predict - (Not recommended) Predict responses using trained deep learning neural

        network - MATLAB ([original](https://www.mathworks.com/help/deeplearning/ref/seriesnetwork.predict.html)) ([raw](?raw))

Main Content

(Not recommended) Predict responses using trained deep learning neural network

Syntax

Description

You can make predictions using a trained neural network for deep learning on either a CPU or GPU. Using a GPU requires a Parallel Computing Toolbox™ license and a supported GPU device. For information about supported devices, seeGPU Computing Requirements (Parallel Computing Toolbox). Specify the hardware requirements using theExecutionEnvironment name-value argument.

[Y](#d126e207163) = predict([net](#mw%5F63c849d9-9878-4f95-98ca-27f144de9a2b),[images](#mw%5F0a51db93-cccf-4b2f-ae4c-6724cbf5ec46%5Fsep%5Fmw%5F99c47767-d581-463d-a32e-fd1427314607)) predicts the responses of the specified images using the trained networknet.

example

[Y](#d126e207163) = predict([net](#mw%5F63c849d9-9878-4f95-98ca-27f144de9a2b),[sequences](#mw%5F0a51db93-cccf-4b2f-ae4c-6724cbf5ec46%5Fsep%5Fmw%5F86d8ee87-82c1-4872-85eb-a67e710ba850)) predicts the responses of the specified sequences using the trained networknet.

[Y](#d126e207163) = predict([net](#mw%5F63c849d9-9878-4f95-98ca-27f144de9a2b),[features](#mw%5F0a51db93-cccf-4b2f-ae4c-6724cbf5ec46%5Fsep%5Fmw%5F783e4ab8-2920-4f09-94e7-019a462a52c0)) predicts the responses of the specified feature data using the trained networknet.

[Y](#d126e207163) = predict([net](#mw%5F63c849d9-9878-4f95-98ca-27f144de9a2b),[X1,...,XN](#mw%5F0a51db93-cccf-4b2f-ae4c-6724cbf5ec46%5Fsep%5Fmw%5Fca2bcb5b-09ef-4e31-b103-c4100ac1a741)) predicts the responses for the data in the numeric or cell arraysX1, …, XN for the multi-input networknet. The input Xi corresponds to the network input net.InputNames(i).

[Y](#d126e207163) = predict([net](#mw%5F63c849d9-9878-4f95-98ca-27f144de9a2b),[mixed](#mw%5F0a51db93-cccf-4b2f-ae4c-6724cbf5ec46%5Fsep%5Fmw%5Fb88600ab-1c39-4500-aaa1-813282327d59)) predicts the responses using the trained network net with multiple inputs of mixed data types.

[[Y1,...,YM](#mw%5Ff60e3f2b-2766-46ca-a730-76219f14102a)] = predict(___) predicts responses for the M outputs of a multi-output network using any of the previous input arguments. The outputYj corresponds to the network outputnet.OutputNames(j). To return categorical outputs for the classification output layers, set the ReturnCategorical option to 1 (true).

___ = predict(___,[Name=Value](#namevaluepairarguments)) predicts the responses with additional options specified by one or more name-value arguments.

Tip

• Use the predict function to predict responses using a regression network or to classify data using a multi-output network. To classify data using a single-output classification network, use the classify function.
• When you make predictions with sequences of different lengths, the mini-batch size can impact the amount of padding added to the input data, which can result in different predicted values. Try using different values to see which works best with your network. To specify mini-batch size and padding options, use the MiniBatchSize and SequenceLength options, respectively.
• For predicting responses using dlnetwork objects, see predict.

Examples

collapse all

Predict Numeric Responses Using Trained Convolutional Neural Network

Predict numeric responses using a trained convolutional neural network

Load a pretrained SqueezeNet neural network.

Read and display an example image.

I = imread("peppers.png"); figure imshow(I)

Resize the image to the network input size.

sz = net.Layers(1).InputSize; I = imresize(I,sz(1:2));

Make predictions using the predict function. Because the network is a classification network, the output of thepredict function is the class probabilities. For regression networks, the function outputs the predicted numeric responses.

Display the probabilities in a bar chart.

figure bar(Y) xlabel("Class") ylabel("Probability")

Input Arguments

collapse all

net — Trained network

SeriesNetwork object | DAGNetwork object

Trained network, specified as a SeriesNetwork or a DAGNetwork object. You can get a trained network by importing a pretrained network (for example, by using thegooglenet function) or by training your own network using trainNetwork.

