importTensorFlowNetwork

Import pretrained TensorFlow network

Since R2021a

Syntax

net = importTensorFlowNetwork(modelFolder)

net = importTensorFlowNetwork(modelFolder,Name,Value)

Description

net = importTensorFlowNetwork(modelFolder) imports a pretrained TensorFlow™ network from the folder modelFolder, which contains the model in the saved model format (compatible only with TensorFlow 2). The function can import TensorFlow networks created with the TensorFlow-Keras sequential or functional API. importTensorFlowNetwork imports the layers defined in the saved_model.pb file and the learned weights contained in the variables subfolder, and returns the network net as a DAGNetwork or dlnetwork object.

importTensorFlowNetwork requires the Deep Learning Toolbox™ Converter for TensorFlow Models support package. If this support package is not installed, then importTensorFlowNetwork provides a download link.

Note

importTensorFlowNetwork tries to generate a custom layer when you import a custom TensorFlow layer or when the software cannot convert a TensorFlow layer into an equivalent built-in MATLAB^® layer. For a list of layers for which the software supports conversion, see TensorFlow-Keras Layers Supported for Conversion into Built-In MATLAB Layers.

importTensorFlowNetwork saves the generated custom layers and the associated TensorFlow operators in the package +modelFolder.

importTensorFlowNetwork does not automatically generate a custom layer for each TensorFlow layer that is not supported for conversion into a built-in MATLAB layer. For more information on how to handle unsupported layers, see Tips.

net = importTensorFlowNetwork(modelFolder,Name,Value) imports the pretrained TensorFlow network with additional options specified by one or more name-value arguments. For example, 'OutputLayerType','classification' imports the network as a DAGNetwork with a classification output layer appended to the end of the imported network architecture.

Examples

Import TensorFlow Network as DAGNetwork to Classify Image

Import a pretrained TensorFlow network in the saved model format as a DAGNetwork object, and use the imported network to classify an image.

Specify the model folder.

if ~exist('digitsDAGnet','dir')
    unzip('digitsDAGnet.zip')
end
modelFolder = './digitsDAGnet';

Specify the class names.

classNames = {'0','1','2','3','4','5','6','7','8','9'};

Import a TensorFlow network in the saved model format. By default, importTensorFlowNetwork imports the network as a DAGNetwork object. Specify the output layer type for an image classification problem.

net = importTensorFlowNetwork(modelFolder,'OutputLayerType','classification','Classes',classNames)

Importing the saved model...
Translating the model, this may take a few minutes...
Finished translation. Assembling network...
Import finished.

net = 
  DAGNetwork with properties:

         Layers: [13×1 nnet.cnn.layer.Layer]
    Connections: [13×2 table]
     InputNames: {'input_1'}
    OutputNames: {'ClassificationLayer_activation_1'}

Plot the network architecture.

plot(net)
title('DAG Network Architecture')

Read the image you want to classify and display the size of the image. The image is a grayscale (one-channel) image with size 28-by-28 pixels.

digitDatasetPath = fullfile(toolboxdir('nnet'),'nndemos','nndatasets','DigitDataset');
I = imread(fullfile(digitDatasetPath,'5','image4009.png'));
size(I)

ans = 1×2

    28    28

Display the input size of the network. In this case, the image size matches the network input size. If they do not match, you must resize the image by using imresize(I, netInputSize(1:2)).

net.Layers(1).InputSize

ans = 1×3

    28    28     1

Classify the image using the pretrained network.

label = classify(net,I);

Display the image and the classification result.

imshow(I)
title(['Classification result ' char(label)])

Import TensorFlow Network as dlnetwork to Classify Image

Import a pretrained TensorFlow Network in the saved model format as a dlnetwork object, and use the imported network to predict class labels.

