# Define Custom Pixel Classification Layer with Tversky Loss

This example shows how to define and create a custom pixel classification layer that uses Tversky loss.

This layer can be used to train semantic segmentation networks. To learn more about creating custom deep learning layers, see Define Custom Deep Learning Layers.

### Tversky Loss

The Tversky loss is based on the Tversky index for measuring overlap between two segmented images [1]. The Tversky index ${\mathrm{TI}}_{\mathit{c}}$ between one image $\mathit{Y}$ and the corresponding ground truth $\mathit{T}$ is given by

`${\mathrm{TI}}_{\mathit{c}}=\frac{{\sum }_{\mathit{m}=1}^{\mathit{M}}{\mathit{Y}}_{\mathrm{cm}}{\mathit{T}}_{\mathrm{cm}}}{{\sum }_{\mathit{m}=1}^{\mathit{M}}{\mathit{Y}}_{\mathrm{cm}}{\mathit{T}}_{\mathrm{cm}}+\alpha {\sum }_{\mathit{m}=1}^{\mathit{M}}{\mathit{Y}}_{\mathrm{cm}}{\mathit{T}}_{\stackrel{‾}{\mathrm{c}}\mathit{m}}+\beta {\sum }_{\mathit{m}=1}^{\mathit{M}}{\mathit{Y}}_{\stackrel{‾}{\mathrm{c}}\mathit{m}}{\mathit{T}}_{\mathrm{cm}}}$`

• $\mathit{c}$ corresponds to the class and $\stackrel{‾}{\mathit{c}}\text{\hspace{0.17em}}$corresponds to not being in class $\mathit{c}$.

• $\mathit{M}$ is the number of elements along the first two dimensions of $\mathit{Y}$.

• $\alpha$ and $\beta$ are weighting factors that control the contribution that false positives and false negatives for each class make to the loss.

The loss $\mathit{L}\text{\hspace{0.17em}}$over the number of classes $\mathit{C}$ is given by

`$\mathit{L}=\sum _{\mathit{c}=1}^{\mathit{C}}1-{\mathrm{TI}}_{\mathit{c}}$`

### Classification Layer Template

Copy the classification layer template into a new file in MATLAB®. This template outlines the structure of a classification layer and includes the functions that define the layer behavior. The rest of the example shows how to complete the `tverskyPixelClassificationLayer`.

```classdef tverskyPixelClassificationLayer < nnet.layer.ClassificationLayer properties % Optional properties end methods function loss = forwardLoss(layer, Y, T) % Layer forward loss function goes here end end end ```

### Declare Layer Properties

By default, custom output layers have the following properties:

• `Name` – Layer name, specified as a character vector or a string scalar. To include this layer in a layer graph, you must specify a nonempty unique layer name. If you train a series network with this layer and `Name` is set to `''`, then the software automatically assigns a name at training time.

• `Description` – One-line description of the layer, specified as a character vector or a string scalar. This description appears when the layer is displayed in a `Layer` array. If you do not specify a layer description, then the software displays the layer class name.

• `Type` – Type of the layer, specified as a character vector or a string scalar. The value of `Type` appears when the layer is displayed in a `Layer` array. If you do not specify a layer type, then the software displays `'Classification layer'` or `'Regression layer'`.

Custom classification layers also have the following property:

• `Classes` – Classes of the output layer, specified as a categorical vector, string array, cell array of character vectors, or `'auto'`. If `Classes` is `'auto'`, then the software automatically sets the classes at training time. If you specify a string array or cell array of character vectors `str`, then the software sets the classes of the output layer to `categorical(str,str)`. The default value is `'auto'`.

If the layer has no other properties, then you can omit the `properties` section.

The Tversky loss requires a small constant value to prevent division by zero. Specify the property, `Epsilon`, to hold this value. It also requires two variable properties A`lpha` and `Beta` that control the weighting of false positives and false negatives, respectively.

```classdef tverskyPixelClassificationLayer < nnet.layer.ClassificationLayer properties(Constant) % Small constant to prevent division by zero. Epsilon = 1e-8; end properties % Default weighting coefficients for false positives and false negatives Alpha = 0.5; Beta = 0.5; end ... end ```

### Create Constructor Function

Create the function that constructs the layer and initializes the layer properties. Specify any variables required to create the layer as inputs to the constructor function.