For information on predicting responses using dlnetwork objects, see predict.

images — Image data

datastore | numeric array | table

Image data, specified as one of the following.

When you use a datastore with networks with multiple inputs, the datastore must be aTransformedDatastore orCombinedDatastore object.

Tip

For sequences of images, for example, video data, use the sequences input argument.

Datastore

Datastores read mini-batches of images and responses. Use datastores when you have data that does not fit in memory or when you want to resize the input data.

These datastores are directly compatible with predict for image data.:

• ImageDatastore
• AugmentedImageDatastore
• CombinedDatastore
• TransformedDatastore
• Custom mini-batch datastore. For details, see Develop Custom Mini-Batch Datastore.

Tip

Use augmentedImageDatastore for efficient preprocessing of images for deep learning, including image resizing. Do not use the ReadFcn option ofImageDatastore objects.

ImageDatastore allows batch reading of JPG or PNG image files using prefetching. If you set the ReadFcn option to a custom function, then ImageDatastore does not prefetch and is usually significantly slower.

You can use other built-in datastores for making predictions by using the transform andcombine functions. These functions can convert the data read from datastores to the format required by classify.

The required format of the datastore output depends on the network architecture.

The format of the predictors depends on the type of data.

For more information, see Datastores for Deep Learning.

Numeric Array

For data that fits in memory and does not require additional processing like augmentation, you can specify a data set of images as a numeric array.

The size and shape of the numeric array depends on the type of image data.

Table

As an alternative to datastores or numeric arrays, you can also specify images in a table.

When you specify images in a table, each row in the table corresponds to an observation.

For image input, the predictors must be in the first column of the table, specified as one of the following:

• Absolute or relative file path to an image, specified as a character vector
• 1-by-1 cell array containing a_h_-by-w_-by-c numeric array representing a 2-D image, where h, w, and_c correspond to the height, width, and number of channels of the image, respectively

Tip

This argument supports complex-valued predictors. To input complex-valued data into aSeriesNetwork or DAGNetwork object, theSplitComplexInputs option of the input layer must be1 (true).

sequences — Sequence or time series data

datastore | cell array of numeric arrays | numeric array

Sequence or time series data, specified as one of the following.

Datastore

Datastores read mini-batches of sequences and responses. Use datastores when you have data that does not fit in memory or when you want to apply transformations to the data.

These datastores are directly compatible with predict for sequence data:

• CombinedDatastore
• TransformedDatastore
• Custom mini-batch datastore. For details, see Develop Custom Mini-Batch Datastore.

You can use other built-in datastores for making predictions by using the transform and combine functions. These functions can convert the data read from datastores to the table or cell array format required bypredict. For example, you can transform and combine data read from in-memory arrays and CSV files using anArrayDatastore and an TabularTextDatastore object, respectively.

The datastore must return data in a table or cell array. Custom mini-batch datastores must output tables.

The format of the predictors depends on the type of data.

For predictors returned in tables, the elements must contain a numeric scalar, a numeric row vector, or a 1-by-1 cell array containing a numeric array.

For more information, see Datastores for Deep Learning.

Numeric or Cell Array

For data that fits in memory and does not require additional processing like custom transformations, you can specify a single sequence as a numeric array or a data set of sequences as a cell array of numeric arrays.

For cell array input, the cell array must be an_N_-by-1 cell array of numeric arrays, where_N_ is the number of observations. The size and shape of the numeric array representing a sequence depends on the type of sequence data.

Tip

This argument supports complex-valued predictors. To input complex-valued data into a SeriesNetwork or DAGNetwork object, theSplitComplexInputs option of the input layer must be1 (true).

features — Feature data

datastore | numeric array | table

Feature data, specified as one of the following.

Datastore

Datastores read mini-batches of feature data and responses. Use datastores when you have data that does not fit in memory or when you want to apply transformations to the data.

These datastores are directly compatible with predict for feature data:

• CombinedDatastore
• TransformedDatastore
• Custom mini-batch datastore. For details, see Develop Custom Mini-Batch Datastore.

You can use other built-in datastores for making predictions by using the transform andcombine functions. These functions can convert the data read from datastores to the table or cell array format required by predict. For more information, see Datastores for Deep Learning.

