YOLOv3_TensorFlow
YOLOv3_TensorFlow copied to clipboard
Published
20 hours ago •
wizyoung
wizyoung
a picture with no object as negetive sample to train,how can I make it as input ? the coord shall I see it as 0,0,0,0?and the class ,what should I put it?
Why do you want to do this? A sparse input can already be considered as a negative sample.
And this repo , emmmm, does not support this. Still you can check the source code and modify it.
I think this makes no sense. Questions are like, how to choose prediction scale using IoU ranking, or how to set ignore mask. Of course you can modify the code yourself to achieve your goal, but this is not consistent with the original yolo idea any more.
