Age | Commit message (Collapse) | Author |
|
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: Id3f1b100bdedf975e008e8f66e08747f8d8ae294
|
|
* Removed the pre-generated ArmnnSchema_generated.h
* This version was generated using flatbuffers v1.12.0 and it contains
code that's incompatible with newer versions
* Android.mk will look for ArmnnSchema_generated.h in the armnnGenerated
directory in the armnn directory.
* The Serializer and Deserializer will look for ArmnnSchema_generated.h
in the armnnGenerated directory.
!android-nn-driver:7626
Signed-off-by: Mike Kelly <mike.kelly@arm.com>
Change-Id: I13ff6b6c78740cf1f82750f56caab83200e6a3e5
Signed-off-by: Mike Kelly <mike.kelly@arm.com>
|
|
(CpuRef)
* Fixed bug occuring in Ref Gather Workload.
Signed-off-by: Cathal Corbett <cathal.corbett@arm.com>
Change-Id: I3ee79f475fd9909bfbd4afb58f698439f26d6d65
|
|
* Deserializer.cpp
* Length() has been deprecated in flatbuffers v.1.12.0 or earlier.
* SerializerTests.cpp
* armnn::BaseDescriptor& descriptor is unused.
Signed-off-by: Mike Kelly <mike.kelly@arm.com>
Change-Id: Icf0f09863f13dfd86c2c209c36c7f74f194c707b
|
|
Make some things private that don't need to be public in RefElementwiseWorkload.
Remove non-workload header files from RefWorkloads.hpp - the non-workload header
files are implementation detail of individual workloads, whereas RefWorloads.hpp
should only contain the workload definitions, needed for RefWorkloadFactory.
Signed-off-by: Matthew Bentham <matthew.bentham@arm.com>
Change-Id: I4c28963a027162a6560e56cf84b6c0063283e48f
|
|
* 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
|
|
* Test already existed but bias was not enabled so yielded false positive
* Updated Conv2d and FC to have const layers as inputs
Signed-off-by: Keith Davis <keith.davis@arm.com>
Change-Id: Id4193adef2ac67b3a4681345e4dc01414cbbbad7
|
|
* BackendHelper.cpp IsXXXLayerSupported doesn't get as far as Neon/Cl
Validate functions where arm_compute::Status is returned.
* Conv2d, Depthwise, DilatedDepthwise and FullyConnected
* Tidy up if() -> if ()
* Clean up logic in FullyConnected so that isLayerSupported gets called
Signed-off-by: Francis Murtagh <francis.murtagh@arm.com>
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: I5da1a882f4a2f55e90aa984b2b9548a847cb3a2d
|
|
* Use new INetwork::AddConvolution2dLayer
instead of deprecated version
* Remove duplicated test in SerlializerTests
* Fix some cosmetics
Signed-off-by: Keith Davis <keith.davis@arm.com>
Change-Id: I3407815bfdc1cdc01ca0a667b8e4d80d8621783f
|
|
* Cleanup and make homepage docs more concise and direct
* Highlight use of the TF Lite Delegate, guides and
AI Tech talk
Signed-off-by: James Conroy <james.conroy@arm.com>
Change-Id: I7d0221bf804dd1769568beccbca93d23cdba24b6
|
|
* Add functionality to check for ConstantTensorsAsInputs to GetConstantTensorsByRef
* Reorder optimizations so RedirectMembersToConstantInputs occurs after
Conversion of Constants
* Ensure graph is in topological order after loading in OptimizedNet
* Fixed test to check release of m_LayerOutputs.
Signed-off-by: Francis Murtagh <francis.murtagh@arm.com>
Change-Id: I7cff50798d7217e8ea0d2f9b153eabd10174a566
|
|
* No trailing permute layer after a constant layer
* Unit test for optimization
Signed-off-by: Cathal Corbett <cathal.corbett@arm.com>
Change-Id: I0d098f5af41d2c55df7cef1ccfb848093320ddc1
|
|
* Support Float16 as input to Dequantize layer
* Add Optimization to substitute Const+Dequantize layers with Const layer
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: I58bb7e3871ca480c7b6fca93c4efb2de84e09e64
Signed-off-by: David <david.monahan@arm.com>
|
|
dimensions
* Added allow-expanded-dims to TFLite parser and ArmNN delegate
* If true ArmNN will disregard dimensions with a size of 1 when
validating tensor shapes. Tensor sizes must still match.
