Are dlnetworks allowed to have output layers? In the following code, I manage to create one, so the answer would seem to be yes.
layers= [imageInputLayer([1,1,1]) , reluLayer(Name=’relu’) ] ;

dln = replaceLayer( dlnetwork(layers) ,’relu’, regressionLayer);

class(dln)
dln.Layers
However, when I try to create this more directly, an error is raised:
dln = dlnetwork( [imageInputLayer([1,1,1]) , regressionLayer] )
Have I found an unintended backdoor?Are dlnetworks allowed to have output layers? In the following code, I manage to create one, so the answer would seem to be yes.
layers= [imageInputLayer([1,1,1]) , reluLayer(Name=’relu’) ] ;

dln = replaceLayer( dlnetwork(layers) ,’relu’, regressionLayer);

class(dln)
dln.Layers
However, when I try to create this more directly, an error is raised:
dln = dlnetwork( [imageInputLayer([1,1,1]) , regressionLayer] )
Have I found an unintended backdoor? Are dlnetworks allowed to have output layers? In the following code, I manage to create one, so the answer would seem to be yes.
layers= [imageInputLayer([1,1,1]) , reluLayer(Name=’relu’) ] ;

dln = replaceLayer( dlnetwork(layers) ,’relu’, regressionLayer);

class(dln)
dln.Layers
However, when I try to create this more directly, an error is raised:
dln = dlnetwork( [imageInputLayer([1,1,1]) , regressionLayer] )
Have I found an unintended backdoor? dlnetwork, output layer MATLAB Answers — New Questions

​