James

The new `CustomDetectionModel` is significantly more robust and fixes several bugs with the old `autodistill-sam-clip` model`. I know it is confusing to have two things with the same name, but...

@csverma610 Have you solved the problem? If so, can we close this issue?

I am going to close this issue, but we can re-open it if further assistance is required.

I have responded to your feedback.

Hello! Would you be able to submit a PR with your contribution? We have [guidance on how to contribute to Autodistill](https://github.com/autodistill/autodistill/blob/main/CONTRIBUTING.md) that you can use to get started!

Hello! Thank you for creating this Issue. Is it possible for you to share an example image from your dataset that raised the `Corrupt JPEG data` warning?

@ashaheedq Do you still require assistance? If not, can we close this issue?

We will be releasing a new version of supervision in the next week that will solve this problem.

This problem has since been fixed in supervision, so I am closing this issue. Thank you!

Thank you for leaving this Issue! Can I confirm you installed the `autodistill-yolov8` package? We have previously run into breaking changes with the `ultralytics` package so we pinned the version...