Specify the model folder.

if ~exist('digitsDAGnet','dir')
    unzip('digitsDAGnet.zip')
end
modelFolder = './digitsDAGnet';

Specify the class names.

classNames = {'0','1','2','3','4','5','6','7','8','9'};

Import a TensorFlow network in the saved model format as a dlnetwork object.

net = importTensorFlowNetwork(modelFolder,'TargetNetwork','dlnetwork')

Importing the saved model...
Translating the model, this may take a few minutes...
Finished translation. Assembling network...
Import finished.

net = 
  dlnetwork with properties:

         Layers: [12×1 nnet.cnn.layer.Layer]
    Connections: [12×2 table]
     Learnables: [6×3 table]
          State: [0×3 table]
     InputNames: {'input_1'}
    OutputNames: {'activation_1'}
    Initialized: 1

Read the image you want to classify and display the size of the image. The image is a grayscale (one-channel) image with size 28-by-28 pixels.

digitDatasetPath = fullfile(toolboxdir('nnet'),'nndemos','nndatasets','DigitDataset');
I = imread(fullfile(digitDatasetPath,'5','image4009.png'));
size(I)

ans = 1×2

    28    28

Display the input size of the network. In this case, the image size matches the network input size. If they do not match, you must resize the image by using imresize(I, netInputSize(1:2)).

netInputSize = net.Layers(1).InputSize

netInputSize = 1×3

    28    28     1

Convert the image to a dlarray. Format the images with the dimensions 'SSCB' (spatial, spatial, channel, batch). In this case, the batch size is 1 and you can omit it ('SSC').

I_dlarray = dlarray(single(I),'SSCB');

Classify the sample image and find the predicted label.

prob = predict(net,I_dlarray);
[~,label] = max(prob);

Display the image and the classification result.

imshow(I)
title(['Classification result ' classNames{label}]) 

Import TensorFlow Network with Autogenerated Custom Layers

Import a pretrained TensorFlow network in the saved model format as a DAGNetwork object, and use the imported network to classify an image. The imported network contains layers that are not supported for conversion into built-in MATLAB layers. The software automatically generates custom layers when you import these layers.

This example uses the helper function findCustomLayers. To view the code for this function, see Helper Function.

Specify the model folder.

if ~exist('digitsDAGnetwithnoise','dir')
    unzip('digitsDAGnetwithnoise.zip')
end
modelFolder = './digitsDAGnetwithnoise';

Specify the class names.

classNames = {'0','1','2','3','4','5','6','7','8','9'};

Import a TensorFlow network in the saved model format. By default, importTensorFlowNetwork imports the network as a DAGNetwork object. Specify the output layer type for an image classification problem.

net = importTensorFlowNetwork(modelFolder,'OutputLayerType','classification','Classes',classNames);

Importing the saved model...
Translating the model, this may take a few minutes...
Finished translation. Assembling network...
Import finished.

If the imported network contains layers not supported for conversion into built-in MATLAB layers, then importTensorFlowNetwork can automatically generate custom layers in place of these layers. importTensorFlowNetwork saves each generated custom layer to a separate .m file in the package +digitsDAGnetwithnoise in the current folder.

Find the indices of the automatically generated custom layers using the helper function findCustomLayers, and display the custom layers.

ind = findCustomLayers(net.Layers,'+digitsDAGnetwithnoise');
net.Layers(ind)

ans = 
  3×1 Layer array with layers:

     1   'concatenate_1'      Concatenate     digitsDAGnetwithnoise.kConcatenate1Layer3826
     2   'gaussian_noise_1'   GaussianNoise   digitsDAGnetwithnoise.kGaussianNoise1Layer3766
     3   'gaussian_noise_2'   GaussianNoise   digitsDAGnetwithnoise.kGaussianNoise2Layer3791

Plot the network architecture.

plot(net)
title('DAG Network Architecture')

Read the image you want to classify.

digitDatasetPath = fullfile(toolboxdir('nnet'),'nndemos','nndatasets','DigitDataset');
I = imread(fullfile(digitDatasetPath,'5','image4009.png'));

Classify the image using the pretrained network.

label = classify(net,I);

Display the image and the classification result.

imshow(I)
title(['Classification result ' char(label)])

Helper Function

This section provides the code of the helper function findCustomLayers used in this example. findCustomLayers returns the indices of the custom layers that importTensorFlowNetwork automatically generates.

function indices = findCustomLayers(layers,PackageName)

s = what(['.' filesep PackageName]);

indices = zeros(1,length(s.m));
for i = 1:length(layers)
    for j = 1:length(s.m)
        if strcmpi(class(layers(i)),[PackageName(2:end) '.' s.m{j}(1:end-2)])
            indices(j) = i;
        end
    end
end

end

Input Arguments

modelFolder — Name of TensorFlow model folder

character vector | string scalar

Name of the folder containing the TensorFlow model, specified as a character vector or string scalar. modelFolder must be in the current folder, or you must include a full or relative path to the folder. modelFolder must contain the file saved_model.pb, and the subfolder variables. It can also contain the subfolders assets and assets.extra.

