Open erwanlenagard opened 1 year ago
Hi @erwanlenagard , thanks for opening an issue. Could you please add help@roboflow.com to your workspace?
Hi @FrancescoSaverioZuppichini, It's done. The error is related to "Michelin GT" project. By the way, there is also an error when I unzip the dataset archive on Windows manually or through the API : the file path is too long.
@erwanlenagard thanks 🙏 keep in mind these are your file so you can change their names to whatever works for you. Let me know if this helps 😄
@erwanlenagard it looks like it may be caused by the fact that one is a substring of another, we are not 100% sure yet. In the meantime, feel free to try and change the class name and see if the order is correct
Thanks a lot for your patience
Hello,
I'd like to report a minor bug. I've annotated a dataset with Roboflow. I exported my data in YOLOv8 format but 2 classes are inverted in data.yaml. The model have been trained sucessfully but when I display the labels on images, they are inverted...
I expected : names: ['Bibendum', 'Casquette', 'Dunlop', 'Goodyear', 'Michelin bibendum', 'Michelin logo', 'Michelin logo carre' 'Michelin sept', 'Pneu']
Here are the augmentations / preprocessing steps I choose in Roboflow before exporting :
PREPROCESSING Resize: Stretch to 640x640 Modify Classes: 4 remapped, 3 dropped
AUGMENTATIONS Outputs per training example: 3 Rotation: Between -15° and +15° Saturation: Between -25% and +25% Brightness: Between -25% and +25% Exposure: Between -25% and +25%