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 can't find a description of these weights used in tutorial for training Yolov4 darknet and I can't really understand where they came from, COCO? PASCAL VOC? ImageNet? I can't understand also if running the command !./darknet detector train ./obj.data ./yolov4-obj.cfg ./yolov4.conv.137 -dont_show -map means fine-tuning (i.e. simply initializing the model with weights without freezing anything) or transfer learning (freezing layers in the model)??
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
-
I can't find a description of these weights used in tutorial for training Yolov4 darknet and I can't really understand where they came from, COCO? PASCAL VOC? ImageNet? I can't understand also if running the command !./darknet detector train ./obj.data ./yolov4-obj.cfg ./yolov4.conv.137 -dont_show -map means fine-tuning (i.e. simply initializing the model with weights without freezing anything) or transfer learning (freezing layers in the model)??
Beta Was this translation helpful? Give feedback.
All reactions