• The file saved_model.pb contains the layer graph architecture and training options (for example, optimizer, losses, and metrics).

• The subfolder variables contains the weights learned by the pretrained TensorFlow network. By default, importTensorFlowNetwork imports the weights.

• The subfolder assets contains supplementary files (for example, vocabularies), which the layer graph can use. importTensorFlowNetwork does not import the files in assets.

• The subfolder assets.extra contains supplementary files (for example, information for users), which coexist with the layer graph.

Example: 'MobileNet'

Example: './MobileNet'

Name-Value Arguments

Specify optional pairs of arguments as Name1=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: importTensorFlowNetwork(modelFolder,'TargetNetwork','dagnetwork','OutputLayerType','classification') imports a network from modelFolder as a DAGNetwork object, saves the automatically generated custom layers in the package +modelFolder in the current folder, and appends a classification output layer to the end of the imported network architecture.

PackageName — Name of custom layers package

character vector | string scalar

Name of the package in which importTensorFlowNetwork saves custom layers, specified as a character vector or string scalar. importTensorFlowNetwork saves the custom layers package +PackageName in the current folder. If you do not specify 'PackageName', then importTensorFlowNetwork saves the custom layers in a package named +modelFolder in the current folder. For more information on packages, see Packages Create Namespaces.

importTensorFlowNetwork tries to generate a custom layer when you import a custom TensorFlow layer or when the software cannot convert a TensorFlow layer into an equivalent built-in MATLAB layer. importTensorFlowNetwork saves each generated custom layer to a separate .m file in +PackageName. To view or edit a custom layer, open the associated .m file. For more information on custom layers, see Custom Layers.

The package +PackageName can also contain the subpackage +ops. This subpackage contains MATLAB functions corresponding to TensorFlow operators (see Supported TensorFlow Operators) that are used in the automatically generated custom layers. importTensorFlowNetwork saves the associated MATLAB function for each operator in a separate .m file in the subpackage +ops. The object functions of dlnetwork, such as the predict function, use these operators when interacting with the custom layers.

Example: 'PackageName','MobileNet'

Example: 'PackageName','CustomLayers'

TargetNetwork — Target type of Deep Learning Toolbox network

'dagnetwork' (default) | 'dlnetwork'

Target type of Deep Learning Toolbox network, specified as 'dagnetwork' or 'dlnetwork'.

• Specify 'TargetNetwork as 'dagnetwork' to import the network as a DAGNetwork object. In this case, net must include an output layer specified by the TensorFlow saved model loss function or the name-value argument 'OutputLayerType'.

• Specify 'TargetNetwork as 'dlnetwork' to import the network as a dlnetwork object. In this case, net does not include an output layer.

Example: 'TargetNetwork','dlnetwork'

OutputLayerType — Type of output layer

'classification' | 'regression' | 'pixelclassification'

Type of output layer that importTensorFlowNetwork appends to the end of the imported network architecture, specified as 'classification', 'regression', or 'pixelclassification'. Appending a pixelClassificationLayer (Computer Vision Toolbox) object requires Computer Vision Toolbox™.

• If you specify 'TargetNetwork' as 'dagnetwork' and the saved model in modelFolder does not specify a loss function, you must assign a value to the name-value argument 'OutputLayerType'. A DAGNetwork object must have an output layer.

• If you specify 'TargetNetwork' as 'dlnetwork', importTensorFlowNetwork ignores the name-value argument 'OutputLayerType'. A dlnetwork object does not have an output layer.

Example: 'OutputLayerType','classification'

ImageInputSize — Size of input images

vector of two or three numerical values

Size of the input images for the network, specified as a vector of two or three numerical values corresponding to [height,width] for grayscale images and [height,width,channels] for color images, respectively. The network uses this information when the saved_model.pb file in modelFolder does not specify the input size.

Example: 'ImageInputSize',[28 28]

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 you specify a string array or cell array of character vectors str, then importTensorFlowNetwork sets the classes of the output layer to categorical(str,str). If Classes is 'auto', then importTensorFlowNetwork sets the classes to categorical(1:N), where N is the number of classes.

• If you specify 'TargetNetwork' as 'dagnetwork', importTensorFlowNetwork stores information on classes in the output layer of the DAGNetwork object.

