focal Loss Layer evaluation

I have created simple CNN for semantic segmentation and repalced last layer with focal loss layer to use focal loss fucntion instead of pixel classification function.

Network = [

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

convolution2dLayer([3 3],128,"Name","conv_1","BiasLearnRateFactor",2,"Padding","same")

reluLayer("Name","relu_1")

batchNormalizationLayer("Name","batchnorm")

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

reluLayer("Name","relu_3")

softmaxLayer("Name","softmax")

focalLossLayer(2,0.25,"Name","focal-loss")];

after training the network, I used,

pxdsResults = semanticseg(imdsTest,Trained_network, ...

'MiniBatchSize',5, ...

'WriteLocation',tempdir, ...

'Verbose',false);

for test images but I got error the following error;

Error using semanticseg>iFindAndAssertNetworkHasOnePixelClassificationLayer (line 584)

The network must have a pixel classification layer.

Error in semanticseg>iParseInputs (line 377)

pxLayerID = iFindAndAssertNetworkHasOnePixelClassificationLayer(net);

Error in semanticseg (line 216)

params = iParseInputs(I, net, varargin{:});

Now its obvious that last layer must be pixel classification layer. but if I am using focal loss layer how to evaluate this?

Answer 1

[Bhargavi Maganuru]

Hi,

Focal loss layer to a semantic segmentation or object classification deep learning network has been added in future release 2020b. In the earlier versions, you can use either PixelClassificationLayer or DicePixelClassificationLayer or a ClassificationLayer as the last layer in the network.

[Raza Ali]

Thank you for the information

[Raza Ali]

Can we use ClassificationLayer for semantic segmentation? please share any example link if you know.

[Bhargavi Maganuru]

You can use ClassficationLayer as the last layer in the network. For more information about ClassficationLayer, refer https://www.mathworks.com/help/deeplearning/ref/classificationlayer.html#responsive_offcanvas