training dataset include images with non-labeled objects that I do not want to detect

toandaominh1997 / EfficientDet.Pytorch

Implementation EfficientDet: Scalable and Efficient Object Detection in PyTorch

MIT License

1.44k stars 306 forks source link

training dataset include images with non-labeled objects that I do not want to detect #85

Open jfkkf123 opened 4 years ago

jfkkf123 commented 4 years ago

My training dataset include images with non-labeled objects that I do not want to detect, I use xml without bounded box in training. but there is an error, File "/root/EfficientDet.Pytorch/datasets/augmentation.py", line 113, in call annots[:, :4] *= scale IndexError: too many indices for array If i remove these images and xml files , it will work . but i want to use these images just like darknet training process. would you please tell me how to solve it? thanks

abhiksark commented 4 years ago

I am also facing the same issue. Did you find any solution for this?