inceptionv3

Inception-v3 convolutional neural network

• 

×

Syntax

net = inceptionv3

net = inceptionv3('Weights','imagenet')

lgraph = inceptionv3('Weights','none')

Description

Inception-v3 is a convolutional neural network that is 48 layers deep. You can load a pretrained version of the network trained on more than a million images from the ImageNet database [1]. The pretrained 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 299-by-299. For more pretrained networks in MATLAB^®, see Pretrained Deep Neural Networks.

You can use classify to classify new images using the Inception-v3 model. Follow the steps of Classify Image Using GoogLeNet and replace GoogLeNet with Inception-v3.

To retrain the network on a new classification task, follow the steps of Train Deep Learning Network to Classify New Images and load Inception-v3 instead of GoogLeNet.

net = inceptionv3 returns an Inception-v3 network trained on the ImageNet database.

This function requires the Deep Learning Toolbox™ Model for Inception-v3 Network support package. If this support package is not installed, then the function provides a download link.

net = inceptionv3('Weights','imagenet') returns an Inception-v3 network trained on the ImageNet database. This syntax is equivalent to net = inceptionv3.

lgraph = inceptionv3('Weights','none') returns the untrained Inception-v3 network architecture. The untrained model does not require the support package.

Examples

Download Inception-v3 Support Package

Download and install the Deep Learning Toolbox Model for Inception-v3 Network support package.

Type inceptionv3 at the command line.

inceptionv3

If the Deep Learning Toolbox Model for Inception-v3 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 inceptionv3 at the command line. If the required support package is installed, then the function returns a DAGNetwork object.

inceptionv3

ans = 

  DAGNetwork with properties:

         Layers: [316×1 nnet.cnn.layer.Layer]
    Connections: [350×2 table]

Visualize the network using Deep Network Designer.

deepNetworkDesigner(inceptionv3)

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.

Output Arguments

net — Pretrained Inception-v3 convolutional neural network

DAGNetwork object

Pretrained Inception-v3 convolutional neural network, returned as a DAGNetwork object.

lgraph — Untrained Inception-v3 convolutional neural network architecture

LayerGraph object

Untrained Inception-v3 convolutional neural network architecture, returned as a LayerGraph object.

References

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

[2] Szegedy, Christian, Vincent Vanhoucke, Sergey Ioffe, Jon Shlens, and Zbigniew Wojna. "Rethinking the inception architecture for computer vision." In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2818-2826. 2016.

[3] https://keras.io/api/applications/inceptionv3/

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 = inceptionv3 or by passing the inceptionv3 function to coder.loadDeepLearningNetwork (MATLAB Coder). For example: net = coder.loadDeepLearningNetwork('inceptionv3')

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

The syntax inceptionv3('Weights','none') is not supported for code generation.

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 = inceptionv3 or by passing the inceptionv3 function to coder.loadDeepLearningNetwork (GPU Coder). For example: net = coder.loadDeepLearningNetwork('inceptionv3').

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

• The syntax inceptionv3('Weights','none') is not supported for GPU code generation.