softmax

Apply softmax activation to channel dimension

Since R2019b

Syntax

Y = softmax(X)

Y = softmax(X,'DataFormat',FMT)

Description

The softmax activation operation applies the softmax function to the channel dimension of the input data.

The softmax function normalizes the value of the input data across the channel dimension such that it sums to one. You can regard the output of the softmax function as a probability distribution.

Note

This function applies the softmax operation to dlarray data. If you want to apply softmax within a layerGraph object or Layer array, use the following layer:

• softmaxLayer

Y = softmax(X) computes the softmax activation of the input X by applying the softmax transfer function to the channel dimension of the input data. All values in Y are between 0 and 1, and sum to 1. The input X must be a formatted dlarray. The output Y is a formatted dlarray with the same dimension format as X.

Y = softmax(X,'DataFormat',FMT) also specifies dimension format FMT when X is not a formatted dlarray. The output Y is an unformatted dlarray with the same dimension order as X.

Examples

Apply Softmax Activation

Use the softmax function to set all values in the input data to values between 0 and 1 that sum to 1 over all channels.

Create the input classification data as two observations of random variables. The data can be in any of 10 categories.

numCategories = 10;
observations = 2;

X = rand(numCategories,observations);
X = dlarray(X,'CB');

Compute the softmax activation.

Y = softmax(X)
totalProb = sum(Y,1)

Y =

  10(C) x 2(B) dlarray

    0.1151    0.0578
    0.1261    0.1303
    0.0579    0.1285
    0.1270    0.0802
    0.0959    0.1099
    0.0562    0.0569
    0.0673    0.0753
    0.0880    0.1233
    0.1328    0.1090
    0.1337    0.1288
totalProb =

  1(C) x 2(B) dlarray

    1.0000    1.0000

All values in Y range between 0 and 1. The values over all channels sum to 1 for each observation.

Input Arguments

X — Input data

dlarray

Input data, specified as a formatted dlarray or an unformatted dlarray. When X is not a formatted dlarray, you must specify the dimension label format using 'DataFormat',FMT.

X must contain a 'C' channel dimension.

Data Types: single | double

FMT — Dimension order of unformatted data

char array | string

Dimension order of unformatted input data, specified as the comma-separated pair consisting of 'DataFormat' and a character array or string FMT that provides a label for each dimension of the data. Each character in FMT must be one of the following:

• 'S' — Spatial

• 'C' — Channel

• 'B' — Batch (for example, samples and observations)

• 'T' — Time (for example, sequences)

• 'U' — Unspecified

You can specify multiple dimensions labeled 'S' or 'U'. You can use the labels 'C', 'B', and 'T' at most once.

You must specify 'DataFormat',FMT when the input data is not a formatted dlarray.

Example: 'DataFormat','SSCB'

Data Types: char | string

Output Arguments

Y — Softmax activations

dlarray

Softmax activations, returned as a dlarray. All values in Y are between 0 and 1. The output Y has the same underlying data type as the input X.

If the input data X is a formatted dlarray, Y has the same dimension format as X. If the input data is not a formatted dlarray, Y is an unformatted dlarray with the same dimension order as the input data.

More About

Softmax Activation

The softmax function normalizes the input across the channel dimension, such that it sums to one. For more information, see the definition of Softmax Layer on the softmaxLayer reference page.

Extended Capabilities

C/C++ Code Generation
Generate C and C++ code using MATLAB® Coder™.

GPU Code Generation
Generate CUDA® code for NVIDIA® GPUs using GPU Coder™.

GPU Arrays

Accelerate code by running on a graphics processing unit (GPU) using Parallel Computing Toolbox™.

Usage notes and limitations:

• When the input argument X is a dlarray with underlying data of type gpuArray, this function runs on the GPU.

For more information, see Run MATLAB Functions on a GPU (Parallel Computing Toolbox).

Version History

Introduced in R2019b