Yolov5: Test Bounding box in Custom Data is shifted!

[chokyungjin]

Hi. I'm sooo glad to meet your repo! But I have a issue,I trained with My custom data.
And now I'm trying to test it and I found a problem.
My Test Result All Bounding Boxes are shifted! I don't know why this is happening!

I look forward to a answer. Thank you!

[github-actions[bot]]

Hello @chokyungjin, 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.

[Ownmarc]

Your labels are probably wrong.. Start by checking the images created in runs/expN/ to confirm your labels are correct. If they are all shifted there too, it means that your ground truth labels are all shifted or you have a problem in you label conversion script.

[chokyungjin]

Thank you!! One more Question..
How Can i Check my annotation data in my Image?
I don't know how to check the annotations after adjusting them to the 0-1 scale coordinates.

[Ownmarc]

After starting a training, look in the folder that gets created "runs/exp1/ " there will be 4 images that show the batches with their labels on it. Make sure they are correct

[chokyungjin]

Thank you again!

[glenn-jocher]

Yes, like @Ownmarc said you want to check your train and test jpgs here for proper labels. If the boxes are incorrect here it means your labels are not correct.

[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.