coder.loadDeepLearningNetwork - Load deep learning network model - MATLAB (original) (raw)
Load deep learning network model
Syntax
Description
[net](#d126e10240) = coder.loadDeepLearningNetwork([filename](#d126e10132)) loads a pretrained deep learning dlnetwork (Deep Learning Toolbox), SeriesNetwork (Deep Learning Toolbox), DAGNetwork (Deep Learning Toolbox), yolov2ObjectDetector (Computer Vision Toolbox), or ssdObjectDetector (Computer Vision Toolbox) object saved in the filename MAT-file. filename must be a valid MAT-file existing on the MATLAB® path containing a single dlnetwork,SeriesNetwork, DAGNetwork,yolov2ObjectDetector, or ssdObjectDetector object. The MAT-file must contain only the network to be loaded.
[net](#d126e10240) = coder.loadDeepLearningNetwork([functionname](#d126e10169)) calls a function that returns a pretrained deep learning dlnetwork (Deep Learning Toolbox),SeriesNetwork, DAGNetwork,yolov2ObjectDetector, orssdObjectDetector object. functionname must be the name of a function existing on the MATLAB path that returns a dlnetwork,SeriesNetwork, DAGNetwork,yolov2ObjectDetector, or ssdObjectDetector object.
[net](#d126e10240) = coder.loadDeepLearningNetwork(___,[network_name](#d126e10209)) is the same as net = coder.loadDeepLearningNetwork(filename) with the option to name the C++ class generated from the network.network_name is a descriptive name for the network object saved in the MAT-file or pointed to by the function. The network name must be achar type that is a valid identifier in C++.
Use this function when generating code from a network object inference. This function generates a C++ class from this network. The class name is derived from the MAT-file name or the function name.
Note
The input argument of coder.loadDeepLearningNetwork must be a compile-time constant.
Examples
Generate C++ Code from a MAT-File Containing the VGG-16 Network
Use of the coder.loadDeepLearningNetwork function to load an VGG-16 series network and generate C++ code for this network.
Get the MAT-file containing the pretrained VGG-16 network.
url = 'https://www.mathworks.com/supportfiles/gpucoder/cnn_models/VGG/vgg16.mat'; websave('vgg16.mat',url);
Create an entry-point function myVGG16 that uses thecoder.loadDeepLearningNetwork function to load thevgg16.mat into the persistentmynet SeriesNetwork object.
function out = myVGG16(in)
persistent mynet; if isempty(mynet) mynet = coder.loadDeepLearningNetwork('vgg16.mat', 'myVGGnet'); end
out = predict(mynet,in);
The persistent object avoids reconstructing and reloading the network object during subsequent calls to the function to invoke thepredict method on the input.
The input layer of the pretrained VGG-16 network accepts images of size 224x224x3. Use the following lines of code to read an input image from a graphics file and resize it to224x224.
in = imread('peppers.png'); in = imresize(in,[224,224]);
Create a coder.config configuration object for MEX code generation and set the target language to C++. On the configuration object, set DeepLearningConfig with targetlib as 'mkldnn'. The codegen function must determine the size, class, and complexity of MATLAB function inputs. Use the -args option to specify the size of the input to the entry-point function. Use the-config option to pass the code configuration object.
cfg = coder.config('mex'); cfg.TargetLang = 'C++'; cfg.DeepLearningConfig = coder.DeepLearningConfig('mkldnn'); codegen -args {ones(224,224,3,'uint8')} -config cfg myVGG16 -report;
The codegen command places all the generated files in the codegen folder. The folder contains the C++ code for the entry-point function myVGG16.cpp, header and source files containing the C++ class definitions for the neural network, weight, and bias files.
Call VGG-16 predict on the input image and display the top five predicted labels.
predict_scores = myVGG16_mex(in); [scores,indx] = sort(predict_scores, 'descend'); net = coder.loadDeepLearningNetwork('vgg16.mat'); classNames = net.Layers(end).Classes; disp(classNames(indx(1:5)));
bell pepper
cucumber
grocery store
acorn squash
butternut squash Code Generation for a SeriesNetwork Inference Loaded from a MATLAB Function
Use of the coder.loadDeepLearningNetwork function to load an resnet50 series network and generate CUDA® code for this network.
Create an entry-point function resnetFun that uses thecoder.loadDeepLearningNetwork function to call the Deep Learning Toolbox™ toolbox function resnet50. This function returns a pretrained ResNet-50 network.
function out = resnetFun(in)
persistent mynet; if isempty(mynet) mynet = coder.loadDeepLearningNetwork('resnet50', 'myresnet'); end
out = predict(mynet,in);
The persistent object avoids reconstructing and reloading the network object during subsequent calls to the function to invoke thepredict method on the input.
The input layer of the pretrained ResNet-50 network accepts images of size 224x224x3. To read an input image from a graphics file and resize it to 224x224, use the following lines of code:
in = imread('peppers.png'); in = imresize(in,[224,224]);
Create a coder.gpuConfig configuration object for MEX code generation and set the target language to C++. The codegen function must determine the size, class, and complexity of MATLAB function inputs. Use the -args option to specify the size of the input to the entry-point function and the-config option to pass the code configuration object.
cfg = coder.gpuConfig('mex'); cfg.TargetLang = 'C++'; cfg.DeepLearningConfig = coder.DeepLearningConfig('cudnn'); codegen -args {ones(224,224,3,'uint8')} -config cfg resnetFun -report;
The codegen command places all the generated files in the codegen folder. It contains the CUDA code for the entry-point functionresnetFun.cu, header, and source files containing the C++ class definitions for the neural network, weight, and bias files.
Input Arguments
filename — MAT file name
name
Specifies the name of the MAT-file containing the pretraineddlnetwork, SeriesNetwork,DAGNetwork, yolov2ObjectDetector, or ssdObjectDetector object.
This input argument must be a compile-time constant.
Data Types: string
functionname — MATLAB function name
name
Specifies the name of the function that returns a pretraineddlnetwork, SeriesNetwork,DAGNetwork, yolov2ObjectDetector, or ssdObjectDetector object.
This input argument must be a compile-time constant.
Data Types: string
network_name — Descriptive name
name
Descriptive name for the network object saved in the MAT-file. It must be a char type that is a valid identifier in C++.
This input argument must be a compile-time constant.
Data Types: char
Output Arguments
net — Network object
dlnetwork object | SeriesNetwork object | DAGNetwork object | yolov2ObjectDetector object | ssdObjectDetector object
Network inference, returned as a dlnetwork,SeriesNetwork, DAGNetwork,yolov2ObjectDetector, orssdObjectDetector object.
Limitations
coder.loadDeepLearningNetworkdoes not support loading MAT-files with multiple networks.- The MAT-file must contain only the network to be loaded.
- The code generator represents characters in an 8-bit ASCII codeset that the locale setting determines. Therefore, the use of non-ASCII characters in file, folder, or network names might result in errors. For more information, see Encoding of Characters in Code Generation.
Extended Capabilities
C/C++ Code Generation
Generate C and C++ code using MATLAB® Coder™.
GPU Code Generation
Generate CUDA® code for NVIDIA® GPUs using GPU Coder™.
Version History
Introduced in R2017b
See Also
Functions
- codegen | imagePretrainedNetwork (Deep Learning Toolbox)