• If you specify 'TargetNetwork' as 'dlnetwork', importTensorFlowNetwork ignores the name-value argument 'Classes'. A dlnetwork object does not have an output layer to store information on classes.

Example: 'Classes',{'0','1','3'}

Example: 'Classes',categorical({'dog','cat'})

Data Types: char | categorical | string | cell

Verbose — Indicator to display import progress information

true or 1 (default) | false or 0

Indicator to display import progress information in the command window, specified as a numeric or logical 1 (true) or 0 (false).

Example: 'Verbose','true'

Output Arguments

net — Pretrained TensorFlow network

DAGNetwork object | dlnetwork object

Pretrained TensorFlow network, returned as a DAGNetwork or dlnetwork object.

• Specify 'TargetNetwork as 'dagnetwork' to import the network as a DAGNetwork object. On the DAGNetwork object, you then predict class labels by using the classify function.

• Specify 'TargetNetwork as 'dlnetwork' to import the network as a dlnetwork object. On the dlnetwork object, you then predict class labels by using the predict function. Specify the input data as a dlarray using the correct data format (for more information, see the fmt argument of dlarray).

Limitations

• importTensorFlowNetwork supports TensorFlow versions v2.0 to 2.6.

More About

TensorFlow-Keras Layers Supported for Conversion into Built-In MATLAB Layers

importTensorFlowNetwork supports the following TensorFlow-Keras layer types for conversion into built-in MATLAB layers, with some limitations.

TensorFlow-Keras Layer	Corresponding Deep Learning Toolbox Layer
Add	additionLayer
Activation, with activation names: elu gelu relu linear softmax sigmoid swish tanh	Layers: eluLayer geluLayer reluLayer or clippedReluLayer None softmaxLayer sigmoidLayer swishLayer tanhLayer
Advanced activations: ELU Softmax ReLU LeakyReLU PReLu*	Layers: eluLayer softmaxLayer reluLayer, clippedReluLayer, or leakyReluLayer leakyReluLayer nnet.keras.layer.PreluLayer
AveragePooling1D	averagePooling1dLayer with PaddingValue specified as 'mean'
AveragePooling2D	averagePooling2dLayer with PaddingValue specified as 'mean'
BatchNormalization	batchNormalizationLayer
Bidirectional(LSTM(__))	bilstmLayer
Conv1D	convolution1dLayer
Conv2D	convolution2dLayer
Conv2DTranspose	transposedConv2dLayer
CuDNNGRU	gruLayer
CuDNNLSTM	lstmLayer
Dense	fullyConnectedLayer
DepthwiseConv2D	groupedConvolution2dLayer
Dropout	dropoutLayer
Embedding	wordEmbeddingLayer (Text Analytics Toolbox)
Flatten	nnet.keras.layer.FlattenCStyleLayer
GlobalAveragePooling1D	globalAveragePooling1dLayer
GlobalAveragePooling2D	globalAveragePooling2dLayer
GlobalMaxPool1D	globalMaxPooling1dLayer
GlobalMaxPool2D	globalMaxPooling2dLayer
GRU	gruLayer
Input	imageInputLayer, sequenceInputLayer, or featureInputLayer
LSTM	lstmLayer
MaxPool1D	maxPooling1dLayer
MaxPool2D	maxPooling2dLayer
Multiply	multiplicationLayer
SeparableConv2D	groupedConvolution2dLayer or convolution2dLayer
TimeDistributed	sequenceFoldingLayer before the wrapped layer, and sequenceUnfoldingLayer after the wrapped layer
UpSampling2D	resize2dLayer (Image Processing Toolbox)
UpSampling3D	resize3dLayer (Image Processing Toolbox)
ZeroPadding1D	nnet.keras.layer.ZeroPadding1DLayer
ZeroPadding2D	nnet.keras.layer.ZeroPadding2DLayer

* For a PReLU layer, importTensorFlowNetwork replaces a vector-valued scaling parameter with the average of the vector elements. You can change the parameter back to a vector after import. For an example, see Import Keras PReLU Layer.

Supported TensorFlow-Keras Loss Functions

importTensorFlowNetwork supports the following Keras loss functions:

• mean_squared_error

• categorical_crossentropy

• sparse_categorical_crossentropy

• binary_crossentropy

Supported TensorFlow Operators

importTensorFlowNetwork supports the following TensorFlow operators for conversion into MATLAB functions with dlarray support.

