Age | Commit message (Collapse) | Author |
|
* Add layers missing in PyArmNN
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: Ia821105f9d235dcf7f9472e54849d268e07fb9a9
|
|
* Adds BatchMatMul layer and descriptor to pyarmnn
* Adds ReverseV2 layer to pyarmnn
* Adds ElementWiseBinary layer and descriptor to pyarmnn
* Adds Tile layer and descriptor to pyarmnn
* Adds network test for each layer
Signed-off-by: Ryan OShea <ryan.oshea3@arm.com>
Change-Id: Iac70fb7f857978d676d3b67a4cc20fb5f3270676
|
|
This reverts commit 9a5e5b7032788249055f40edd763420f6bdba8fe.
Reason for revert: Build failing while building pyarmnn
Change-Id: I465c494ee1a19a830bf85a8ab078ead08cefccd4
|
|
features added in ArmNN
* Adds BatchMatMul layer and descriptor to pyarmnn
* Adds ReverseV2 layer to pyarmnn
* Adds ElementWiseBinary layer and descriptor to pyarmnn
* Adds Tile layer and descriptor to pyarmnn
* Adds network test for each layer
Signed-off-by: Ryan OShea <ryan.oshea3@arm.com>
Change-Id: I07116d9e7b1eb6b6f8a687d8ba7cfbd11c912d0d
|
|
- Remove Bf16ToFp32 Conversion Layer
- Remove Fp32ToBf16 Conversion Layer
- Remove B16 Conversion tests
* Throw exception if m_ReduceFp32ToBf16 optimzer option is set to true
* Provide comments to enable fast math in order to use bf16
* Update docs to inform users to enable fast math for bf16
Execute Network Changes
* Require bf16_turbo_mode to also have fast_math_enabled set to true
- Remove setting m_ReduceFp32ToBf16 optimizer option
Signed-off-by: Ryan OShea <ryan.oshea3@arm.com>
Change-Id: Ibaa6da9d29c96a1ce32ff5196b0847fde9f04a1c
|
|
* AddConv and AddDWConv with weights and bias
* ResizeBilinearDescriptor
* b,blacklist option in accuracy tool
!android-nn-driver:8172
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: Ibbc04fd18be7f938b11590bf67cd7af103cb4d99
|
|
This reverts commit a0f8b15d4ddb5075f380003ff31b271d389d3b66.
Reason for revert: <Test ClDmaBufInternalTests review >
Change-Id: Ibc4a77fa008643849da7330391942e4c87b941e2
|
|
This reverts commit 03bf98a8bc51ad20eef4b9ca5fbf6ce15e063721.
Reason for revert: Caused failures in tests located in internal repo.
Change-Id: If35cb0ede349b270e4e7827324382e09455d8cfa
|
|
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
|
|
* armnn_network.i: IVGCVSW-6127 ConstTensorsAsInput:
DepthwiseConvolution2d.
* armnn_descriptors.i: IVGCVSW-6127 ConstTensorsAsInput:
DepthwiseConvolution2d. MLCE-604 Add Unidirectional Sequence
Lstm support to TFLite. MLCE-530 Add support for
UnidirectionalSequenceLstm to RefWorkload
Signed-off-by: Colm Donelan <colm.donelan@arm.com>
Change-Id: I0c054db17dbf9a1eb14c12d1fd1337f8003a92d3
|
|
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: I7c80299f539b64682a6a68cd1709089f71600cd9
|
|
* Add layer to __init__.py
* Add descriptor for Pooling3d
* Add descriptor test for Pooling3d
* Add network test for Pooling3d layer
Signed-off-by: Ryan OShea <ryan.oshea3@arm.com>
Change-Id: Id5e1587a89d3ffb5bee7764a92b299fa43a2ae35
|
|
* Remove deprecated INetwork::AddFullyconnectedLayer() taking weights
as argument as they are now taken as separate input layers.
* Updated test that was using the deprecated function.
