To useMATLAB®Coder™to generate code for deep learning networks, you must also install:
Deep Learning Toolbox™
MATLAB Coder Interface for Deep Learning Libraries
TheMATLAB Coder Interface for Deep Learning Librariesis not supported forMATLAB Online™.
You can useMATLAB Coderto generate C++ code for deep learning networks that you deploy to Intel®or ARM®processors. The generated code takes advantage of deep learning libraries optimized for the target CPU. The hardware and software requirements depend on the target platform.
You can also useMATLAB Coderto generate generic C or C++ code for deep learning networks. Such C or C++ code does not depend on any third-party libraries. For more information, seeGenerate Generic C/C++ Code for Deep Learning Networks.
Note
The paths to the required software libraries must not contain spaces or special characters, such as parentheses. On Windows®操作系统ems, special characters and spaces are allowed only if 8.3 file names are enabled. For more information on 8.3 file names, refer to the Windows documentation.
Intel CPUs | ARM CPUs | |
---|---|---|
Hardware Requirements | Intel processor with support for Intel Advanced Vector Extensions 2 (Intel |
ARM Cortex-A processors that support the |
Software Libraries | Intel Math Kernel Library for Deep Neural Networks (MKL-DNN), v1.4. Seehttps://01.org/onednn Do not use a prebuilt library because some required files are missing. Instead, build the library from the source code. Seeinstructions for building the libraryon GitHub®. For more information on build, see this post inMATLAB Answers™://www.tatmou.com/matlabcentral/answers/447387-matlab-coder-how-do-i-build-the-intel-mkl-dnn-library-for-deep-learning-c-code-generation-and-dep |
ARM Compute Library for computer vision and machine learning, versions 19.05 and 20.02.1. Seehttps://developer.arm.com/ip-products/processors/machine-learning/compute-library Specify the version number in a Do not use a prebuilt library because it might be incompatible with the compiler on the ARM hardware. Instead, build the library from the source code. Build the library on either your host machine or directly on the target hardware. Seeinstructions for building the libraryon GitHub. The folder that contains the library files such as For more information on build, see this post inMATLAB Answers://www.tatmou.com/matlabcentral/answers/455590-matlab-coder-how-do-i-build-the-arm-compute-library-for-deep-learning-c-code-generation-and-deplo |
Operating System Support | Windows, Linux®, andmacOS. |
Windows and Linux only. |
C++ Compiler | MATLAB Coderlocates and uses a supported installed compiler. For the list of supported compilers, seeSupported and Compatible Compilerson the MathWorks®website. You can use The C++ compiler must support C++11. On Windows, to generate code that uses the Intel MKL-DNN library by using the On Windows, to generate generic C or C++ code that does not use any third-party libraries, useMicrosoft Visual Studioor the MinGW®compiler. For more information, seeGenerate Generic C/C++ Code for Deep Learning Networks. |
|
Other | Open Source Computer Vision Library (OpenCV), v3.1.0 is required for the ARM based deep learning examples. Note: The examples require separate libraries such as For more information, refer to the OpenCV documentation. |
MATLAB Coderuses environment variables to locate the libraries required to generate code for deep learning networks.
Platform | Variable Name | Description |
---|---|---|
Windows | INTEL_MKLDNN |
Path to the root folder of the Intel MKL-DNN library installation. For example:
|
ARM_COMPUTELIB |
Path to the root folder of the ARM Compute Library installation on the ARM target hardware. For example:
Set |
|
路径 |
Path to the Intel MKL-DNN library folder. For example:
|
|
Linux | LD_LIBRARY_PATH |
Path to the Intel MKL-DNN library folder. For example:
|
Path to the ARM Compute Library folder on the target hardware. For example:
Set |
||
INTEL_MKLDNN |
Path to the root folder of the Intel MKL-DNN library installation. For example:
|
|
ARM_COMPUTELIB |
Path to the root folder of the ARM Compute Library installation on the ARM target hardware. For example:
Set |
|
macOS | INTEL_MKLDNN |
Path to the root folder of the Intel MKL-DNN library installation. For example:
|
UNIX®based OS on ARM targets | OPENCV_DIR |
Path to the build folder of OpenCV. Install OpenCV for deep learning examples that use OpenCV. For example:
|
Note
To generate code for Raspberry Pi™ using theMATLAB Support Package for Raspberry Pi Hardware, you must set the environment variables non-interactively. For instructions, see//www.tatmou.com/matlabcentral/answers/455591-matlab-coder-how-do-i-setup-the-environment-variables-on-arm-targets-to-point-to-the-arm-compute-li
Note
To build and run examples that use OpenCV, you must install the OpenCV libraries on the target board. For OpenCV installations on Linux, make sure that the path to the library files and the path to the header files are on the system path. By default, the library and header files are installed in a standard location such as/usr/local/lib/
and/usr/local/include/opencv
, respectively.
For OpenCV installations on the target board, set theOPENCV_DIR
and路径
environment variables as described in the previous table.