TensorFlow Operator	Corresponding MATLAB Function
Add	tfAdd
AddN	tfAddN
AddV2	tfAdd
All	tfAll
Assert	assert
AvgPool	tfAvgPool
BatchMatMulV2	tfBatchMatMulV2
BiasAdd	tfBiasAdd
BroadcastTo	tfBroadcastTo
Cast	tfCast
ConcatV2	tfCat
Const	None (translated to weights in custom layer)
Conv2D	tfConv2D
DepthToSpace	depthToSpace (Image Processing Toolbox)
DepthwiseConv2dNative	tfDepthwiseConv2D
Equal	==
Exp	exp
ExpandDims	tfExpandDims
Fill	tfFill
FusedBatchNormV3	tfBatchnorm
GatherV2	tfGather
Greater	gt>
GreaterEqual	ge, >=
Identity	None (translated to value assignment in custom layer)
IdentityN	tfIdentityN
L2Loss	tfL2Loss
LeakyRelu	leakyrelu
Less	lt, <
Log	log
MatMul	tfMatMul
MaxPool	tfMaxPool
Maximum	tfMaximum
Mean	tfMean
Minimum	tfMinimum
MirrorPad	tfMirrorPad
Mul	tfMul
Neg	minus, -
NonMaxSuppressionV5	tfNonMaxSuppressionV5
Pack	tfStack
Pad	tfPad
PadV2	tfPad
PartitionedCall	None (translated to function in custom layer methods)
Pow	power, .^
Prod	tfProd
RandomStandardNormal	tfRandomStandardNormal
Range	tfRange
ReadVariableOp	None (translated to value assignment in custom layer)
RealDiv	tfDiv
Relu	relu
Relu6	relu and min
Reshape	tfReshape
ResizeBilinear	dlresize (Image Processing Toolbox)
ResizeNearestNeighbor	dlresize (Image Processing Toolbox)
Rsqrt	sqrt
Select	tfSelect
Shape	tfShape
Sigmoid	sigmoid
Size	tfSize
Slice	tfSlice
Softmax	softmax
SpaceToDepth	spaceToDepth (Image Processing Toolbox)
Split	tfSplit
Square	.^2
Sqrt	sqrt
SquaredDifference	tfMul or tfSub
Squeeze	tfSqueeze
StatefulPartitionedCall	None (translated to function in custom layer methods)
StopGradient	tfStopGradient
StridedSlice	tfStridedSlice or tfSqueeze
Sub	tfSub
Sum	tfSum
Tanh	tanh
Tile	tfTile
Transpose	tfTranspose
Unpack	tfUnpack
Where	tfWhere

For more information on functions that operate on dlarray objects, see List of Functions with dlarray Support.

Generate Code for Imported Network

You can use MATLAB Coder™ or GPU Coder™ together with Deep Learning Toolbox to generate MEX, standalone CPU, CUDA^® MEX, or standalone CUDA code for an imported network. For more information, see Code Generation.

• Use MATLAB Coder with Deep Learning Toolbox to generate MEX or standalone CPU code that runs on desktop or embedded targets. You can deploy generated standalone code that uses the Intel^® MKL-DNN library or the ARM^® Compute library. Alternatively, you can generate generic C or C++ code that does not call third-party library functions. For more information, see Deep Learning with MATLAB Coder (MATLAB Coder).

• Use GPU Coder with Deep Learning Toolbox to generate CUDA MEX or standalone CUDA code that runs on desktop or embedded targets. You can deploy generated standalone CUDA code that uses the CUDA deep neural network library (cuDNN), the TensorRT™ high performance inference library, or the ARM Compute library for Mali GPU. For more information, see Deep Learning with GPU Coder (GPU Coder).

importTensorFlowNetwork returns the network net as a DAGNetwork or dlnetwork object. Both these objects support code generation. For more information on MATLAB Coder and GPU Coder support for Deep Learning Toolbox objects, see Supported Classes (MATLAB Coder) and Supported Classes (GPU Coder), respectively.

You can generate code for any imported network whose layers support code generation. For lists of the layers that support code generation with MATLAB Coder and GPU Coder, see Supported Layers (MATLAB Coder) and Supported Layers (GPU Coder), respectively. For more information on the code generation capabilities and limitations of each built-in MATLAB layer, see the Extended Capabilities section of the layer. For example, see Code Generation and GPU Code Generation of imageInputLayer.