* This allows us to support models where tensors have expanded
dimensions (i.e. extra dimensions with a size of 1).
* Fixed bug in Network where it assumed that only the first option
could be ShapeInferenceMethod.
* Fixed bug where m_ShapeInferenceMethod was lost when copying or
moving Graphs.
* Changed Delegate to pass "infer-output-shape", "allow-expanded-dims"
and other BackendOptions through to the Network during construction.
Signed-off-by: Mike Kelly <mike.kelly@arm.com>
Change-Id: Ibe7c5ae6597796fc9164cb07bd372bd7f8f8cacf
|
|
* Resolves: IVGCVSW-6952
Signed-off-by: Finn Williams <finn.williams@arm.com>
Change-Id: Ic85bd5267cf94e0ee8461ff4e62b9db3cb80877a
|
|
* Signature change is ABI/API break, overloaded and forwarded to new function.
Signed-off-by: Francis Murtagh <francis.murtagh@arm.com>
Change-Id: I8590a6fd65986b5aeff905c1e761cb5c51042e99
|
|
!android-nn-driver:7477
Signed-off-by: Cathal Corbett <cathal.corbett@arm.com>
Change-Id: Ibf633ccccc385bd980934ff829407d21981323ef
|
|
Remove use of std::unary_function and std::binary_function which were
deprecated in C+11.
Signed-off-by: Matthew Bentham <matthew.bentham@arm.com>
Change-Id: I9e4624f570b475595c9e28bdf185ddcc2ddceb2f
|
|
* Update Front-end and Tools.
* Updated Serializer, Deserializer and unit tests to reflect this.
* Updated TfLiteDelegate, TfLiteParser and OnnxParser.
* Updated Ref.
* Fixed resulting Neon / CL tests
* Unified optimizers for conv2d ops
* Optimizer Fix - Fp32ToBf16
* Partial implementation for ACL backends to fix VTS failures
!android-nn-driver:7477
Signed-off-by: Keith Davis <keith.davis@arm.com>
Change-Id: I5fb18877f7ee32643e15a9818945356274bb401b
|
|
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: I8d1584478983aeb68f65739a9ad3d4e5d3573a5c
|
|
* Add IsSupported for Pooling3d
* Add CreateWorkload case for Pooling3d
* Create new NeonPooling3dWorkload header and source files
* Add Pooling3d workload to NeonWorkloads.hpp
* Add float32 tests for Pooling3d workload
* Add Uint8 tests for Cl and NE pooling3d
Signed-off-by: Ryan OShea <ryan.oshea3@arm.com>
Change-Id: Ic992e1233d1eb8db52df2c8446183df1c907bc4d
|
|
* IVGCVSW-6940 ConstTensorsAsInput: DepthwiseConvolution2d - Complete Neon and Cl Bug Fix
* Bug fix to enable Cl and Neon Backend Compatibility ConstantTensorsAsInputs
* Updated Cl and Neon FullyConnected workloads to handle constant
weights and bias as inputs rather than reading from member variables.
* Prevent non const weights and biases passing CL and NEON validate
for Depthwise Convolution.
Signed-off-by: Cathal Corbett <cathal.corbett@arm.com>
Change-Id: I0f505ff5998a183152f843d0f6cc74327ba920e7
|
|
Change-Id: I2c23a8d7173b07aa8797a771489599762cba5a16
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
|
|
* Added backend specific optimization & test for CpuAcc and GpuAcc: PermuteDepthwiseConv2dWeights
Signed-off-by: Cathal Corbett <cathal.corbett@arm.com>
Change-Id: I600476b2e9c557a39818a574c1091c9d650b21b1
|
|
* Addressing unresolved comment.
Signed-off-by: Cathal Corbett <cathal.corbett@arm.com>
Change-Id: Ia70999582670f2b521e9e2c891831618e476024f
|
|
* Fixes Segmentation fault in RefDepthwiseConvolution2d workload
originated by IVGCVSW-6127 ConstTensorsAsInput DepthwiseConvolution2d
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: I019377777ae384bcd193ecab7b8cdf8266e79f45
|
|
* Add Unit Tests
* Bug Fix: add Sqrt to Neon and Cl workload factories
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: I0db1d813a4e7d15431e87e825e6d14e61f5ffb7d
|
|
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: I8ba7e56062c285c672dcaa9d13be319eb4f1fca6
|
|
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: I6b1c7c1c499dc93aa58fa9f58b64fb664e8bcc56
|
|
* It's possible that a model may have an input entry for bias tensors
but that the index for those is -1. If it's -1 then it's not present.
