diff options
author | Colm Donelan <colm.donelan@arm.com> | 2022-05-30 15:20:36 +0100 |
---|---|---|
committer | Colm Donelan <colm.donelan@arm.com> | 2022-06-20 15:04:10 +0000 |
commit | 03bf98a8bc51ad20eef4b9ca5fbf6ce15e063721 (patch) | |
tree | 161e9f9efdeffb72cf6237b7a67dc2e990eb97c4 /python/pyarmnn/README.md | |
parent | 8f397a1efed11e17e9f8cb12b53a72b7e32ab978 (diff) | |
download | armnn-03bf98a8bc51ad20eef4b9ca5fbf6ce15e063721.tar.gz |
IVGCVSW-6873 Import inputs but don't export outputs fails.
Only one bool is used to indicate whether inputs should be imported.
However, its possible for the user to want to import inputs but not
export outputs. In addition it's possible for a user to enabled import
during optimize but then pass a memory source that does not require
import.
* Add m_ExportEnabled to INetwork.hpp.
* Modify Network::dNetwork to consider both m_ImportEnabled
and m_ExportEnabled.
* Add ValidateSourcesMatchOptimizedNetwork to LoadedNetwork to validate
import options between optimize and network load.
* Update the TfLite delegate consider exportEnabled flag in the
optimizer.
!armnn-internal-tests:425350
Signed-off-by: Colm Donelan <colm.donelan@arm.com>
Change-Id: I776eab81595898e43f91ab40306962eae61329f4
Diffstat (limited to 'python/pyarmnn/README.md')
-rw-r--r-- | python/pyarmnn/README.md | 14 |
1 files changed, 7 insertions, 7 deletions
diff --git a/python/pyarmnn/README.md b/python/pyarmnn/README.md index 7dc8d8693a..6d8b42d41a 100644 --- a/python/pyarmnn/README.md +++ b/python/pyarmnn/README.md @@ -91,14 +91,14 @@ This step will put all generated files under `./src/pyarmnn/_generated` folder a ```bash $ python setup.py sdist ``` -As the result you will get `./dist/pyarmnn-29.0.0.tar.gz` file. As you can see it is platform independent. +As the result you will get `./dist/pyarmnn-30.0.0.tar.gz` file. As you can see it is platform independent. ##### 5. Build the binary package ```bash $ python setup.py bdist_wheel ``` -As the result you will get something like `./dist/pyarmnn-29.0.0-cp36-cp36m-linux_x86_64.whl` file. As you can see it +As the result you will get something like `./dist/pyarmnn-30.0.0-cp36-cp36m-linux_x86_64.whl` file. As you can see it is platform dependent. # PyArmNN installation @@ -107,8 +107,8 @@ 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-29.0.0-cp36-cp36m-*linux_x86_64*.whl -* Linux Aarch 64 bit machine: pyarmnn-29.0.0-cp36-cp36m-*linux_aarch64*.whl +* Linux x86 64bit machine: pyarmnn-30.0.0-cp36-cp36m-*linux_x86_64*.whl +* Linux Aarch 64 bit machine: pyarmnn-30.0.0-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. @@ -126,7 +126,7 @@ $ gcc --print-search-dirs ``` Install PyArmNN from binary by pointing to the wheel file: ```bash -$ pip install /path/to/pyarmnn-29.0.0-cp36-cp36m-linux_aarch64.whl +$ pip install /path/to/pyarmnn-30.0.0-cp36-cp36m-linux_aarch64.whl ``` ## Installing from source package @@ -143,7 +143,7 @@ $ export ARMNN_INCLUDE=/full/path/to/armnn/include:/full/path/to/armnn/profilin Install PyArmNN as follows: ```bash -$ pip install /path/to/pyarmnn-29.0.0.tar.gz +$ pip install /path/to/pyarmnn-30.0.0.tar.gz ``` If PyArmNN installation script fails to find Arm NN libraries it will raise an error like this @@ -157,7 +157,7 @@ $ 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())" -'29.0.0' +'30.0.0' ``` # PyArmNN API overview |