fromnndata

(To be removed) Convert data from standard neural network cell array form

fromnndata will be removed in a future release. For more information, see Transition Legacy Neural Network Code to dlnetwork Workflows.

For advice on updating your code, see Version History.

Syntax

fromnndata(x,toMatrix,columnSample,cellTime)


Description

fromnndata(x,toMatrix,columnSample,cellTime) takes these arguments,

net	Neural network
toMatrix	True if result is to be in matrix form
columnSample	True if samples are to be represented as columns, false if rows
cellTime	True if time series are to be represented as a cell array, false if represented with a matrix

and returns the original data reformatted accordingly.

Examples

Here time-series data is converted from a matrix representation to standard cell array representation, and back. The original data consists of a 5-by-6 matrix representing one time-series sample consisting of a 5-element vector over 6 timesteps arranged in a matrix with the samples as columns.

x = rands(5,6)
columnSamples = true; % samples are by columns.
cellTime = false;     % time-steps in matrix, not cell array.
[y,wasMatrix] = tonndata(x,columnSamples,cellTime)
x2 = fromnndata(y,wasMatrix,columnSamples,cellTime)

Here data is defined in standard neural network data cell form. Converting this data does not change it. The data consists of three time series samples of 2-element signals over 3 timesteps.

x = {rands(2,3);rands(2,3);rands(2,3)}
columnSamples = true;
cellTime = true;
[y,wasMatrix] = tonndata(x)
x2 = fromnndata(y,wasMatrix,columnSamples)

Version History

Introduced in R2010b

R2026a: fromnndata will be removed

fromnndata will be removed in a future release.

To learn more about data processing for neural networks, see these examples and topics:

• Preprocess Data for Domain-Specific Deep Learning Applications

• Datastores for Deep Learning

• Choose an App to Label Ground Truth Data

For more information, see Transition Legacy Neural Network Code to dlnetwork Workflows.