Autodistill execution error

[sa136199]

Search before asking

• I have searched the Autodistill issues and found no similar feature requests.

Question

When I use Autodistill on Roboflow to label images
After the marking is completed, the marked pictures will be automatically moved from Unassigned to Dataset
But in recent days, it cannot be executed correctly
The error message is as shown below
Is there a solution or do I need to wait for the system to repair automatically?
Thanks!

Additional

No response

[nguyenthekhoig7]

Hi, same here. I got the same problem, and I found a walkaround to get over it (not sure if it will work to submit as a PR).

You can open the yolo.py file (click on the blue link to the file), change the line that directly causing this error from
for xyxy, mask, _, class_id, _ in detections:

to

for xyxy, mask, _, class_id, _ , _ in detections: (add one placeholder)

The reason for this walkaround is that when I printed out the detections variable and turned out it had 6 var instead of 5, so I added one.

Hope this helps.

[nguyenthekhoig7]

Since the file I made the change to is in the supervision folder, not autodistill, I am not sure if I can submit a PR for this. I hope that there's another way for this rather than manually fixing like the way I did.

[sa136199]

Thank you
This method solved my problem
I also hope there can be a fundamental solution
Anyway thank you very much

[SkalskiP]

Hi @nguyenthekhoig7 and @sa136199, This problem is related to a bug in the current version of supervision. All you must do is pip install supervision==0.19.0rc2 in your Python environment. This will update supervision and the bug should go away.

[sa136199]

Thank you for providing a more convenient solution

[capjamesg]

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

[capjamesg]

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