* Fixed logic error in IsOptionalOperandPresent: it returned false if
it was present and true if it was missing.
Signed-off-by: Mike Kelly <mike.kelly@arm.com>
Change-Id: I45ad8d8552122493c529b1a35a5689416ccfbb71
|
|
valid from IVGCVSW-4449
* Github issue: https://github.com/ARM-software/armnn/issues/639
Signed-off-by: Cathal Corbett <cathal.corbett@arm.com>
Change-Id: If93f2cae101814652664c671417946b94a9f749c
|
|
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: Ib90bade63cd0437329c690b09cf719a2e2bd06a4
|
|
* Add validate for all layers for GatherNd
* Fix convert policy for Mul
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: I0f2bae5107607ba3c02b5546f60dd9623cd95853
|
|
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: I195957541069cb52cdd2c8aead0e4a34498a6f38
|
|
!android-nn-driver:7418
* Update Front-end and Tools.
* Updated Serializer, Deserializer and unit tests to reflect this.
* Updated TfLiteDelegate, TfLiteParser and OnnxParser.
* Change NNDriver to new API.
* Updated Ref.
* Neon and Cl backend partially completed (Backend.cpp files).
* Added dynamic or constant input EndToEnd tests.
* Added ConstantTensorAsInputMemeberVariableRedirect Optimization.
Signed-off-by: Cathal Corbett <cathal.corbett@arm.com>
Change-Id: Ib18b6c10a093042e165e25237dc04a4c67ba82da
|
|
This reverts commit 38b72e8de898d84a1481e242803da61009719891.
* It is not longer needed as this functionality is cover with the commit:
IVGCVSW-6938 Do not add Floor when FloorDiv is int32 in Tfliteparser
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: Iac757cf9b47d2516804dca2efb347cfbd3282f14
|
|
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: I7ce633a66e2ecb72a9cdd1bff690c4195a9a449f
|
|
* Changing the test in the delegate to match one of the unit tests
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: I553ca266116ba8ee173fc951ab1ffd2b6eed1428
|
|
* Corrected TensorInfo order for IsUnidirectionalSequenceLstmSupported
* outputStateOut TensorInfo is not optional.
* cellStateOut TensorInfo is not optional.
* TensorInfo Order matches other QLSTM/LSTM layers.
* Added missing parameters to UnidirectionalSequenceLstmOperator for
delegate.
* Added quantized UnidirectionalSequenceLstm support to Neon
!android-nn-driver:7457
Signed-off-by: Mike Kelly <mike.kelly@arm.com>
Change-Id: I26dde1bb96793dd25eb9081ca5ae5f63752288c4
|
|
* Added building flatbuffer section
* Added installing cmake 3.19
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: I35925a1dc3c1fdcf3c7b7a1d44f24bd3253c9159
|
|
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: I6f7cddb2d23c67ae682132d18f98776c074dcb3b
|
|
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: I3b1f44c10a3446cfe45a7757d8a98e9788ec5dc0
|
|
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: I5c314213d3ac4fe150b0ea41cc9117add7654e50
|
|
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: I7c80299f539b64682a6a68cd1709089f71600cd9
|
|
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: I56418875b3bb2ae45b5c69bfeaafa1a6126b8085
|
|
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: I8142072f104b23c6eaf80b54cf6ddfa0393c4921
|
|
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: Ibab3525d53edbdf6a48e43b2bf668fcd2efaba58
|
|
* Add front end
* Add reference workload
* Add unit tests
* Add EndToEnd test
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: I4cebd17b18476df86162e2dda3366c10e80bd2f8
|
|
* Fix shellcheck warnings, some have been
suppressed using shellcheck ignore.
Change-Id: Icae175a42bb348a58befb296949edca51713e977
Signed-off-by: James Conroy <james.conroy@arm.com>
|
|
Signed-off-by: Jim Flynn <jim.flynn@arm.com>
Change-Id: Ic7a1cd6e03d4a2c6a717323469d429ca6cb2c914
|