For networks with multiple inputs, the datastore must be a TransformedDatastore orCombinedDatastore object.

The datastore must return data in a table or a cell array. Custom mini-batch datastores must output tables. The format of the datastore output depends on the network architecture.

The predictors must be c_-by-1 column vectors, where_c is the number of features.

For more information, see Datastores for Deep Learning.

Table

For feature data that fits in memory and does not require additional processing like custom transformations, you can specify feature data and responses as a table.

Each row in the table corresponds to an observation. The arrangement of predictors in the table columns depends on the type of task.

Numeric Array

For feature data that fits in memory and does not require additional processing like custom transformations, you can specify feature data as a numeric array.

The numeric array must be an_N_-by-numFeatures numeric array, where_N_ is the number of observations and numFeatures is the number of features of the input data.

Tip

This argument supports complex-valued predictors. To input complex-valued data into aSeriesNetwork or DAGNetwork object, theSplitComplexInputs option of the input layer must be1 (true).

X1,...,XN — Numeric or cell arrays for networks with multiple inputs

numeric array | cell array

Numeric or cell arrays for networks with multiple inputs.

For image, sequence, and feature predictor input, the format of the predictors must match the formats described in the images,sequences, or features argument descriptions, respectively.

For an example showing how to train a network with multiple inputs, see Train Network on Image and Feature Data.

To input complex-valued data into a DAGNetwork orSeriesNetwork object, the SplitComplexInputs option of the input layer must be 1 (true).

Data Types: single | double | int8 | int16 | int32 | int64 | uint8 | uint16 | uint32 | uint64 | cell
Complex Number Support: Yes

mixed — Mixed data

TransformedDatastore | CombinedDatastore | custom mini-batch datastore

Mixed data, specified as one of the following.

You can use other built-in datastores for making predictions by using the transform and combine functions. These functions can convert the data read from datastores to the table or cell array format required by predict. For more information, see Datastores for Deep Learning.

The datastore must return data in a table or a cell array. Custom mini-batch datastores must output tables. The format of the datastore output depends on the network architecture.

For image, sequence, and feature predictor input, the format of the predictors must match the formats described in the images, sequences, orfeatures argument descriptions, respectively.

For an example showing how to train a network with multiple inputs, see Train Network on Image and Feature Data.

Tip

To convert a numeric array to a datastore, use arrayDatastore.

Name-Value Arguments

Specify optional pairs of arguments asName1=Value1,...,NameN=ValueN, where Name is the argument name and Value is the corresponding value. Name-value arguments must appear after other arguments, but the order of the pairs does not matter.

Before R2021a, use commas to separate each name and value, and enclose Name in quotes.

Example: MiniBatchSize=256 specifies the mini-batch size as 256.

Size of mini-batches to use for prediction, specified as a positive integer. Larger mini-batch sizes require more memory, but can lead to faster predictions.

When you make predictions with sequences of different lengths, the mini-batch size can impact the amount of padding added to the input data, which can result in different predicted values. Try using different values to see which works best with your network. To specify mini-batch size and padding options, use the MiniBatchSize and SequenceLength options, respectively.

Data Types: single | double | int8 | int16 | int32 | int64 | uint8 | uint16 | uint32 | uint64

Acceleration — Performance optimization

"auto" (default) | "mex" | "none"

Performance optimization, specified as one of the following:

• "auto" — Automatically apply a number of optimizations suitable for the input network and hardware resources.
• "mex" — Compile and execute a MEX function. This option is available only when you use a GPU. Using a GPU requires a Parallel Computing Toolbox license and a supported GPU device. For information about supported devices, seeGPU Computing Requirements (Parallel Computing Toolbox). If Parallel Computing Toolbox or a suitable GPU is not available, then the software returns an error.
• "none" — Disable all acceleration.

If Acceleration is "auto", then MATLAB® applies a number of compatible optimizations and does not generate a MEX function.

The "auto" and "mex" options can offer performance benefits at the expense of an increased initial run time. Subsequent calls with compatible parameters are faster. Use performance optimization when you plan to call the function multiple times using new input data.

The "mex" option generates and executes a MEX function based on the network and parameters used in the function call. You can have several MEX functions associated with a single network at one time. Clearing the network variable also clears any MEX functions associated with that network.