Specify an optional input argument name to assign to the `Name` property at creation.

```function layer = tverskyPixelClassificationLayer(name, alpha, beta) % layer = tverskyPixelClassificationLayer(name) creates a Tversky % pixel classification layer with the specified name. % Set layer name layer.Name = name; % Set layer properties layer.Alpha = alpha; layer.Beta = beta; % Set layer description layer.Description = 'Tversky loss'; end ```

### Create Forward Loss Function

Create a function named `forwardLoss` that returns the weighted cross entropy loss between the predictions made by the network and the training targets. The syntax for `forwardLoss` is `loss = forwardLoss(layer,Y,T)`, where `Y` is the output of the previous layer and `T` represents the training targets.

For semantic segmentation problems, the dimensions of `T` match the dimension of `Y`, where `Y` is a 4-D array of size `H`-by-`W`-by-`K`-by-`N`, where `K` is the number of classes, and `N` is the mini-batch size.

The size of `Y` depends on the output of the previous layer. To ensure that `Y` is the same size as `T`, you must include a layer that outputs the correct size before the output layer. For example, to ensure that `Y` is a 4-D array of prediction scores for `K` classes, you can include a fully connected layer of size `K` or a convolutional layer with `K` filters followed by a softmax layer before the output layer.

```function loss = forwardLoss(layer, Y, T) % loss = forwardLoss(layer, Y, T) returns the Tversky loss between % the predictions Y and the training targets T. Pcnot = 1-Y; Gcnot = 1-T; TP = sum(sum(Y.*T,1),2); FP = sum(sum(Y.*Gcnot,1),2); FN = sum(sum(Pcnot.*T,1),2); numer = TP + layer.Epsilon; denom = TP + layer.Alpha*FP + layer.Beta*FN + layer.Epsilon; % Compute Tversky index lossTIc = 1 - numer./denom; lossTI = sum(lossTIc,3); % Return average Tversky index loss N = size(Y,4); loss = sum(lossTI)/N; end ```

### Backward Loss Function

As the `forwardLoss` function fully supports automatic differentiation, there is no need to create a function for the backward loss.

For a list of functions that support automatic differentiation, see List of Functions with dlarray Support.

### Completed Layer

The completed layer is provided in `tverskyPixelClassificationLayer.m`.

```classdef tverskyPixelClassificationLayer < nnet.layer.ClassificationLayer % This layer implements the Tversky loss function for training % semantic segmentation networks. % References % Salehi, Seyed Sadegh Mohseni, Deniz Erdogmus, and Ali Gholipour. % "Tversky loss function for image segmentation using 3D fully % convolutional deep networks." International Workshop on Machine % Learning in Medical Imaging. Springer, Cham, 2017. % ---------- properties(Constant) % Small constant to prevent division by zero. Epsilon = 1e-8; end properties % Default weighting coefficients for False Positives and False % Negatives Alpha = 0.5; Beta = 0.5; end methods function layer = tverskyPixelClassificationLayer(name, alpha, beta) % layer = tverskyPixelClassificationLayer(name, alpha, beta) creates a Tversky % pixel classification layer with the specified name and properties alpha and beta. % Set layer name. layer.Name = name; layer.Alpha = alpha; layer.Beta = beta; % Set layer description. layer.Description = 'Tversky loss'; end function loss = forwardLoss(layer, Y, T) % loss = forwardLoss(layer, Y, T) returns the Tversky loss between % the predictions Y and the training targets T. Pcnot = 1-Y; Gcnot = 1-T; TP = sum(sum(Y.*T,1),2); FP = sum(sum(Y.*Gcnot,1),2); FN = sum(sum(Pcnot.*T,1),2); numer = TP + layer.Epsilon; denom = TP + layer.Alpha*FP + layer.Beta*FN + layer.Epsilon; % Compute tversky index lossTIc = 1 - numer./denom; lossTI = sum(lossTIc,3); % Return average tversky index loss. N = size(Y,4); loss = sum(lossTI)/N; end end end ```

### GPU Compatibility

The MATLAB functions used in `forwardLoss` in `tverskyPixelClassificationLayer` all support `gpuArray` inputs, so the layer is GPU compatible.

### Check Output Layer Validity

Create an instance of the layer.

`layer = tverskyPixelClassificationLayer('tversky',0.7,0.3);`

Check the validity of the layer by using `checkLayer`. Specify the valid input size to be the size of a single observation of typical input to the layer. The layer expects a `H`-by-`W`-by-`K`-by-`N` array inputs, where `K` is the number of classes, and `N` is the number of observations in the mini-batch.

