Sangwoo Nam
Sangwoo Nam
> and train.py line 184 " 'num_class': args.num_class" is wrong,please check!!! maybe changing it to `'num_class': args.num_classes` would do.
Hello, I'm just a newbie. Color issue of demo.py could be fixed as https://github.com/toandaominh1997/EfficientDet.Pytorch/issues/31#issuecomment-565888531 Next, _Why need data augmentation when running demo.py?_ As I know data augmentation used in demo.py...
@pangpanghuahuamaomi > Hi, I have met the same problem,when run eval.py to test voc2007(4952imgs), some images show "No boxes to NMS",and some other images can be detected, but finally, all...
Yes, I think so. If you could make dataset and dataloader, which outputs same format as VOC or COCO in this repository then it might work.
@lgl603 > How to set the value of num_classes? Is the num_classes equals the real classes of objects, or num_classes = "real classes of object +1"? it's "real classes of...
@alen-mask Do you mean class name something like this? ` VOC_CLASSES = ( # always index 0 'aeroplane', 'bicycle', 'bird', 'boat', 'bottle', 'bus', 'car', 'cat', 'chair', 'cow', 'diningtable', 'dog', 'horse',...
@xafarranxera The code has been changed since the author replied, so you should retrain it your self. I think...
@xafarranxera You could try this. #110
@xafarranxera I'm currently training with my own dataset. I'm trying to detect cars and license plates. The model that inference below image is by using this repository's code about a...