The "mex" option supports networks that contain the layers listed on the Supported Layers (GPU Coder) page, except forsequenceInputLayer objects.

The "mex" option is available when you use a single GPU.

To use the "mex" option, you must have a C/C++ compiler installed and the GPU Coder™ Interface for Deep Learning support package. Install the support package using the Add-On Explorer in MATLAB. For setup instructions, see MEX Setup (GPU Coder). GPU Coder is not required.

For quantized networks, the "mex" option requires a CUDA® enabled NVIDIA® GPU with compute capability 6.1, 6.3, or higher.

MATLAB Compiler™ does not support deploying networks when you use the"mex" option.

ExecutionEnvironment — Hardware resource

"auto" (default) | "gpu" | "cpu" | "multi-gpu" | "parallel"

Hardware resource, specified as one of the following:

• "auto" — Use a GPU if one is available; otherwise, use the CPU.
• "gpu" — Use the GPU. Using a GPU requires a Parallel Computing Toolbox license and a supported GPU device. For information about supported devices, seeGPU Computing Requirements (Parallel Computing Toolbox). If Parallel Computing Toolbox or a suitable GPU is not available, then the software returns an error.
• "cpu" — Use the CPU.
• "multi-gpu" — Use multiple GPUs on one machine, using a local parallel pool based on your default cluster profile. If there is no current parallel pool, the software starts a parallel pool with pool size equal to the number of available GPUs.
• "parallel" — Use a local or remote parallel pool based on your default cluster profile. If there is no current parallel pool, the software starts one using the default cluster profile. If the pool has access to GPUs, then only workers with a unique GPU perform computation. If the pool does not have GPUs, then computation takes place on all available CPU workers instead.

For more information on when to use the different execution environments, see Scale Up Deep Learning in Parallel, on GPUs, and in the Cloud.

The "gpu", "multi-gpu", and"parallel" options require Parallel Computing Toolbox. To use a GPU for deep learning, you must also have a supported GPU device. For information on supported devices, seeGPU Computing Requirements (Parallel Computing Toolbox). If you choose one of these options and Parallel Computing Toolbox or a suitable GPU is not available, then the software returns an error.

To make predictions in parallel with networks with recurrent layers (by settingExecutionEnvironment to either "multi-gpu" or "parallel"), the SequenceLength option must be "shortest" or "longest".

Networks with custom layers that contain State parameters do not support making predictions in parallel.

ReturnCategorical — Option to return categorical labels

0 (false) (default) | 1 (true)

Option to return categorical labels, specified as 0 (false) or 1 (true).

If ReturnCategorical is 1 (true), then the function returns categorical labels for classification output layers. Otherwise, the function returns the prediction scores for classification output layers.

SequenceLength — Option to pad, truncate, or split sequences

"longest" (default) | "shortest" | positive integer

Option to pad, truncate, or split sequences, specified as one of these values:

• "longest" — Pad sequences in each mini-batch to have the same length as the longest sequence. This option does not discard any data, though padding can introduce noise to the neural network.
• "shortest" — Truncate sequences in each mini-batch to have the same length as the shortest sequence. This option ensures that no padding is added, at the cost of discarding data.
• Positive integer — For each mini-batch, pad the sequences to the length of the longest sequence in the mini-batch, and then split the sequences into smaller sequences of the specified length. If splitting occurs, then the software creates extra mini-batches. If the specified sequence length does not evenly divide the sequence lengths of the data, then the mini-batches containing the ends those sequences have length shorter than the specified sequence length. Use this option if the full sequences do not fit in memory. Alternatively, try reducing the number of sequences per mini-batch by setting the MiniBatchSize option to a lower value.

To learn more about the effect of padding and truncating sequences, see Sequence Padding and Truncation.

Data Types: single | double | int8 | int16 | int32 | int64 | uint8 | uint16 | uint32 | uint64 | char | string

SequencePaddingDirection — Direction of padding or truncation

"right" (default) | "left"

Direction of padding or truncation, specified as one of the following:

• "right" — Pad or truncate sequences on the right. The sequences start at the same time step and the software truncates or adds padding to the end of the sequences.
• "left" — Pad or truncate sequences on the left. The software truncates or adds padding to the start of the sequences so that the sequences end at the same time step.

Because recurrent layers process sequence data one time step at a time, when the recurrent layer OutputMode property is "last", any padding in the final time steps can negatively influence the layer output. To pad or truncate sequence data on the left, set the SequencePaddingDirection option to "left".

