squeezenet

Pretrained SqueezeNet convolutional neural network

SqueezeNet is a convolutional neural network that is trained on more than a million images from the ImageNet database [1]. The network is 18 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. This function returns a SqueezeNet v1.1 network, which has similar accuracy to SqueezeNet v1.0 but requires fewer floating-point operations per prediction [3]. The network has an image input size of 227-by-227. For more pretrained networks in MATLAB^®, see Pretrained Convolutional Neural Networks.

You can use classify to classify new images using the SqueezeNet network. Follow the steps of Classify Image Using GoogLeNet and replace GoogLeNet with SqueezeNet.

To retrain the network on a new classification task, follow the steps of Train Deep Learning Network to Classify New Images. Load the SqueezeNet network instead of GoogLeNet and change the names of the layers that you replace to 'conv10' and 'ClassificationLayer_predictions', respectively. Because SqueezeNet does not have a fully connected layer in the end of the network, replace the 'conv10' layer with a new convolutional layer with numClasses filters and a filter size of 1.

Syntax

net = squeezenet

Description

net = squeezenet returns a pretrained SqueezeNet convolutional neural network.

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

Examples

Load SqueezeNet Network

Download and install the Deep Learning Toolbox Model for SqueezeNet Network support package.

Type squeezenet at the command line.

squeezenet

If the Deep Learning Toolbox Model for SqueezeNet 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 squeezenet at the command line. If the required support package is installed, then the function returns a DAGNetwork object.

net = squeezenet

net = 

  DAGNetwork with properties:

         Layers: [68×1 nnet.cnn.layer.Layer]
    Connections: [75×2 table]

Output Arguments

net — Pretrained SqueezeNet convolutional neural network

DAGNetwork object

Pretrained SqueezeNet convolutional neural network, returned as a DAGNetwork object.

References

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

[2] Iandola, Forrest N., Song Han, Matthew W. Moskewicz, Khalid Ashraf, William J. Dally, and Kurt Keutzer. "SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5 MB model size." arXiv preprint arXiv:1602.07360 (2016).

[3] https://github.com/DeepScale/SqueezeNet

Extended Capabilities

C/C++ Code Generation

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

For code generation, load the network by passing the squeezenet function to coder.loadDeepLearningNetwork. For example: net = coder.loadDeepLearningNetwork('squeezenet')

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