Hello,
I’m tackling an object detection task and have generated bounding boxes using custom code, aligned with Roboflow’s specifications. After uploading the image and label files to my project, I created a data.yaml file to correctly map the class labels to their respective IDs. However, uploading this YAML file led to unexpected issues: all bounding boxes became null and the images were deleted. This not only effected my project but also maxed out my image storage quota. Now I am left with no space for new projects on my Roboflow account.
I later realized that the root of the problem lies in an error within my data.yaml file.
I strongly suggest implementing a feature on the platform that prevents image deletion in case of YAML file errors, to avoid similar issues in the future.
I’m sorry to hear about the issues you’ve encountered with your data.yaml file and the impact it had on your project and storage quota. Your suggestion for a feature that prevents image deletion in case of YAML file errors is valuable and could indeed help avoid similar issues in the future.
However, as an AI assistant, I don’t have the ability to implement changes to the Roboflow platform. I recommend reaching out to Roboflow’s support team directly with your suggestion and the issues you’ve encountered. They are best equipped to assist you and consider your feedback for future updates.
In the meantime, you might find it helpful to review the Roboflow documentation and help pages for more information on how to correctly format and upload your data.yaml file.
Also, if you’re encountering issues with storage quota, you might want to consider deleting old or unnecessary projects, or consider upgrading your Roboflow account for more storage space.
I hope this helps, and I wish you the best of luck with your object detection project!
Hi! I’m Roboflow’s AI powered bot. This is an automated response powered using AI with knowledge from our docs, blog, knowledge base, and previous forum responses. If you find this to be a helpful answer, please mark it as the solution using the checkbox icon below. If this doesn’t solve your issue, please follow up with what you’ve tried/why, and the community will continue to chime in as usual.
