MLCE-193 Add FAQ.md to ArmNN GitHub.

* Add basic FAQ.md file.
* Refer to the file from README.md

Signed-off-by: Colm Donelan <Colm.Donelan@arm.com>
Change-Id: I16b861cd5513bd5493e3d2d459b61378b36a6846

diff --git a/README.md b/README.md
index 1019d12..9c404f8 100644 (file)
--- a/README.md
+++ b/README.md
@@ -35,6 +35,8 @@ Static quantization is supported by default but dynamic quantization can be enab
 
 Note that Arm NN needs to be built against a particular version of [ARM's Compute Library](https://github.com/ARM-software/ComputeLibrary). The get_compute_library.sh in the scripts subdirectory will clone the compute library from the review.mlplatform.org github repository into a directory alongside armnn named 'clframework' and checks out the correct revision.
 
+For FAQs and troubleshooting advice, see [FAQ.md](docs/FAQ.md)
+
 ### License
 
 Arm NN is provided under the [MIT](https://spdx.org/licenses/MIT.html) license.

diff --git a/docs/FAQ.md b/docs/FAQ.md
new file mode 100644 (file)
index 0000000..2f06df6
--- /dev/null
+++ b/docs/FAQ.md
@@ -0,0 +1,15 @@
+Frequently asked questions
+==========================
+
+These are issues that have been commonly seen when using ArmNN.
+
+Segmentation fault following a failed call to armnn::Optimize using CpuRef backend.
+---------------------------------------------------------
+
+In some error scenarios of calls to armnn::Optimize a null pointer may be
+returned. This contravenes the function documentation however, it can
+happen. Users are advised to check the value returned from the function as a
+precaution.
+
+If you encounter this problem and are able to isolate it consider contributing
+a solution.