* Remove calls in pyarmnn
Signed-off-by: Francis Murtagh <francis.murtagh@arm.com>
Change-Id: Ibc52ac7fa57afd9033eb226bbc24a09e88a7d361
|
|
* AddReduceLayer to PyArmNN armnn_network.i
* AddReduceDescriptor to PyArmNN armnn_descriptors.i
* Add layer to test_network.py
* Add descriptor unit tests to test_descriptors.py
Signed-off-by: Ryan OShea <ryan.oshea3@arm.com>
Change-Id: I2a8706052baf8f9c0038a5ea327d73b8f3ea1961
|
|
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: I2bfc54ea9aae78c60a66d7a5c39a33ca8a238e62
|
|
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: I6d09abb75db1875d4d4075b1801fdc46a0f4ae7b
|
|
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: If9c6902396b9f3cec3b38b70ccfa12fcbb3fd5a7
|
|
* Add layer to armnn.network.i
* Add layer to test_network.py
Signed-off-by: Ryan OShea <ryan.oshea3@arm.com>
Change-Id: I7554a0ff62d81fcc99aa68204ae5f1cc3965c44b
|
|
* AddTransposeLayer to PyArmNN armnn_network.i
* AddTranposeDescriptor to PyArmNN armnn_descriptors.i
* Add layer to test_network_method_exists() in test_network.py
* Add descriptor unit tests to test_descriptors.py
Signed-off-by: Cathal Corbett <cathal.corbett@arm.com>
Change-Id: Ic198448ad11d10701b6b263656285bb75d3656cd
|
|
* AddLogicalBinaryLayer to PyArmNN armnn_network.i
* LogicalBinaryDescriptor to PyArmNN armnn_descriptors.i
* Add layer to test_network_method_exists() in test_network.py
* Add descriptor unit tests to test_descriptors.py
Signed-off-by: Cathal Corbett <cathal.corbett@arm.com>
Change-Id: I2f6288987332e1556235a9c16582e96b3a0fb641
|
|
* Added new test for AddConstantLayer to FullyConnectedLayer with
actual data in test_network.py
* Added support for m_ConstantWeights in FullyConnectedDescriptor in
file armnn_descriptors.i
* Amended AddFullyConnectedLayer methods in armnn_netowrk.i to
add support for ConstTensorsAsInputs to FullyConnected.
* Fixed indentation in test_network.py
Signed-off-by: Cathal Corbett <cathal.corbett@arm.com>
Change-Id: Id25c7ef6ed2cd3de3285416d90588ccb345aa9bc
|
|
constructor.
Signed-off-by: alexander <alexander.efremov@arm.com>
Change-Id: Ic2ad6a46c3830f2526ba8b20ca0db0780be4b9a2
|
|
* Removes deprecated AddLayer, IsLayerSupported functions
* Marks the whole LayerVisitor class as deprecated not just the
constructor. This required to wrap all Accept functions in a
no deprecate macro because the LayerVisitor is used as a parameter in
there
* Removes usage of deprecated LayerVisitor and replaces it
with ExecuteStrategy. This required a few structural changes
in the unit tests
* Adds a default implementation for IStrategy called StrategyBase
* Changes pyarmnn to use non deprecated constructor for
INetworkProperties and adds related unit test
* Marks usage of deprecated code in pyarmnn as deprecated. This
required to extend INetworkProperties to allow backwards compatibility
* Removes deprecated functions from CpuAcc, GpuAcc and Ref backends
Note: This patch breaks compatibility with backends that are not
updated in this patch
!android-nn-driver:6325
Signed-off-by: Jan Eilers <jan.eilers@arm.com>
Change-Id: Id13b6f37a74d26eadeda2da1dc92915e725ed5a5
|
|
profiling common
!android-nn-driver:5691
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: Ib71af0831e324ac6bd27b1a36f4a6ec1a703b14a
|
|
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
Change-Id: Ic7c288fd829d7f1f1ae2910c47fbccdd635def8f
|
|
* Add HalfPixelCenters to Resize
* Update pyarmnn version to semantic versioning
* Add fill operator
* Add Bf16 optimization
* Add Gather operator
* Update TransposeConvolution2d descriptor
* Add Rank operator
* Add load dynamic tensor support of TfLiteParser
Signed-off-by: Jan Eilers <jan.eilers@arm.com>
Change-Id: I7e76ed286ab87bd97a65ff62868ba7db7967376f
|
|
* Add Swig rules for generating python wrapper
* Add documentation
* Add tests and testing data
Change-Id: If48eda08931514fa21e72214dfead2835f07237c
Signed-off-by: Richard Burton <richard.burton@arm.com>
Signed-off-by: Derek Lamberti <derek.lamberti@arm.com>
|