nasnetmobile

Pretrained NASNet-Mobile convolutional neural network

• 

×

Syntax

net = nasnetmobile

Description

NASNet-Mobile is a convolutional neural network that is trained on more than a million images from the ImageNet database [1]. The network 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 224-by-224. For more pretrained networks in MATLAB^®, see Pretrained Deep Neural Networks.

You can use classify to classify new images using the NASNet-Mobile model. Follow the steps of Classify Image Using GoogLeNet and replace GoogLeNet with NASNet-Mobile.

To retrain the network on a new classification task, follow the steps of Train Deep Learning Network to Classify New Images and load NASNet-Mobile instead of GoogLeNet.

net = nasnetmobile returns a pretrained NASNet-Mobile convolutional neural network.

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

Examples

Download NASNet-Mobile Support Package

Download and install the Deep Learning Toolbox Model for NASNet-Mobile Network support package.

Type nasnetmobile at the command line.

nasnetmobile

If the Deep Learning Toolbox Model for NASNet-Mobile 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 nasnetmobile at the command line. If the required support package is installed, then the function returns a DAGNetwork object.

nasnetmobile

ans = 

  DAGNetwork with properties:

         Layers: [914×1 nnet.cnn.layer.Layer]
    Connections: [1073×2 table]

Visualize the network using Deep Network Designer.

deepNetworkDesigner(nasnetmobile)

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

If you need to download the network, then click Install to open the Add-On Explorer.

Transfer Learning with NASNet-Mobile

You can use transfer learning to retrain the network to classify a new set of images.

Open the example Train Deep Learning Network to Classify New Images. The original example uses the GoogLeNet pretrained network. To perform transfer learning using a different network, load your desired pretrained network and follow the steps in the example.

Load the NASNet-Mobile network instead of GoogLeNet.

net = nasnetmobile

Follow the remaining steps in the example to retrain your network. You must replace the last learnable layer and the classification layer in your network with new layers for training. The example shows you how to find which layers to replace.

Output Arguments

net — Pretrained NASNet-Mobile convolutional neural network

DAGNetwork object

Pretrained NASNet-Mobile convolutional neural network, returned as a DAGNetwork object.

References

[1] ImageNet. http://www.image-net.org

[2] Zoph, Barret, Vijay Vasudevan, Jonathon Shlens, and Quoc V. Le. "Learning Transferable Architectures for Scalable Image Recognition ." arXiv preprint arXiv:1707.07012 2, no. 6 (2017).

Extended Capabilities

C/C++ Code Generation

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

For code generation, you can load the network by using the syntax net = nasnetmobile or by passing the nasnetmobile function to coder.loadDeepLearningNetwork (MATLAB Coder). For example: net = coder.loadDeepLearningNetwork('nasnetmobile')

For more information, see Load Pretrained Networks for Code Generation (MATLAB Coder).

GPU Code Generation

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

Usage notes and limitations:

For code generation, you can load the network by using the syntax net = nasnetmobile or by passing the nasnetmobile function to coder.loadDeepLearningNetwork (GPU Coder). For example: net = coder.loadDeepLearningNetwork('nasnetmobile')

For more information, see Load Pretrained Networks for Code Generation (GPU Coder).