You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I'm currently working on the 3D detection task and I'm confused about the anchor generator in monai.apps.detection.networks.retinanet_detector.
Could you please explain why the generate_anchors function uses the head_outputs[self.cls_key] as the input instead of the fpn_outputs? self.anchors = self.anchor_generator(images, head_outputs[self.cls_key])
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
-
Hi @Can-Zhao ,
I'm currently working on the 3D detection task and I'm confused about the anchor generator in monai.apps.detection.networks.retinanet_detector.
Could you please explain why the generate_anchors function uses the head_outputs[self.cls_key] as the input instead of the fpn_outputs?
self.anchors = self.anchor_generator(images, head_outputs[self.cls_key])I'm really looking forward to your reply.
Beta Was this translation helpful? Give feedback.
All reactions