aboutsummaryrefslogtreecommitdiff
path: root/samples
diff options
context:
space:
mode:
authorJan Eilers <jan.eilers@arm.com>2021-08-17 13:50:08 +0100
committerNikhil Raj <nikhil.raj@arm.com>2021-08-20 11:14:02 +0100
commit3309c339b20aaeb29157576a620c4f38ee98730c (patch)
treebb118acb596a6b3366f4acb9968ebb3f5bf4fb2d /samples
parent4914d0c1f4cbb01fe276a7093af4cff13270b74a (diff)
downloadarmnn-3309c339b20aaeb29157576a620c4f38ee98730c.tar.gz
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 <jan.eilers@arm.com> Change-Id: Ie8ae19ca471a0616eeea7f708d547388c8ee860e Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Diffstat (limited to 'samples')
-rw-r--r--samples/examples.dox41
1 files changed, 41 insertions, 0 deletions
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
+**/
+
+}