Hi, when running the following code, I encountered the following error:

Error using nnet.internal.cnn.util.validateLayersForLayerGraph>iAssertUniqueAndNonEmptyLayerNames (line 45)

Layer names in layer array must be nonempty.

Error in nnet.internal.cnn.util.validateLayersForLayerGraph (line 33)

iAssertUniqueAndNonEmptyLayerNames(larray, existingLayers);

Error in nnet.cnn.LayerGraph>iValidateLayers (line 556)

larray = nnet.internal.cnn.util.validateLayersForLayerGraph(larray, existingLayers);

Error in nnet.cnn.LayerGraph/replaceLayer (line 420)

larray = iValidateLayers(larray, existingLayers);

Error in dazuoye (line 51 )

net = replaceLayer(net,"encoderImageInputLayer", ...

My code is as follows:

net = encoderDecoderNetwork(inputSize,encoder,decoder, ...
    LatentNetwork=bridgeLayers, ...
    SkipConnections="concatenate", ...
    FinalNetwork=finalLayers);
net = layerGraph(net);
net = replaceLayer(net,"encoderImageInputLayer", ...
    imageInputLayer(inputSize,Normalization="zerocenter"));

Answer 1

[Cris LaPierre]

See this answer: https://www.mathworks.com/matlabcentral/answers/603127-how-to-replace-imageinputlayer-with-sequenceinputlayer-in-imported-tensorflow-keras-network