Gitiles
Code Review Sign In
review.mlplatform.org / ml / armnn / 4d1ff588288b1a7a98dd2fd7f2ba5717b8ecf102
commit4d1ff588288b1a7a98dd2fd7f2ba5717b8ecf102[log] [tgz]
authorJames Conroy <james.conroy@arm.com>Mon Jun 10 17:06:39 2019 +0100
committerMatteo Martincigh <matteo.martincigh@arm.com>Mon Jun 17 11:16:58 2019 +0000
treea6b8dbd9434b887dab4c9915b0bacea500410517
parentaece4edd329a1d6a66472cb314c49b20dc243183 [diff]
IVGCVSW-3221 Refactor Mean ref workload and tests

 * Renamed RefMeanFloat32Workload and RefMeanUint8Workload
   to RefMeanWorkload, updated references to reflect this
   change.
 * Refactored RefFloorWorkload to use Decoders/Encoders,
   to support the use of multiple data types.
 * Deleted reference Unit8 Mean tests as they were
   duplicates of the Float32 tests. Refactored these tests
   to support multiple data types and updated references.
 * Adjusted the values used in the tests' input tensors so
   that they are more like floating point numbers
   e.g. change 1.0f to 1.5f.
 * Replace size_t with unsigned int in Mean ref workload,
   for better compatibility with the Encoder/Decoder,
   removed some unnecessary casts after this.
 * Added ValidateTensorDataTypesMatch() function to
   WorkloadData.cpp, added CreateIncorrectDimensionsErrorMsg
   function to RefLayerSupport.cpp.
 * Added passing and failing tests for ref IsMeanSupported.

Signed-off-by: James Conroy <james.conroy@arm.com>
Change-Id: Id3d44463d1385255c727a497d4026d21a49e7eb2
21 files changed
tree: a6b8dbd9434b887dab4c9915b0bacea500410517
  1. Android.bp
  2. Android.mk
  3. BuildGuideAndroidNDK.md
  4. BuildGuideCrossCompilation.md
  5. CMakeLists.txt
  6. ContributorGuide.md
  7. LICENSE
  8. README.md
  9. cmake/
  10. docs/
  11. include/
  12. samples/
  13. scripts/
  14. src/
  15. tests/
  16. third-party/
README.md

Arm NN

Arm NN is a key component of the machine learning platform which is part of the Linaro Machine Intelligence Initiative. For more information on the machine learning platform and Arm NN, see: https://mlplatform.org/, also there is further Arm NN information available from https://developer.arm.com/products/processors/machine-learning/arm-nn

There is a getting started guide here using TensorFlow: https://developer.arm.com/technologies/machine-learning-on-arm/developer-material/how-to-guides/configuring-the-arm-nn-sdk-build-environment-for-tensorflow

There is a getting started guide here using TensorFlow Lite: https://developer.arm.com/technologies/machine-learning-on-arm/developer-material/how-to-guides/configuring-the-arm-nn-sdk-build-environment-for-tensorflow-lite

There is a getting started guide here using Caffe: https://developer.arm.com/technologies/machine-learning-on-arm/developer-material/how-to-guides/configuring-the-arm-nn-sdk-build-environment-for-caffe

There is a getting started guide here using ONNX: https://developer.arm.com/technologies/machine-learning-on-arm/developer-material/how-to-guides/configuring-the-arm-nn-sdk-build-environment-for-onnx

There is a guide for backend development: Backend development guide

Build Instructions

Arm tests the build system of Arm NN with the following build environments:

Arm NN is written using portable C++14 and the build system uses CMake so it is possible to build for a wide variety of target platforms, from a wide variety of host environments.

The armnn/tests directory contains tests used during Arm NN development. Many of them depend on third-party IP, model protobufs and image files not distributed with Arm NN. The dependencies of some of the tests are available freely on the Internet, for those who wish to experiment.

The 'armnn/samples' directory contains SimpleSample.cpp. A very basic example of the ArmNN SDK API in use.

The 'ExecuteNetwork' program, in armnn/tests/ExecuteNetwork, has no additional dependencies beyond those required by Arm NN and the model parsers. It takes any model and any input tensor, and simply prints out the output tensor. Run with no arguments to see command-line help.

The 'ArmnnConverter' program, in armnn/src/armnnConverter, has no additional dependencies beyond those required by Arm NN and the model parsers. It takes a model in TensorFlow format and produces a serialized model in Arm NN format. Run with no arguments to see command-line help. Note that this program can only convert models for which all operations are supported by the serialization tool (src/armnnSerializer).

The 'ArmnnQuantizer' program, in armnn/src/armnnQuantizer, has no additional dependencies beyond those required by Arm NN and the model parsers. It takes a 32-bit float network and converts it into a quantized asymmetric 8-bit or quantized symmetric 16-bit network. Static quantization is supported by default but dynamic quantization can be enabled if CSV file of raw input tensors is specified. Run with no arguments to see command-line help.

Note that Arm NN needs to be built against a particular version of ARM's Compute Library. 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 checkouts the correct revision

License

Arm NN is provided under the MIT license. See LICENSE for more information. Contributions to this project are accepted under the same license.

Individual files contain the following tag instead of the full license text.

SPDX-License-Identifier: MIT

This enables machine processing of license information based on the SPDX License Identifiers that are available here: http://spdx.org/licenses/

Contributions

The Arm NN project welcomes contributions. For more details on contributing to Arm NN see the Contributing page on the MLPlatform.org website, or see the Contributor Guide.