Hi, I'm wondering have you changed a two-stage net like faster-rcnn or FPN to a one-stage net like the paper said? Do I just need to change the softmax loss layer to your focal loss layer for classification?
@zhanglonghao1992 Focal loss is not necessary in two-stage detection frameworks. The class imbalance problem only exists in one-stage detection networks such as YOLO and SSD.
Hi, I'm wondering have you changed a two-stage net like faster-rcnn or FPN to a one-stage net like the paper said? Do I just need to change the softmax loss layer to your focal loss layer for classification?