For sequence-to-sequence neural networks (when the OutputMode property is "sequence" for each recurrent layer), any padding in the first time steps can negatively influence the predictions for the earlier time steps. To pad or truncate sequence data on the right, set the SequencePaddingDirection option to "right".

To learn more about the effect of padding and truncating sequences, see Sequence Padding and Truncation.

SequencePaddingValue — Value to pad sequences

0 (default) | scalar

Value by which to pad input sequences, specified as a scalar.

Do not pad sequences with NaN, because doing so can propagate errors throughout the neural network.

Data Types: single | double | int8 | int16 | int32 | int64 | uint8 | uint16 | uint32 | uint64

Output Arguments

collapse all

Y — Predicted responses

numeric array | categorical array | cell array

Predicted responses, returned as a numeric array, a categorical array, or a cell array. The format of Y depends on the type of problem.

The following table describes the format for regression problems.

For sequence-to-sequence regression problems with one observation,sequences can be a matrix. In this case,Y is a matrix of responses.

If ReturnCategorical is 0 (false) and the output layer of the network is a classification layer, thenY is the predicted classification scores. This table describes the format of the scores for classification tasks.

If ReturnCategorical is 1 (true), and the output layer of the network is a classification layer, thenY is a categorical vector or a cell array of categorical vectors. This table describes the format of the labels for classification tasks.

Y1,...,YM — Predicted scores or responses of networks with multiple outputs

numeric array | categorical array | cell array

Predicted scores or responses of networks with multiple outputs, returned as numeric arrays, categorical arrays, or cell arrays.

Each output Yj corresponds to the network outputnet.OutputNames(j) and has format as described in theY output argument.

Algorithms

collapse all

Floating-Point Arithmetic

When you train a neural network using the trainnet or trainNetwork functions, or when you use prediction or validation functions with DAGNetwork and SeriesNetwork objects, the software performs these computations using single-precision, floating-point arithmetic. Functions for prediction and validation include predict, classify, and activations. The software uses single-precision arithmetic when you train neural networks using both CPUs and GPUs.

Reproducibility

To provide the best performance, deep learning using a GPU in MATLAB is not guaranteed to be deterministic. Depending on your network architecture, under some conditions you might get different results when using a GPU to train two identical networks or make two predictions using the same network and data.

Alternatives

For networks with a single classification layer only, you can compute the predicted classes and the predicted scores from a trained network using the classify function.

To compute the activations from a network layer, use the activations function.

For recurrent networks such as LSTM networks, you can make predictions and update the network state using classifyAndUpdateState and predictAndUpdateState.

References

[1] Kudo, Mineichi, Jun Toyama, and Masaru Shimbo. “Multidimensional Curve Classification Using Passing-through Regions.” Pattern Recognition Letters 20, no. 11–13 (November 1999): 1103–11. https://doi.org/10.1016/S0167-8655(99)00077-X.

Extended Capabilities

C/C++ Code Generation

Generate C and C++ code using MATLAB® Coder™.

Usage notes and limitations:

• C++ code generation supports the following syntaxes:
  • Y = predict(net,images), whereimages is a numeric array
  • Y = predict(net,sequences), wheresequences is a cell array
  • Y = predict(net,features), wherefeatures is a numeric array
  • [Y1,...,YM] = predict(__) using any of the previous syntaxes
  • __ = predict(__,Name=Value) using any of the previous syntaxes
• For numeric inputs, the input must not have a variable size. The size must be fixed at code generation time.
• For vector sequence inputs, the number of features must be a constant during code generation. The sequence length can be variable sized.
• For image sequence inputs, the height, width, and the number of channels must be a constant during code generation.
• Only the MiniBatchSize,ReturnCategorical,SequenceLength,SequencePaddingDirection, andSequencePaddingValue name-value pair arguments are supported for code generation. All name-value pairs must be compile-time constants.
• Only the "longest" and"shortest" options of theSequenceLength name-value pair is supported for code generation.
• If ReturnCategorical is 1 (true) and you use a GCC C/C++ compiler version 8.2 or above, you might get a -Wstringop-overflow warning.
• Code generation for Intel® MKL-DNN target does not support the combination ofSequenceLength="longest",SequencePaddingDirection="left", andSequencePaddingValue=0 name-value arguments.

