ClassificationOutputLayer

(Not recommended) Classification output layer

ClassificationOutputLayer objects are recommended. Use the trainnet function and set the loss function to "crossentropy" instead. For more information, see Version History.

Description

A classification layer computes the cross-entropy loss for classification and weighted classification tasks with mutually exclusive classes.

Creation

Create a classification layer using classificationLayer.

Properties

Classification Output

ClassWeights — Class weights for weighted cross-entropy loss

'none' (default) | vector of positive numbers

Class weights for weighted cross-entropy loss, specified as a vector of positive numbers or 'none'.

For vector class weights, each element represents the weight for the corresponding class in the Classes property. To specify a vector of class weights, you must also specify the classes using the Classes option.

If the ClassWeights property is 'none', then the layer applies unweighted cross-entropy loss.

Classes — Classes of the output layer

"auto" (default) | categorical vector | string array | cell array of character vectors

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 the string array or cell array of character vectors str, then the software sets the classes of the output layer to categorical(str,str).

Data Types: char | categorical | string | cell

OutputSize — Size of the output

Read-only: 'auto' (default) | positive integer

This property is read-only.

Size of the output, specified as a positive integer. This value is the number of labels in the data. Before the training, the output size is set to 'auto'.

LossFunction — Loss function for training

Read-only: 'crossentropyex'

This property is read-only.

Loss function for training, specified as 'crossentropyex', which stands for Cross Entropy Function for k Mutually Exclusive Classes.

Layer

Name — Layer name

"" (default) | character vector | string scalar

Layer name, specified as a character vector or a string scalar. For Layer array input, the trainNetwork function automatically assigns names to layers with the name "".

The ClassificationOutputLayer object stores this property as a character vector.

Data Types: char | string

NumInputs — Number of inputs

1 (default)

Number of inputs to the layer, returned as 1. This layer accepts a single input only.

Data Types: double

InputNames — Input names

{'in'} (default)

Input names, returned as {'in'}. This layer accepts a single input only.

Data Types: cell

NumOutputs — Number of outputs

0 (default)

Number of outputs of the layer, returned as 0. This layer has no outputs.

Data Types: double

OutputNames — Output names

{} (default)

Output names of the layer, returned as {}. This layer has no outputs.

Data Types: cell

Examples

Create Classification Layer

Create a classification layer.

Create a classification layer with the name 'output'.

layer = classificationLayer('Name','output')

layer = 
  ClassificationOutputLayer with properties:

            Name: 'output'
         Classes: 'auto'
    ClassWeights: 'none'
      OutputSize: 'auto'

   Hyperparameters
    LossFunction: 'crossentropyex'

Include a classification output layer in a Layer array.

layers = [ ...
    imageInputLayer([28 28 1])
    convolution2dLayer(5,20)
    reluLayer
    maxPooling2dLayer(2,'Stride',2)
    fullyConnectedLayer(10)
    softmaxLayer
    classificationLayer]

layers = 
  7x1 Layer array with layers:

     1   ''   Image Input             28x28x1 images with 'zerocenter' normalization
     2   ''   2-D Convolution         20 5x5 convolutions with stride [1  1] and padding [0  0  0  0]
     3   ''   ReLU                    ReLU
     4   ''   2-D Max Pooling         2x2 max pooling with stride [2  2] and padding [0  0  0  0]
     5   ''   Fully Connected         10 fully connected layer
     6   ''   Softmax                 softmax
     7   ''   Classification Output   crossentropyex

More About

Classification Output Layer

A classification layer computes the cross-entropy loss for classification and weighted classification tasks with mutually exclusive classes.

For typical classification networks, the classification layer usually follows a softmax layer. In the classification layer, trainNetwork takes the values from the softmax function and assigns each input to one of the K mutually exclusive classes using the cross entropy function for a 1-of-K coding scheme [1]:

$$\text{loss}=-\frac{1}{N}{\displaystyle \sum _{n=1}^N{\displaystyle \sum }_{i=1}^K}\text{}{w}_i{\text{t}}_{ni}\ln y_{ni},$$

where N is the number of samples, K is the number of classes, w_i is the weight for class i, t_ni is the indicator that sample n belongs to class i, and y_ni is the output for sample n for class i, which in this case, is the value from the softmax function. In other words, y_ni is the probability that the network associates observation n with class i.

References

[1] Bishop, C. M. Pattern Recognition and Machine Learning. Springer, New York, NY, 2006.

Version History

Introduced in R2016a

R2024a: Not recommended

Starting in R2024a, ClassificationOutputLayer objects are not recommended, use the trainnet and set the loss function to "crossentropy" instead.

There are no plans to remove support for ClassificationOutputLayer objects. However, the trainnet function has these advantages and is recommended instead:

• trainnet supports dlnetwork objects, which support a wider range of network architectures that you can create or import from external platforms.

• trainnet enables you to easily specify loss functions. You can select from built-in loss functions or specify a custom loss function.

• trainnet outputs a dlnetwork object, which is a unified data type that supports network building, prediction, built-in training, visualization, compression, verification, and custom training loops.

• trainnet is typically faster than trainNetwork.

This table shows some typical usages of the trainNetwork function with ClassificationOutputLayer objects and how to update your code to use the trainnet function instead.

Not Recommended	Recommended
net = trainNetwork(data,layers,options), where layers contains a ClassificationOutputLayer object.	net = trainnet(data,layers,"crossentropy",options); In this example, layers specifies same network without a ClassificationOutputLayer object.
net = trainNetwork(data,layers,options), where layers contains a ClassificationOutputLayer object with ClassWeights set to a numeric vector.	lossFcn = @(Y,T) crossentropy(Y,T,Weights=weights); net = trainnet(data,layers,"crossentropy",options); In this example, weights specifies the class weights and layers specifies same network without a ClassificationOutputLayer object.

R2018b: ClassNames property will be removed

ClassNames will be removed. Use Classes instead. To update your code, replace all instances of ClassNames with Classes. There are some differences between the properties that require additional updates to your code.

The ClassNames property of the output layer is a cell array of character vectors. The Classes property is a categorical array. To use the value of Classes with functions that require cell array input, convert the classes using the cellstr function.