Dataset not in Roboflow

[Shouq95]

Search before asking

• I have searched the Roboflow Notebooks issues and found no similar bug report.

Description

Hello,
I am very new to this and wanted to use my own dataset with masks for this code. I failed to modify the code to accept my own folders instead of a roboflow dataset. Has anyone tried to do this? Any advice or code suggestions would be appretiated.
Thank you!

Additional

No response

Are you willing to submit a PR?

• Yes I'd like to help by submitting a PR!

[github-actions]

👋 Hello @Shouq95, thank you for leaving an issue on Roboflow Notebooks.

🐞 Bug reports

If you are filing a bug report, please be as detailed as possible. This will help us more easily diagnose and resolve the problem you are facing. To learn more about contributing, check out our Contributing Guidelines.

If you require support with custom code that is not part of Roboflow Notebooks, please reach out on the Roboflow Forum or on the GitHub Discussions page associated with this repository.

💬 Get in touch

Do you have more questions about Roboflow that we haven't responded to yet? Feel free to ask them on the Roboflow Discuss forum. Our developer advocates and community team actively respond to questions there.

To ask questions about Notebooks, head over to the GitHub Discussions section of this repository.

[capjamesg]

Hello @Shouq95! Thank you for your comment. You can upload your dataset to Roboflow to use the Roboflow data download features in our notebooks. You can also replace anywhere that dataset.location or a similar path is used with a local folder if you have data in the accepted format for the model you are training (i.e. YOLO format for YOLOv8).

Can you share which notebook you are working with?

[Shouq95]

Hello @capjamesg, thank you for your reply. I'm using the Segformer with custom data notebook. I first tried to use roboflow to upload my dataset but it's requiring me to annotate which I have already done outside of Roboflow. For me to use Roboflow it seems that my only option is to annotate all my images again.

This might be inexperience but I am having trouble finding a way to use any of these codes without having to use a dataset in Roboflow.

https://blog.roboflow.com/how-to-train-segformer-on-a-custom-dataset-with-pytorch-lightning/

[capjamesg]

Thank you for your comments! Have you uploaded your annotations into Roboflow? You can upload images and annotations into Roboflow, then download them into the notebook (see our supported upload formats). If you uploaded your annotations with your images, try again and see if there is an error or warning that appears in the Roboflow platform?