efficientnetb0

EfficientNet-b0 convolutional neural network

• 

×

Syntax

net = efficientnetb0

net = efficientnetb0('Weights','imagenet')

lgraph = efficientnetb0('Weights','none')

Description

EfficientNet-b0 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 EfficientNet-b0 model. Follow the steps of Classify Image Using GoogLeNet and replace GoogLeNet with EfficientNet-b0.

To retrain the network on a new classification task, follow the steps of Train Deep Learning Network to Classify New Images and load EfficientNet-b0 instead of GoogLeNet.

net = efficientnetb0 returns an EfficientNet-b0 model network trained on the ImageNet data set.

This function requires the Deep Learning Toolbox™ Model for EfficientNet-b0 Network support package. If this support package is not installed, then the function provides a download link.

net = efficientnetb0('Weights','imagenet') returns a EfficientNet-b0 model network trained on the ImageNet data set. This syntax is equivalent to net = efficientnetb0.

lgraph = efficientnetb0('Weights','none') returns the untrained EfficientNet-b0 model network architecture. The untrained model does not require the support package.

Examples

Download EfficientNet-b0 Support Package

Download and install the Deep Learning Toolbox Model for EfficientNet-b0 Network support package.

Type efficientnetb0 at the command line.

efficientnetb0

If the Deep Learning Toolbox Model for EfficientNet-b0 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 efficientnetb0 at the command line. If the required support package is installed, then the function returns a DAGNetwork object.

efficientnetb0

ans = 

  DAGNetwork with properties:

         Layers: [290×1 nnet.cnn.layer.Layer]
    Connections: [363×2 table]
     InputNames: {'ImageInput'}
    OutputNames: {'classification'}

Visualize the network using Deep Network Designer.

deepNetworkDesigner(efficientnetb0)

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 EfficientNet-b0 convolutional neural network

DAGNetwork object

Pretrained EfficientNet-b0 convolutional neural network, returned as a DAGNetwork object.

lgraph — Untrained EfficientNet-b0 convolutional neural network architecture

LayerGraph object

Untrained EfficientNet-b0 convolutional neural network architecture, returned as a LayerGraph object.

References

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

[2] Mingxing Tan and Quoc V. Le, “EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks,” ArXiv Preprint ArXiv:1905.1194, 2019.

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 = efficientnetb0 or by passing the efficientnetb0 function to coder.loadDeepLearningNetwork (MATLAB Coder). For example: net = coder.loadDeepLearningNetwork('efficientnetb0')

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

The syntax efficientnetb0('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 = efficientnetb0 or by passing the efficientnetb0 function to coder.loadDeepLearningNetwork (GPU Coder). For example: net = coder.loadDeepLearningNetwork('efficientnetb0')

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

• The syntax efficientnetb0('Weights','none') is not supported for GPU code generation.