How to manually modify weights in a SeriesNetwork?
42 visualizaciones (últimos 30 días)
Mostrar comentarios más antiguos
Carlo Tomasi
el 6 de Jul. de 2017
Editada: Andrea Tagliabue
el 26 de Jul. de 2022
For some of my studies on deep neural nets, I need to change select weights in a (previously trained) SeriesNetwork by hand, and evaluate changes in the classification results. Ideally, I would like to do
net.Layers(k).Weights = W;
where net is a SeriesNetwork (a class in the Neural Network Toolbox), k is an integer that indexes a fully connected layer, and W is a suitable array. I would then classify inputs with the net modified in this way.
However, the field net.Layers(k).Weights is read-only, so the instruction above will generate the following error message:
You cannot set the read-only property 'Layers' of SeriesNetwork.
Is there some way to circumvent this restriction?
Here is what I tried, to no avail: First define an array of Layers by saying something like this:
layers = [imageInputLayer([28 28 1])
% Severa layers here
classificationLayer()];
then initialize the weights as desired, and finally make these layers into a SeriesNetwork with the class’s constructor:
net = SeriesNetwork(layers);
While this does create a new SeriesNetwork, attempting to classify an input with
y = classify(net, x);
where x is a suitable input results in the following error message:
Error using nnet.internal.cnn.layer.FullyConnected/forwardPropagateSize (line 99)
An input size for the layer must be defined in order to call forwardPropagateSize.
Error in SeriesNetwork>iDetermineLayerOutputSize (line 417)
inputSize = layers{i}.forwardPropagateSize(inputSize);
Error in SeriesNetwork/get.OutputSize (line 80)
val = iDetermineLayerOutputSize( internalLayers, outputLayerIdx );
Error in SeriesNetwork/predict (line 185)
Y = precision.cast( zeros([this.OutputSize dispatcher.NumObservations]) );
Error in SeriesNetwork/classify (line 250)
scores = this.predict( X, varargin{:} );
What is missing in my use of the constructor to make net a fully-fledged SeriesNetwork that can be used with classify?
0 comentarios
Respuesta aceptada
Más respuestas (2)
DL
el 29 de Mzo. de 2021
You can covert the trained NN to an object and it is a possible way, which I had test for it.
modify_able_NN = NN.saveobj;
% Changes made in NN
Modified_NN = NN.loadobj(modify_able_NN);
2 comentarios
Andrea Tagliabue
el 26 de Jul. de 2022
Editada: Andrea Tagliabue
el 26 de Jul. de 2022
The above code does not work for me. Trying to access the saveobj method in a shallow neural network returns the following errors: "Switch expression must be a scalar or a character vector". Any suggestion?
Code to reproduce:
myNN = feedforwardnet(10);
modifiableNN= myNN.saveobj
Shashank
el 14 de Jul. de 2017
Editada: Shashank
el 14 de Jul. de 2017
Hi Carlo,
Please see the following image to understand how the weights of various layers are stored in MATLAB.
![](https://www.mathworks.com/matlabcentral/answers/uploaded_files/177422/image.png)
It is stored as a cell array of matrices and each matrix corresponds to a weight matrix of that layer. It is like a map from 1st to 2nd layer , 2nd to 3rd and so on. Hence only the corresponding indices have weight vectors.
The 1st layer is called the input layer and weights can be set by :
>>net.IW{1} = [1;2;3;4;5;6;7;8;9;10;11;10];
However, please train the network using the following function before modifying the weight vectors:
>> net = trainscg(net,x,t); % where x and t are the input and output variables respectively.
For the succeeding layers, you can modify the weights using:
>> net.LW{2,1}=rand(128,12);
as shown in the screenshot.Please do not modify the empty vectors
Hope this helps.
- Shashank
Ver también
Categorías
Más información sobre Deep Learning Toolbox en Help Center y File Exchange.
Productos
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!