```numClasses = 2; validInputSize = [4 4 numClasses]; checkLayer(layer,validInputSize, 'ObservationDimension',4)```
```Skipping GPU tests. No compatible GPU device found. Skipping code generation compatibility tests. To check validity of the layer for code generation, specify the 'CheckCodegenCompatibility' and 'ObservationDimension' options. Running nnet.checklayer.TestOutputLayerWithoutBackward ........ Done nnet.checklayer.TestOutputLayerWithoutBackward __________ Test Summary: 8 Passed, 0 Failed, 0 Incomplete, 2 Skipped. Time elapsed: 0.31452 seconds. ```

The test summary reports the number of passed, failed, incomplete, and skipped tests.

### Use Custom Layer in Semantic Segmentation Network

Create a semantic segmentation network that uses the `tverskyPixelClassificationLayer`.

```layers = [ imageInputLayer([32 32 1]) convolution2dLayer(3,64,'Padding',1) batchNormalizationLayer reluLayer maxPooling2dLayer(2,'Stride',2) convolution2dLayer(3,64,'Padding',1) reluLayer transposedConv2dLayer(4,64,'Stride',2,'Cropping',1) convolution2dLayer(1,2) softmaxLayer tverskyPixelClassificationLayer('tversky',0.3,0.7)];```

Load training data for semantic segmentation using `imageDatastore` and `pixelLabelDatastore`.

```dataSetDir = fullfile(toolboxdir('vision'),'visiondata','triangleImages'); imageDir = fullfile(dataSetDir,'trainingImages'); labelDir = fullfile(dataSetDir,'trainingLabels'); imds = imageDatastore(imageDir); classNames = ["triangle" "background"]; labelIDs = [255 0]; pxds = pixelLabelDatastore(labelDir, classNames, labelIDs);```

Associate the image and pixel label data by using datastore `combine`.

`ds = combine(imds,pxds);`

Set the training options and train the network.

```options = trainingOptions('adam', ... 'InitialLearnRate',1e-3, ... 'MaxEpochs',100, ... 'LearnRateDropFactor',5e-1, ... 'LearnRateDropPeriod',20, ... 'LearnRateSchedule','piecewise', ... 'MiniBatchSize',50); net = trainNetwork(ds,layers,options);```
```Training on single CPU. Initializing input data normalization. |========================================================================================| | Epoch | Iteration | Time Elapsed | Mini-batch | Mini-batch | Base Learning | | | | (hh:mm:ss) | Accuracy | Loss | Rate | |========================================================================================| | 1 | 1 | 00:00:01 | 50.32% | 1.2933 | 0.0010 | | 13 | 50 | 00:00:20 | 98.83% | 0.0991 | 0.0010 | | 25 | 100 | 00:00:37 | 99.33% | 0.0549 | 0.0005 | | 38 | 150 | 00:00:53 | 99.37% | 0.0465 | 0.0005 | | 50 | 200 | 00:01:07 | 99.48% | 0.0400 | 0.0003 | | 63 | 250 | 00:01:20 | 99.47% | 0.0385 | 0.0001 | | 75 | 300 | 00:01:31 | 99.54% | 0.0349 | 0.0001 | | 88 | 350 | 00:01:42 | 99.51% | 0.0353 | 6.2500e-05 | | 100 | 400 | 00:01:53 | 99.56% | 0.0331 | 6.2500e-05 | |========================================================================================| Training finished: Max epochs completed. ```

Evaluate the trained network by segmenting a test image and displaying the segmentation result.

```I = imread('triangleTest.jpg'); [C,scores] = semanticseg(I,net); B = labeloverlay(I,C); montage({I,B})```

### References

[1] Salehi, Seyed Sadegh Mohseni, Deniz Erdogmus, and Ali Gholipour. "Tversky loss function for image segmentation using 3D fully convolutional deep networks." International Workshop on Machine Learning in Medical Imaging. Springer, Cham, 2017.