How to change input values for weight classfication layer.

I am using weigth classfication fucntion which given as example in MATALAB documentaion.

But whenI use it in my network it gives error "Error using 'backwardLoss' in Layer weightedClassificationLayer. The function threw an error and could not be executed". I think the error is due to input value but i am not sure where to change these valuse. The weighted classification function works well according to input valuse assigned in example.

The link of example https://in.mathworks.com/help/deeplearning/ug/create-custom-weighted-cross-entropy-classification-layer.html

the code I am using for weighted classification function

%%%%%%

classdef weightedClassificationLayer < nnet.layer.ClassificationLayer

properties

% Row vector of weights corresponding to the classes in the

% training data.

ClassWeights

end

methods

function layer = weightedClassificationLayer(classWeights, name)

% layer = weightedClassificationLayer(classWeights) creates a

% weighted cross entropy loss layer. classWeights is a row

% vector of weights corresponding to the classes in the order

% that they appear in the training data.

%

% layer = weightedClassificationLayer(classWeights, name)

% additionally specifies the layer name.

% Set class weights.

layer.ClassWeights = classWeights;

% Set layer name.

if nargin == 2

layer.Name = name;

end

% Set layer description

layer.Description = 'Weighted cross entropy';

end

function loss = forwardLoss(layer, Y, T)

% loss = forwardLoss(layer, Y, T) returns the weighted cross

% entropy loss between the predictions Y and the training

% targets T.

N = size(Y,4);

Y = squeeze(Y);

T = squeeze(T);

W = layer.ClassWeights;

loss = -sum(W*(T.*log(Y)))/N;

end

function dLdY = backwardLoss(layer, Y, T)

% dLdX = backwardLoss(layer, Y, T) returns the derivatives of

% the weighted cross entropy loss with respect to the

% predictions Y.

[~,~,K,N] = size(Y);

Y = squeeze(Y);

T = squeeze(T);

W = layer.ClassWeights;

dLdY = -(W'.*T./Y)/N;

dLdY = reshape(dLdY,[1 1 K N]);

end

end

end

Answer 1

[Pujitha Narra]

This is a way to initialize 'classWeights'

classWeights = 1./countcats(YTrain);
classWeights = classWeights'/mean(classWeights);

and you can use it here:

Network = [
    imageInputLayer([256 256 3],"Name","imageinput")
    convolution2dLayer([3 3],2,"Name","conv","Padding","same")
    reluLayer("Name","relu")
    softmaxLayer("Name","softmax")
    weightedClassificationLayer(classWeights)
     ];

I think this should solve the problem.

[Raza Ali]

can you explain here two terms: YTrain and Classweight.

what does these term means here?

what should be the size of class weights?

i am getting same error "Error using 'backwardLoss' in Layer weightedClassificationLayer. The function threw an error and could not be executed."

[Raza Ali]

Layer Name Activation

imageInputLayer([256 256 3] 256 256 3

convolution2dLayer([3 3],2,"Name","conv","Padding","same") 256 256 2

reluLayer("Name","relu") 256 256 2

softmaxLayer("Name","softmax") 256 256 2

weightedClassificationLayer(classWeights)

Now what should I set class weights....to avoid this error "Error using 'backwardLoss' in Layer weightedClassificationLayer. The function threw an error and could not be executed."

[Pujitha Narra]

'classWeights' are the weights you want to set the layer(weightedClassificationLayer) with. The number of weights(the size of 'classWeights') is defined by the training data.

'YTrain' is the set of all the labels/classes in your training data set.

You can go through this example for further clarification.

https://in.mathworks.com/help/deeplearning/examples/deep-learning-speech-recognition.html#responsive_offcanvas

[Raza Ali]

Thank you for your help and sharing this link. I have been to this link, but my problem is still un solved.

I tried different valuse of Class weigths but getting same error again and again,

Let me explain you through example.

I have two classes A and B. both folders has 2500 images of 256 by 256 by 3 (in total 5000 images in two different classes).

I have tried following classweights.

1. classWeights = rand(1,2)
2. classWeights = rand(1,2500)
3. classWeights = rand(1,5000)
4. classWeights = rand(1,196608) % 256*256*3=196608

but no vlaues of classweight is working... Error using 'backwardLoss' in Layer weightedClassificationLayer. The function threw an error and could not be executed."

