PyTorch-YOLOv3 icon indicating copy to clipboard operation
PyTorch-YOLOv3 copied to clipboard

Having some doubts for build_target

Open d5423197 opened this issue 3 years ago • 1 comments

Hello there,

After learning your code, I still have some doubts. If one label has a chance to appear in each layer(13 13, 26 26, 52 52) and many anchors. I am seeing that the loss will be added for each layer. I don't know the reason behind this.

If there is a big object which is better to be handled for grid 13 by 13. But it may also become a target in another layer?

Thanks, ZD

d5423197 avatar Jun 08 '22 05:06 d5423197

Some other implementation for yolov3 would find the best anchor for each true box. Is there any gap I am having? I can understand that each true box would be assigned by one best anchor from one grid, but I could not understand the implementation that one true box to many anchors from different layers.

d5423197 avatar Jun 08 '22 05:06 d5423197