You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Is it possible to do incremental learning based con yolov7.pt? Let me explain:
I need that the model still detects the 80 classes of COCO, but i have extra images (labeled) that are different and not included in the COCO dataset but they contain classes that are included in the COCO dataset that i want the model to detect as well (car, motorcycle and truck). Is it possible??
I labeled the new images with the same n# class as in the COCO dataset, and the yaml in data contains all 80 classes and the path to the new images. But the training only were able to detect the 3 new classes... Am I doing anything wrong?
The text was updated successfully, but these errors were encountered:
Is it possible to do incremental learning based con yolov7.pt? Let me explain:
I need that the model still detects the 80 classes of COCO, but i have extra images (labeled) that are different and not included in the COCO dataset but they contain classes that are included in the COCO dataset that i want the model to detect as well (car, motorcycle and truck). Is it possible??
I labeled the new images with the same n# class as in the COCO dataset, and the yaml in data contains all 80 classes and the path to the new images. But the training only were able to detect the 3 new classes... Am I doing anything wrong?
The text was updated successfully, but these errors were encountered: