Deep learning is a branch of machine learning that teaches computers to do what comes naturally to humans: learn from experience. The learning algorithms use computational methods to “learn” information directly from data without relying on a predetermined equation as a model. Deep learning uses convolutional neural networks (CNNs) to learn useful representations of data directly from images.
You can use MATLAB® Coder™ with Deep Learning Toolbox to generate C++ code from a trained CNN. You can deploy the generated code to an embedded platform that uses an Intel® or ARM® processor. You can also generate generic C or C++ code from a trained CNN that does not depend on any third-party libraries.
Deep Learning with MATLAB Coder is not supported in MATLAB Online™.
|Generate C/C++ code from MATLAB code|
|Load deep learning network model|
|Create deep learning code generation configuration objects|
|Parameters to configure deep learning code generation with the ARM Compute Library|
|Parameters to configure deep learning code generation with the Intel Math Kernel Library for Deep Neural Networks|
|Get the list of layers supported for code generation for a specific deep learning library|
|Regenerate files containing network learnables and states parameters|
Install products and configure environment for code generation for deep learning networks.
Generate code for prediction from a pretrained network.
Choose a convolutional neural network that is supported for your target processor.
Use deep learning arrays in MATLAB code intended for code generation.
Adhere to code generation limitations for deep learning arrays.
dlnetwork object for code generation.
Generate C/C++ code for prediction from a deep learning network that does not depend on any third-party libraries.
Generate C++ code for prediction from a deep learning network, targeting an Intel CPU.
Generate C++ code for prediction from a deep learning network, targeting an ARM processor.
Generate library or executable code on host computer for deployment on ARM hardware target.
Quantize and generate code for a pretrained convolutional neural network.
Perform post code generation updates of deep learning network parameters.