Use Imported Network on GPU

importTensorFlowNetwork does not execute on a GPU. However, importTensorFlowNetwork imports a pretrained neural network for deep learning as a DAGNetwork or dlnetwork object, which you can use on a GPU.

• If you import the network as a DAGNetwork object, you can make predictions with the imported network on either a CPU or GPU by using classify. Specify the hardware requirements using the name-value argument ExecutionEnvironment. For networks with multiple outputs, use the predict function for DAGNetwork objects.

• If you import the network as a DAGNetwork object, you can make predictions with the imported network on either a CPU or GPU by using predict. Specify the hardware requirements using the name-value argument ExecutionEnvironment. If the network has multiple outputs, specify the name-value argument ReturnCategorical as true.

• If you import the network as a dlnetwork object, you can make predictions with the imported network on either a CPU or GPU by using predict. The function predict executes on the GPU if either the input data or network parameters are stored on the GPU.

  • If you use minibatchqueue to process and manage the mini-batches of input data, the minibatchqueue object converts the output to a GPU array by default if a GPU is available.

  • Use dlupdate to convert the learnable parameters of a dlnetwork object to GPU arrays.

    net = dlupdate(@gpuArray,net)

• You can train the imported network on either a CPU or GPU by using trainNetwork. To specify training options, including options for the execution environment, use the trainingOptions function. Specify the hardware requirements using the name-value argument ExecutionEnvironment. For more information on how to accelerate training, see Scale Up Deep Learning in Parallel, on GPUs, and in the Cloud.

Using a GPU requires a Parallel Computing Toolbox™ license and a supported GPU device. For information about supported devices, see GPU Computing Requirements (Parallel Computing Toolbox).

Tips

• If the imported network contains a layer not supported for conversion into a built-in MATLAB layer (see TensorFlow-Keras Layers Supported for Conversion into Built-In MATLAB Layers) and importTensorFlowNetwork does not generate a custom layer, then importTensorFlowNetwork returns an error. In this case, you can still use importTensorFlowLayers to import the network architecture.

• To use a pretrained network for prediction or transfer learning on new images, you must preprocess your images in the same way the images that were used to train the imported model were preprocessed. The most common preprocessing steps are resizing images, subtracting image average values, and converting the images from BGR format to RGB format.

  • To resize images, use imresize. For example, imresize(image,[227,227,3]).

  • To convert images from RGB to BGR format, use flip. For example, flip(image,3).

  For more information on preprocessing images for training and prediction, see Preprocess Images for Deep Learning.

• The members of the package +PackageName (custom layers and TensorFlow operators) are not accessible if the package parent folder is not on the MATLAB path. For more information, see Packages and the MATLAB Path.

• MATLAB uses one-based indexing, whereas Python^® uses zero-based indexing. In other words, the first element in an array has an index of 1 and 0 in MATLAB and Python, respectively. For more information on MATLAB indexing, see Array Indexing. In MATLAB, to use an array of indices (ind) created in Python, convert the array to ind+1.

• For more tips, see Tips on Importing Models from TensorFlow, PyTorch, and ONNX.

Alternative Functionality

Use importTensorFlowNetwork or importTensorFlowLayers to import a TensorFlow network in the saved model format [2]. Alternatively, if the network is in HDF5 or JSON format, use importKerasNetwork or importKerasLayers to import the network.

References

[1] TensorFlow. https://www.tensorflow.org/.

[2] Using the SavedModel format. https://www.tensorflow.org/guide/saved_model.

Version History

Introduced in R2021a

R2023a: importTensorFlowNetwork creates a custom layer for concatenation

The importTensorFlowNetwork function returns an autogenerated custom layer for theTensorFlow-Keras Concatenate layer instead of the built-in Deep Learning Toolbox layer concatenationLayer or depthConcatenationLayer. Previously, the function used concatenationLayer or depthConcatenationLayer and assumed a concatenation axis value based on the input layer of the network being imported. However, for some complex networks this assumption might not be true. Therefore, the software uses an autogenerated custom layer to perform the concatenation. The autogenerated custom layer ensures the correct translation of the TensorFlow-Keras Concatenate layer into MATLAB at runtime.