New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Detections.__getitem__ not supported for index of type <class 'numpy.ndarray'>. #42
Comments
Hello there, thank you for opening an Issue ! 🙏🏻 The team was notified and they will get back to you asap. |
I have used the same code you provided. |
Sorry for the inconvenience. |
@arami1 could you give me a link to your Roboflow project? |
Hi, @arami1! 👋🏻 Thanks a lot for your patience. I spent a bit of time debugging. And I know what is going on. Quick fixRemove Explanation2 training epochs are not enough for the model to learn detecting objects from your dataset. As a result, your model is not detecting any object on the image. |
I just merged the fix into the |
ok thank you |
I have tried training for 50 epochs but got the same error |
This might be because this training does not utilize dataset augmentations, so the model learns quite slowly. As for the bug, it should be eliminated with the release. It should be done in the next hour or so. |
The fix was just released under I'm closing the issue. Feel free to reopen if you'd still experience any issues. |
but I don't want to use data augmentation techniques. |
Your problem is not related to the dataset format.
|
ok, thank you for your guidance. means a lot |
No worries ;) Feel free to ask more questions |
Search before asking
Bug
this is a link to my notebook, please take a look
https://colab.research.google.com/drive/1nFgpu2bTKLDuFfxeSW6yzzHzIkKtQi9w?authuser=1#scrollTo=jbzTzHJW22up
I downloaded the dataset after doing annotations from roboflow and then uploaded the zip file to google drive.
Environment
torch: 1.13
cuda: cu116
roboflow: 0.2.34
supervision: 0.3.0
transformers: 4.26.1
Minimal Reproducible Example
No response
Additional
No response
Are you willing to submit a PR?
The text was updated successfully, but these errors were encountered: