search

c0nn3r / RetinaNet

An implementation of RetinaNet in PyTorch.
BSD 3-Clause "New" or "Revised" License
299 stars 52 forks source link

classification branch #21

Open foralliance opened 5 years ago

foralliance commented 5 years ago

@c0nn3r HI

For focal loss. The classification branch uses the sigmoid function.

Why background class is considered in the classification branch??such as coco, num_classes=80 instead of 81.