Main Content


(Not recommended) Pretrained Inception-ResNet-v2 convolutional neural network

  • Inception-ResNet-v2 network architecture

inceptionresnetv2 is not recommended. Use the imagePretrainedNetwork function instead and specify the "inceptionresnetv2" model. For more information, see Version History.


Inception-ResNet-v2 is a convolutional neural network that is trained on more than a million images from the ImageNet database [1]. The network is 164 layers deep and can classify images into 1000 object categories, such as keyboard, mouse, pencil, and many animals. As a result, the network has learned rich feature representations for a wide range of images. The network has an image input size of 299-by-299. For more pretrained networks in MATLAB®, see Pretrained Deep Neural Networks.


net = inceptionresnetv2 returns a pretrained Inception-ResNet-v2 network.

This function requires the Deep Learning Toolbox™ Model for Inception-ResNet-v2 Network support package. If this support package is not installed, then the function provides a download link.


collapse all

Download and install the Deep Learning Toolbox Model for Inception-ResNet-v2 Network support package.

Type inceptionresnetv2 at the command line.


If the Deep Learning Toolbox Model for Inception-ResNet-v2 Network support package is not installed, then the function provides a link to the required support package in the Add-On Explorer. To install the support package, click the link, and then click Install. Check that the installation is successful by typing inceptionresnetv2 at the command line. If the required support package is installed, then the function returns a DAGNetwork object.

net = inceptionresnetv2
net = 

  DAGNetwork with properties:

         Layers: [824×1 nnet.cnn.layer.Layer]
    Connections: [921×2 table]
     InputNames: {'input_1'}
    OutputNames: {'ClassificationLayer_predictions'}

Visualize the network using Deep Network Designer.


Explore other pretrained neural networks in Deep Network Designer by clicking New.

Deep Network Designer start page showing available pretrained neural networks

If you need to download a neural network, pause on the desired neural network and click Install to open the Add-On Explorer.

Output Arguments

collapse all

Pretrained Inception-ResNet-v2 convolutional neural network, returned as a DAGNetwork object.


[1] ImageNet.

[2] Szegedy, Christian, Sergey Ioffe, Vincent Vanhoucke, and Alexander A. Alemi. "Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning." In AAAI, vol. 4, p. 12. 2017.

Extended Capabilities

Version History

Introduced in R2017b

collapse all

R2024a: Not Recommended

inceptionresnetv2 is not recommended. Use the imagePretrainedNetwork function instead and specify "inceptionresnetv2" as the model.

There are no plans to remove support for the inceptionresnetv2 function. However, the imagePretrainedNetwork function has additional functionality that helps with transfer learning workflows. For example, you can specify the number of classes in your data using the numClasses option, and the function returns a network that is ready for retraining without the need for modification.

The imagePretrainedNetwork function returns the network as a dlnetwork object, which does not store the class names, To get the class names of the pretrained network, use the second output argument of the imagePretrainedNetwork function.

This table shows some typical usages of the inceptionresnetv2 function and how to update your code to use the imagePretrainedNetwork function instead.

Not RecommendedRecommended
net = inceptionresnetv2;[net,classNames] = imagePretrainedNetwork("inceptionresnetv2");
net = inceptionresnetv2(Weights="none");net = imagePretrainedNetwork("inceptionresnetv2",Weights="none");

The imagePretrainedNetwork returns a dlnetwork object, which also has these advantages:

  • 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 train a neural network specified as a dlnetwork object, use the trainnet function.