For more information about generating code for deep learning neural networks, seeWorkflow for Deep Learning Code Generation with MATLAB Coder (MATLAB Coder).

GPU Code Generation

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

Usage notes and limitations:

• GPU code generation supports the following syntaxes:
  • Y = predict(net,images), whereimages is a numeric array
  • Y = predict(net,sequences), wheresequences is a cell array or numeric array
  • Y = predict(net,features), wherefeatures is a numeric array
  • [Y1,...,YM] = predict(__) using any of the previous syntaxes
  • __ = predict(__,Name=Value) using any of the previous syntaxes
• For numeric inputs, the input must not have variable size. The size must be fixed at code generation time.
• GPU code generation does not support gpuArray inputs to the predict function.
• The cuDNN library supports vector and 2-D image sequences. The TensorRT library support only vector input sequences. The ARM® Compute Library for GPU does not support recurrent networks.
• For vector sequence inputs, the number of features must be a constant during code generation. The sequence length can be variable sized.
• For image sequence inputs, the height, width, and the number of channels must be a constant during code generation.
• Only the MiniBatchSize,ReturnCategorical,SequenceLength,SequencePaddingDirection, andSequencePaddingValue name-value pair arguments are supported for code generation. All name-value pairs must be compile-time constants.
• Only the "longest" and"shortest" option of theSequenceLength name-value pair is supported for code generation.
• GPU code generation for the predict function supports inputs that are defined as half-precision floating point data types. For more information, see half (GPU Coder).
• If ReturnCategorical is set to1 (true) and you use a GCC C/C++ compiler version 8.2 or above, you might get a -Wstringop-overflow warning.

Automatic Parallel Support

Accelerate code by automatically running computation in parallel using Parallel Computing Toolbox™.

To run computations in parallel, set the ExecutionEnvironment option to "multi-gpu" or "parallel".

For details, see Scale Up Deep Learning in Parallel, on GPUs, and in the Cloud.

GPU Arrays

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

• The ExecutionEnvironment option must be"auto" or "gpu" when the input data is:
  • A gpuArray
  • A cell array containing gpuArray objects
  • A table containing gpuArray objects
  • A datastore that outputs cell arrays containinggpuArray objects
  • A datastore that outputs tables containinggpuArray objects

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

Version History

Introduced in R2016a

expand all

R2024a: Not recommended

Starting in R2024a, DAGNetwork and SeriesNetwork objects are not recommended, use dlnetwork objects instead. This recommendation means that the predict function is also not recommended. Use the minibatchpredict function or the predict (dlnetwork) function instead.

There are no plans to remove support for DAGNetwork andSeriesNetwork objects. However, dlnetwork objects have these advantages and are recommended instead:

• dlnetwork objects are a unified data type that supports network building, prediction, built-in training, visualization, compression, verification, and custom training loops.
• dlnetwork objects support a wider range of network architectures that you can create or import from external platforms.
• The trainnet function supports dlnetwork objects, which enables you to easily specify loss functions. You can select from built-in loss functions or specify a custom loss function.
• Training and prediction with dlnetwork objects is typically faster than LayerGraph and trainNetwork workflows.

To convert a trained DAGNetwork or SeriesNetwork object to a dlnetwork object, use the dag2dlnetwork function.

This table shows a typical usage of the predict function and how to update your code to use dlnetwork objects instead.

R2022b: Prediction functions pad mini-batches to length of longest sequence before splitting when you specify SequenceLength option as an integer

Starting in R2022b, when you make predictions with sequence data using thepredict, classify,predictAndUpdateState, classifyAndUpdateState, and activations functions and the SequenceLength option is an integer, the software pads sequences to the length of the longest sequence in each mini-batch and then splits the sequences into mini-batches with the specified sequence length. If SequenceLength does not evenly divide the sequence length of the mini-batch, then the last split mini-batch has a length shorter thanSequenceLength. This behavior prevents time steps that contain only padding values from influencing predictions.

In previous releases, the software pads mini-batches of sequences to have a length matching the nearest multiple of SequenceLength that is greater than or equal to the mini-batch length and then splits the data. To reproduce this behavior, manually pad the input data such that the mini-batches have the length of the appropriate multiple of SequenceLength. For sequence-to-sequence workflows, you may also need to manually remove time steps of the output that correspond to padding values.