[Pujitha Narra]

Can you share the code your are using?

[Raza Ali]

I am using two different image types( two classes A and B). Each Image has size: 256 by 256 by 3

%%%Start

imds = imageDatastore('Images','IncludeSubfolders',true,'LabelSource','foldernames');

[imdsTrain,imdsValidation] = splitEachLabel(imds,0.7,'randomized');

YTrain=imdsTrain.Labels;

YTrain = removecats(YTrain);

classWeights = 1./countcats(YTrain)

classWeights = classWeights'/mean(classWeights)

Network = [

imageInputLayer([256 256 3],"Name","data")

convolution2dLayer([3 3],16,"Name","conv1","BiasLearnRateFactor",2,"Stride",[4 4])

reluLayer("Name","relu1")

crossChannelNormalizationLayer(5,"Name","norm1","K",1)

maxPooling2dLayer([3 3],"Name","pool1","Stride",[2 2])

convolution2dLayer([3 3],32,"Name","conv","Padding","same")

reluLayer("Name","relu5")

maxPooling2dLayer([3 3],"Name","pool5","Stride",[2 2])

fullyConnectedLayer(2,"Name","fc8","BiasLearnRateFactor",2)

softmaxLayer("Name","prob")

weightedClassificationLayer("classWeights")

];

Options = trainingOptions('sgdm', ...

'MiniBatchSize',5, ...

'MaxEpochs',3, ...

'Shuffle','every-epoch', ...

'InitialLearnRate',1e-4, ...

'ValidationData',imdsValidation, ...

'ValidationFrequency',2100, ...

'Verbose',true, ...

'Plots','training-progress');

TrainedNetwork = trainNetwork(imdsTrain,Network,Options);

Answer 2

[Pujitha Narra]

Hi Raza Ali,

Can you mention how are you using 'weightedClassificationLayer' in your network? Assuming you want to know the inputs to the constructor of this class:

'classWeights' and the layer's 'name' are the only inputs.

'classWeights'-. classWeights is a row vector of weights corresponding to the classes in the order that they appear in the training data.

'name' -additionally specifies the layer name.

Also this example might be of help

https://in.mathworks.com/help/deeplearning/examples/deep-learning-speech-recognition.html

Hope this helps!

[Raza Ali]

Thank you.

I am using this after softmax layer:

Network= [

imageInputLayer([256 256 3],"Name","imageinput")

convolution2dLayer([3 3],64,"Name","conv_1","BiasLearnRateFactor",2,"Padding","same")

reluLayer("Name","relu_1")

transposedConv2dLayer([3 3],2,"Name","transposed-conv","Cropping","same")

softmaxLayer("Name","softmax")

weightedClassificationLayer("ClassificationLayer") ];

my input size is 256 by 256 by 3.

[Pujitha Narra]

In the last line, when calling the constructor 'weightedClassificationLayer()', 'classWeights' are missing in the inputs. 'classWeights' are those which customize the classification layer according to your requirements.

[Raza Ali]

Here is the problem, these classweights has to be taken from softmax layer.

[Raza Ali]

I recive this Error

Error using trainNetwork (line 170)

Error using 'backwardLoss' in Layer weightedClassificationLayer. The function threw an error and could not be executed.

[Pujitha Narra]

Hi Raza,

What do you mean when you say, you want to take classWeights from softmax layer?

[Raza Ali]

I just want to use weightClassfication layer in simple CNN layer as output layer. and my image size is 256 x 256 x 3.

The nnetwork configurations i have mentioned in question. but when i use it gives error.

Error using 'backwardLoss' in Layer weightedClassificationLayer. The function threw an error and could not be executed.

[Raza Ali]

Network = [

imageInputLayer([256 256 3],"Name","imageinput")

convolution2dLayer([3 3],2,"Name","conv","Padding","same")

reluLayer("Name","relu")

softmaxLayer("Name","softmax")

weightedClassificationLayer('classWeights')

];

Answer 3

[Ashwin]

Try to use classWeights' instead of classWeights

And check if it works