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
This may not be a bug/error but in create_model_from_config you have the following:
pretrained_backbone=kwargs.pop('pretrained_backbone', True)
ifpretrainedorcheckpoint_path:
pretrained_backbone=False# no point in loading backbone weights
If pretrained is True in create_model_from_config , this lead to not loading pretrained weight for the backbone in the EfficientDet class:
Is there an explanation or it should be changed to the following ?
pretrained_backbone=kwargs.pop('pretrained_backbone', True)
ifnotpretrainedorcheckpoint_path:
pretrained_backbone=False# no point in loading backbone weights
The text was updated successfully, but these errors were encountered:
This may not be a bug/error but in
create_model_from_config
you have the following:If
pretrained
is True increate_model_from_config
, this lead to not loading pretrained weight for the backbone in the EfficientDet class:Is there an explanation or it should be changed to the following ?
The text was updated successfully, but these errors were encountered: