importCaffeNetwork

Import pretrained convolutional neural network models from Caffe

Syntax

net = importCaffeNetwork(protofile,datafile)

net = importCaffeNetwork(___,Name,Value)

Description

net = importCaffeNetwork(protofile,datafile) imports a pretrained network from Caffe [1]. The function returns the pretrained network with the architecture specified by the .prototxt file protofile and with network weights specified by the .caffemodel file datafile.

This function requires Deep Learning Toolbox™ Importer for Caffe Models support package. If this support package is not installed, the function provides a download link.

You can download pretrained networks from Caffe Model Zoo [2].

net = importCaffeNetwork(___,Name,Value) returns a network with additional options specified by one or more Name,Value pair arguments using any of the previous syntaxes.

Examples

Download Importer for Caffe Models Support Package

Download and install Deep Learning Toolbox Importer for Caffe Models support package.

To download the required support package, type importCaffeNetwork at the command line.

importCaffeNetwork

If Deep Learning Toolbox Importer for Caffe Models 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.

Import Caffe Network

Specify files to import.

protofile = 'digitsnet.prototxt';
datafile = 'digits_iter_10000.caffemodel';

Import network.

net = importCaffeNetwork(protofile,datafile)

net = 
  SeriesNetwork with properties:

    Layers: [7×1 nnet.cnn.layer.Layer]

Input Arguments

protofile — File name

character vector

File name of the .prototxt file containing the network architecture, specified as a character vector. protofile must be in the current folder, in a folder on the MATLAB^® path, or you must include a full or relative path to the file. If the .prototxt file does not specify the size of the input data, you must specify the size using the 'InputSize' name-value pair argument.

Example: 'digitsnet.prototxt'

Data Types: char

datafile — File name

character vector

File name of the .caffemodel file containing the network weights, specified as a character vector. datafile must be in the current folder, in a folder on the MATLAB path, or you must include a full or relative path to the file. To import network layers without weights, use importCaffeLayers.

Example: 'digits_iter_10000.caffemodel'

Data Types: char

Name-Value Pair Arguments

Specify optional comma-separated pairs of Name,Value arguments. Name is the argument name and Value is the corresponding value. Name must appear inside quotes. You can specify several name and value pair arguments in any order as Name1,Value1,...,NameN,ValueN.

Example: importCaffeNetwork(protofile,datafile,'AverageImage',I,'ClassNames',{'A','B','C'}) imports a pretrained network using the average image I for zero-center normalization and specifies the class names to be 'A', 'B', and 'C'.

'InputSize' — Size of input data

row vector

Size of input data, specified as a row vector. Specify a vector of two or three integer values [h,w], or [h,w,c] corresponding to the height, width, and the number of channels of the input data. If the .prototxt file does not specify the size of the input data, then you must specify the input size.

Example: [28 28 1]

'AverageImage' — Average image

matrix

Average image for zero-center normalization, specified as a matrix. If you specify an image, then you must specify an image of the same size as the input data. If you do not specify an image, the software uses the data specified in the .prototxt file, if present. Otherwise, the function sets the Normalization property of the image input layer of the network to 'none'.

'Classes' — Classes of the output layer

'auto' (default) | categorical vector | string array | cell array of character vectors

Classes of the output layer, specified as a categorical vector, string array, cell array of character vectors, or 'auto'. If you specify a string array or cell array of character vectors str, then the software sets the classes of the output layer to categorical(str,str). If Classes is 'auto', then the function sets the classes to categorical(1:N), where N is the number of classes.

Data Types: char | categorical | string | cell

Output Arguments

net — Imported pretrained Caffe network

SeriesNetwork object | DAGNetwork object

Imported pretrained Caffe network, returned as a SeriesNetwork object or DAGNetwork object. Caffe networks that take color images as input expect the images to be in BGR format. During import, importCaffeNetwork modifies the network so that the imported MATLAB network takes RGB images as input.

Tips

• importCaffeNetwork can import networks with the following Caffe layer types, with some limitations:

  • Input

  • Convolution

  • Deconvolution

  • Batch Norm

  • ReLU

  • Tanh

  • Local Response Normalization (LRN)

  • Pooling

  • Inner Product/Fully Connected

  • Dropout

  • Concat

  • Eltwise (only sum)

  • Softmax With Loss

  • Euclidean Loss

  If the network contains any other type of layer, then the software returns an error.

  The function imports only the layers that protofile specifies with the include-phase TEST. The function ignores any layers that protofile specifies with the include-phase TRAIN.

Compatibility Considerations

'ClassNames' option will be removed

Not recommended starting in R2018b

'ClassNames' will be removed. Use 'Classes' instead. To update your code, replace all instances of 'ClassNames' with 'Classes'. There are some differences between the corresponding properties in classification output layers that require additional updates to your code.

The ClassNames property of a classification output layer is a cell array of character vectors. The Classes property is a categorical array. To use the value of Classes with functions that require cell array input, convert the classes using the cellstr function.

References

[1] Caffe. https://caffe.berkeleyvision.org/.

[2] Caffe Model Zoo. https://caffe.berkeleyvision.org/model_zoo.html.