diff options
| author | Cathal Corbett <cathal.corbett@arm.com> | 2022-09-01 11:34:37 +0100 |
|---|---|---|
| committer | Cathal Corbett <cathal.corbett@arm.com> | 2022-12-12 12:38:15 +0000 |
| commit | 5383767a7a759c867235ab66bd71f88281e3bd06 (patch) | |
| tree | 5704c33171d39dda9e4428c953e2efdd62ead656 /python/pyarmnn/README.md | |
| parent | a98e79a709f7c29728e1fc79c21ba5265993b8b6 (diff) | |
| download | armnn-5383767a7a759c867235ab66bd71f88281e3bd06.tar.gz | |
Optimize the calling of IsLayerSupported().
* Done as part of 22.11/23.02 innovation days.
* IsLayerSupported() is called in model prepare (delegate, android-nn-driver and shim/support_library)
and again in ArmNN once model otimization is performed.
* From calling IsLayerSupported() the first time, we should know that the layers are supported
and what backend they are supported on.
* Solution is to set the BackendId of the IConnectableLayer when IsLayerSupported() is called the first time,
* In the Optimize() function we then check if the backend is set. If so, we do not call IsLayerSupported() again.
* In the case a layer that is supported gets optimized, then the BackendId of that layer get set to "Unknown"
for the new optimized layer and IsLayerSupported() will get called on the newly optimized layer.
* Includes bug fix IVGCVSW-7213 for Android Mean FP16 CpuAcc tests. Also related to bug IVGCVSW-7211.
Signed-off-by: Cathal Corbett <cathal.corbett@arm.com>
Change-Id: I7a7820d0cdb079ffb5a3a2e0c44e252f652df53b
Diffstat (limited to 'python/pyarmnn/README.md')
| -rw-r--r-- | python/pyarmnn/README.md | 6 |
1 files changed, 3 insertions, 3 deletions
diff --git a/python/pyarmnn/README.md b/python/pyarmnn/README.md index 0d2c511a17..3962e11395 100644 --- a/python/pyarmnn/README.md +++ b/python/pyarmnn/README.md @@ -69,8 +69,8 @@ PyArmNN can be distributed as a source package or a binary package (wheel). Binary package is platform dependent, the name of the package will indicate the platform it was built for, e.g.: -* Linux x86 64bit machine: pyarmnn-31.0.0-cp36-cp36m-*linux_x86_64*.whl -* Linux Aarch 64 bit machine: pyarmnn-31.0.0-cp36-cp36m-*linux_aarch64*.whl +* Linux x86 64bit machine: pyarmnn-32.0.0-cp36-cp36m-*linux_x86_64*.whl +* Linux Aarch 64 bit machine: pyarmnn-32.0.0-cp36-cp36m-*linux_aarch64*.whl The source package is platform independent but installation involves compilation of Arm NN python extension. You will need to have g++ compatible with C++ 14 standard and a python development library installed on the build machine. @@ -110,7 +110,7 @@ $ pip show pyarmnn You can also verify it by running the following and getting output similar to below: ```bash $ python -c "import pyarmnn as ann;print(ann.GetVersion())" -'31.0.0' +'32.0.0' ``` # PyArmNN API overview |