Custom data training, hyperparameter evolution, and model exportation to any destination.

For more information please visit https://www.ultralytics.com.

[glenn-jocher]

@ZhengfengLee background images do not require label files.

[ZhengfengLee]

@ZhengfengLee background images do not require label files.

I see. Thank you for your answer

[ZhengfengLee]

@ZhengfengLee background images do not require label files.

I still have a question: background images dont compute any loss, right?

[glenn-jocher]

@glenn-jocher all images are treated equally in the loss function. If they have no objects, they have no objects, but they are still processed as any other image and evaluate objectness loss at each anchor.

[ZhengfengLee]

@glenn-jocher all images are treated equally in the loss function. If they have no objects, they have no objects, but they are still processed as any other image and evaluate objectness loss at each anchor.

thanks

[github-actions[bot]]

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.