From 2650556a8f1bdc4ade0855df2b9c21d420b9dad2 Mon Sep 17 00:00:00 2001 From: Jan Eilers Date: Tue, 17 Aug 2021 13:50:08 +0100 Subject: Make samples visible in doxygen * uses the @example doxygen command to add all our simple examples into an 'Examples' tab in the doxygen documentation Signed-off-by: Jan Eilers Change-Id: Ie8ae19ca471a0616eeea7f708d547388c8ee860e Signed-off-by: Nikhil Raj --- docs/01_01_parsers.dox | 4 ++-- docs/Doxyfile | 3 ++- samples/examples.dox | 41 +++++++++++++++++++++++++++++++++++++++++ 3 files changed, 45 insertions(+), 3 deletions(-) create mode 100644 samples/examples.dox diff --git a/docs/01_01_parsers.dox b/docs/01_01_parsers.dox index 3ac5b27735..97497fe016 100644 --- a/docs/01_01_parsers.dox +++ b/docs/01_01_parsers.dox @@ -22,7 +22,7 @@ bindings take a look into the @ref md_python_pyarmnn_README section. -@section S5_onnx_parser ArmNN Onnx Parser +@section S5_onnx_parser Arm NN Onnx Parser `armnnOnnxParser` is a library for loading neural networks defined in ONNX protobuf files into the Arm NN runtime. @@ -92,7 +92,7 @@ More machine learning operators will be supported in future releases. -@section S6_tf_lite_parser ArmNN Tf Lite Parser +@section S6_tf_lite_parser Arm NN Tf Lite Parser `armnnTfLiteParser` is a library for loading neural networks defined by TensorFlow Lite FlatBuffers files into the Arm NN runtime. diff --git a/docs/Doxyfile b/docs/Doxyfile index 16510041cf..3fc872eda2 100644 --- a/docs/Doxyfile +++ b/docs/Doxyfile @@ -840,7 +840,8 @@ INPUT = ./docs/01_00_software_tools.dox \ ./InstallationViaAptRepository.md \ ./ContributorGuide.md \ ./BuildGuideAndroidNDK.md \ - ./BuildGuideCrossCompilation.md + ./BuildGuideCrossCompilation.md \ + ./samples/examples.dox # This tag can be used to specify the character encoding of the source files # that doxygen parses. Internally doxygen uses the UTF-8 encoding. Doxygen uses diff --git a/samples/examples.dox b/samples/examples.dox new file mode 100644 index 0000000000..e0b0ea345e --- /dev/null +++ b/samples/examples.dox @@ -0,0 +1,41 @@ +/// Copyright (c) 2021 ARM Limited and Contributors. All rights reserved. +/// +/// SPDX-License-Identifier: MIT +/// + +namespace armnn +{ +/** +This is a very simple example which uses the Arm NN SDK API to create a neural network which consists of +nothing else but a single fully connected layer with a single weights value. It's as minimalistic as it can get. + +@note Most of our users won't use our API to create a network manually. Usually you would use one of our software + tools like the @ref S6_tf_lite_parser "TfLite Parser" that will translate a TfLite model into Arm NN for you. + Still it's a very nice example to see how an Arm NN network is created, optimized and executed. + + (You can find more complex examples using the TfLite Parser in samples/ObjectDetection and + samples/SpeechRecognition. And another example using @ref md_python_pyarmnn_README "PyArmnn" in + samples/ImageClassification) +@example SimpleSample.cpp +**/ + +/** +This is simple example that shows how to use a dynamic backend. Dynamic Backends can be compiled as standalone +against Arm NN and can be loaded by Arm NN dynamically at runtime. This way you can quickly integrate new backends +without having to worry or recompile Arm NN. + +This example makes use of a very simplistic dynamic backend called 'SampleDynamic'. There is a guide that tells you +more about dynamic backends and how this particular backend was created so you can create a dynamic backend +yourself @ref md_src_dynamic_README. +@example DynamicSample.cpp +**/ + +/** +This example is basically a copy of the SimpleSample example. But it makes use of a CustomAllocator to allocate +memory for the inputs, outputs and inter layer memory. + +@note This is currently an experimental interface +@example CustomMemoryAllocatorSample.cpp +**/ + +} -- cgit v1.2.1