change outputlayer in layergraph object

Question

Rubén 2023-5-18

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/1967064-change-outputlayer-in-layergraph-object

评论： Rubén 2023-5-24

Hello,

I have a layerGraph object and I need to remove the output layer because it is not relevant and it is not supported by Deep Learning HDL Toolbox.

I removed another layer and then make the corresponding connection but the output layer is different because I need to change the 'OutputNames' or set the out output layer in other way. However, 'OutputNames' property is read only.

I also tried to replace the last layer by the previous one and remove the previous layer but I get the same result

find in the following link the layerGraph object layers.mat

Is there any way to change the output layer in a layerGraph object?

Thank you in advance.

0 个评论
显示 -2更早的评论隐藏 -2更早的评论

请先登录，再进行评论。

请先登录，再回答此问题。

Answer 1

Matt J 2023-5-18

0
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/1967064-change-outputlayer-in-layergraph-object#answer_1238989

在 MATLAB Online 中打开

For example,

lgraph=layerGraph(regressionLayer)

lgraph =

LayerGraph with properties: InputNames: {1×0 cell} OutputNames: {'regressionoutput'} Layers: [1×1 nnet.cnn.layer.RegressionOutputLayer] Connections: [0×2 table]

layers=lgraph.Layers;

layers(end).Name='newName';

lgraph=layerGraph(layers)

lgraph =

LayerGraph with properties: InputNames: {1×0 cell} OutputNames: {'newName'} Layers: [1×1 nnet.cnn.layer.RegressionOutputLayer] Connections: [0×2 table]

8 个评论
显示 6更早的评论隐藏 6更早的评论

Rubén 2023-5-19

编辑：Rubén 2023-5-19

在 MATLAB Online 中打开

Hello @Matt J,

If I'm not wrong, it only changes the name of the layer and biulds a new layerGraph object with the same layer but with a different name.

I tried something similar, replacing the last layer and replacing its name but layerGraph's 'OutputNames' property changes to be empty and last layer seems not no be connected or set as output layer

I need to remove the 'BinaryCrossEntropyRegressionLaye_reshape' and make 'conv2d_8_sigmoid' the output layer.

-->

Before replacing/removing last layer

 LayerGraph with properties:
         Layers: [22×1 nnet.cnn.layer.Layer]
    Connections: [21×2 table]
     InputNames: {'input_1'}
    OutputNames: {'BinaryCrossEntropyRegressionLayer_reshape'}

After replacing/removing last layer

     LayerGraph with properties:
         Layers: [21×1 nnet.cnn.layer.Layer]
    Connections: [20×2 table]
     InputNames: {'input_1'}
    OutputNames: {1×0 cell}

However, if i read the name of the last layer it is nt empty (you suggested changing the last layer name but it doesn't change 'outputNames' porperty):

    layers.Layers(end).Name
ans =
    'conv2d_8_sigmoid'

The problem comess when I try to assemble a NN with 'assembleNetwork' function

Network: Missing output layer. The network must have at least one output layer.

Invalid network.
Caused by:
    Network: Missing output layer. The network must have at least one output layer.
    Layer 'conv2d_8_sigmoid': Unconnected output. Each layer output must be connected to the input of another layer.

In addition I trid to replace the last layer with a copy of the previous layer changing its name to 'BinaryCrossEntropyRegressionLayer_reshape' but I get 'Output Names' property empty

    outLayer=layers.Layers(end-1);
    outLayer.Name = layers.Layers(end).Name;
    layers = replaceLayer(layers, layers.Layers(end).Name, outLayer)
    
    layers = 
  LayerGraph with properties:
         Layers: [22×1 nnet.cnn.layer.Layer]
    Connections: [21×2 table]
     InputNames: {'input_1'}
    OutputNames: {1×0 cell}
    

The point how change the connection of the last layer with the output layer or change the reference of the output layer.

Matt J 2023-5-21

编辑：Matt J 2023-5-21

在 MATLAB Online 中打开

It will definitely given an error because it has no input and output layers, but that is not the point. Your original question was how to change the output name property of an output layer within an existing layerGraph and my original answer demonstrated how to do that.

If the question is about making predictions in a network without using an output layer, you can do it by using dlnetwork instead of assembleNetwork.

cl=convolution2dLayer([3,3],1 ,'Padding','same','Weights',rand(3),'Bias',0);

net=dlnetwork(cl,networkDataLayout([8,8,1],'SSC'));

net.predict(dlarray(rand(8),'SSC'))

ans =

8(S) × 8(S) × 1(C) single dlarray 1.9330 1.6235 1.4864 1.6687 2.1314 1.7076 1.5632 1.1103 2.1311 2.7175 1.8709 3.1219 2.9320 2.4912 2.6637 1.8686 2.0587 2.2242 2.5526 2.5633 2.7993 2.7756 2.4032 1.2422 1.8285 2.6174 1.9562 2.4646 2.5606 2.4817 2.1627 1.1586 1.9782 2.2336 2.9013 2.7397 2.2003 2.0638 1.7779 1.1409 1.0009 2.6439 2.3893 3.0688 2.0361 2.4400 2.3526 1.9205 1.3489 2.1934 2.7162 2.8103 2.6220 2.7962 2.9462 2.1174 1.0200 1.3155 1.1040 1.8461 1.8275 1.5256 2.7954 2.0552

Rubén 2023-5-24

I'm sorry but the original question was how to change the output layer itself. Maybe the misunderstanding comes because the 'OutputNames' property. Anyway, question is solved. Thank you

请先登录，再进行评论。

change outputlayer in layergraph object

0 个评论
显示 -2更早的评论隐藏 -2更早的评论

采纳的回答

8 个评论
显示 6更早的评论隐藏 6更早的评论

更多回答（0 个）

另请参阅

类别

标签

产品

版本

Community Treasure Hunt

change outputlayer in layergraph object

0 个评论 显示 -2更早的评论隐藏 -2更早的评论

采纳的回答

8 个评论 显示 6更早的评论隐藏 6更早的评论

更多回答（0 个）

另请参阅

类别

标签

产品

版本

Community Treasure Hunt

0 个评论
显示 -2更早的评论隐藏 -2更早的评论

8 个评论
显示 6更早的评论隐藏 6更早的评论