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 read that one should start training from yolov4.conv.137 pre-trained weights file.
May I ask what a pre-trained weights file is? Is it a "standard template file" for training, but does not contain any trained class?
Is it possible to use the yolov4.weights to start training, if I want to detect the original 80 classes of the coco dataset plus another 2 additional classes? Or does training strictly have to start from a pre-trained weights file?
Is it possible to only detect say 3 classes of the 80 classes of the trained coco dataset? If I try to change the number of classes from the original 80 to a lower number, I get an error "filters= in the [convolutional]-layer doesn't correspond to classes".
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 read that one should start training from yolov4.conv.137 pre-trained weights file.
May I ask what a pre-trained weights file is? Is it a "standard template file" for training, but does not contain any trained class?
Is it possible to use the yolov4.weights to start training, if I want to detect the original 80 classes of the coco dataset plus another 2 additional classes? Or does training strictly have to start from a pre-trained weights file?
Is it possible to only detect say 3 classes of the 80 classes of the trained coco dataset? If I try to change the number of classes from the original 80 to a lower number, I get an error "filters= in the [convolutional]-layer doesn't correspond to classes".
Beta Was this translation helpful? Give feedback.
All reactions