Age | Commit message (Collapse) | Author |
|
Previously we were adding a reshape layer to "broadcast" tensors
for elementwise operations. This broadcast was happening too late
and was really just an expand dims. This was breaking the constant
attributes of tensors and layer support of certain backends.
* Remove addition of reshape layer when expanding dimensions
* Replace broadcast function with expand dims to equal rank function
* Fix some error status checks in various layers
* Add new TensorUtil function that expands dims to a defined rank
* Add unit tests to new TensorUtil function
Signed-off-by: Ryan OShea <ryan.oshea3@arm.com>
Change-Id: I31aca47c98075fef4f86864a15470f5faa55ab8d
|
|
* The test cases that use DebugTestImpl were creating temporary files
but not cleaning them up after running.
* Refactored FileSystem to extract a common RemoveDirectoryAndContents
function.
Signed-off-by: Colm Donelan <colm.donelan@arm.com>
Change-Id: I35b8d2eeed286742358a9abccbc078493d033902
|
|
* Added ability to reduce dimension sizes when calling BuildArmComputeTensorInfo or
BuildArmComputeTensorShapes, this will attempt to remove leading 1s in order to
squeeze the number of dimensions but retain the size.
* Changed ClBatchMatMulWorkload to attempt to squeeze the number of dimensions to 3
as the CL Gemm Kernel can only support up to 3 dimensions.
Signed-off-by: Mike Kelly <mike.kelly@arm.com>
Change-Id: I6b3d0886c5b97fdb686838fc3dc292833ddc4643
|
|
* Fixed bug when converting Constants with Per-Axis Quantization
Signed-off-by: Mike Kelly <mike.kelly@arm.com>
Change-Id: Ifbea23e60483746ec987da491dae96e74cb33af4
|
|
This tool forces explicit includes of all dependencies and
highlights unused dependencies.
Signed-off-by: Colm Donelan <colm.donelan@arm.com>
Change-Id: I92e449245246452a0227cbd13f9c082e2088bf8c
|
|
* Add functionality to print output tensors to file in tempdir
* UnitTests
Signed-off-by: Keith Davis <keith.davis@arm.com>
Change-Id: Idfb4c186544187db1fecdfca11c662540f645439
|
|
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
|
|
Change-Id: Icc2f83c5f27f413758fee3e5c1445e9fc44f42c8
Signed-off-by: Jim Flynn <jim.flynn@arm.com>
|
|
Change-Id: I18b8ca22896567904768170350ee5eb22edd4a22
Signed-off-by: Jim Flynn <jim.flynn@arm.com>
|
|
* Move MemCopyTestImpl.hpp from src/backends/aclCommon/test/ to
include/armnnTestutils.
* Refactor MemCopyTests in aclCommon, cl and Neon.
* Introduce RefMemCopyTests to exercise this utility in x86 builds.
Signed-off-by: Colm Donelan <colm.donelan@arm.com>
Change-Id: I8824f013d3656658ed0a2904bb79384e3af68641
|
|
* Moved CompatibleTypes.hpp to include folder
* Added implementation file to source CompatibleTypes.cpp
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: I94d2bffdb82a0592943f497d4f57972151d9f2db
|
|
Subtask of story: IVGCVSW-6164 Add a Pooling3d FrontEnd and Ref Implementation
* Add front end
* Add reference workload
* Add corresponding unit tests
Change-Id: Icce4146dd0a06a1da46a2def00a82d343e171750
Signed-off-by: Tamas Nyiri <tamas.nyiri@arm.com>
|
|
This reverts commit 2d9956162dd002a41f7fb4fa6753195d33524c7f.
Reason for revert: After some discussion, this does technically implement Float16 support for ExecuteNetwork, but not in a way which matches most use cases and is likely to cause issues in the future. Reverting for now.
Change-Id: I4ce6de6879216e694631f5dc68e46fb793fae0a9
|
|
* Allows the user to specify float16 as a datatype
* Does not contain support for float16 on the TfLiteDelegate via
ExecuteNetwork
Signed-off-by: David Monahan <David.Monahan@arm.com>
Change-Id: Icba56feedab32662e2cf671cc46ada899cf40c6c
|
|
* Move TContainer to armnnUtils library
Signed-off-by: Francis Murtagh <francis.murtagh@arm.com>
Change-Id: I3c0f895d11b66f6ee224ac689a19d0477f990b98
|
|
* Added front-end
* Added Reference workload
* Added Serializer & Deserializer support
* Added unit tests
* Added NDHWC DataLayout
Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com>
Change-Id: Iec4d39e7433b5334d52fa44cf8efc6bcd39319d8
|
|
!android-nn-driver:5966
Change-Id: Ice0b4d2872bb0e09bfc0763034a206c3a8f24af4
Signed-off-by: Rob Hughes <robert.hughes@arm.com>
|
|
* Reading tensor infos won't allow a permutation vector anymore.
The permutation only changed the quantization dimension not the
shape and was therefore misleading
* The permutation of the full tensor info is now performed in
armnnUtils::Permuted
* Changed TfLite Parser depthwise parsing function
* Added unit tests to TfLite Parser with more random data
* Changed TfLite Delegate depthwise parsing function
* Added unit test to the delegate with per channel quantization
!android-nn-driver:5412
Signed-off-by: Jan Eilers <jan.eilers@arm.com>
Change-Id: I1f985ee69547bcaf16a72201e00a6b6fe1ef9a97
|
|
* Added FloatingPointComparison.hpp and FloatingPointComparisonTest.cpp,
which compares two floats and returns true if the values are
within a specified or default tolerance of each other.
* Also removed boost::math::fpc from test/TensorHelpers.hpp to validate.
Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com>
Change-Id: I164c32eccd213c53bb1bc4f9cd4ee4838f1781c9
|
|
Signed-off-by: Francis Murtagh <francis.murtagh@arm.com>
Change-Id: Ib98ec471e6fdd47600b7c62d0b4d19dd36e20cbd
|
|
Change-Id: Ia4b4bb3be0ed6e933c77d58f8e9879b1370e9537
Signed-off-by: Laurent Carlier <laurent.carlier@arm.com>
|
|
* Change boost assert to armnn assert
* Change include file to armnn assert
* Fix ARMNN_ASSERT_MSG issue with multiple conditions
* Change BOOST_ASSERT to BOOST_TEST where appropriate
* Remove unused include statements
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
Change-Id: I5d0fa3a37b7c1c921216de68f0073aa34702c9ff
|
|
* Doxygen comment touch-ups
* Fixed markup in .dox files
* Fixed stylesheet
* Doxyfile changes
* Added logo file
* Added header file
Signed-off-by: Ryan OShea <Ryan.OShea2@arm.com>
Change-Id: I94c7f5a6923a0bbb5c6ed610f1f55d57e2bb8a49
|
|
* Add ConvertFloat32ToBFloat16
* Add ConvertBFloat16ToFloat32
* Add BFloat16Encoder
* Add BFloat16Decoder
* Unit tests
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
Change-Id: I198888384c923aba28cfbed09a02edc6f8194b3e
|
|
* Added TransposeLayer
* Added CL, Neon and Ref Workloads
* Added Transpose utilities
* Added Serializer and Deserializer support
* Added Quantizer support
Signed-off-by: Mike Kelly <mike.kelly@arm.com>
Change-Id: I04c755ba7cb5b1edf72b3c9f3c0314878032e3c7
|
|
* Moved the relevant armnnUtils headers to the new location:
include/armnnUtils
* Update the header usage throughout the source code
!android-nn-driver:2387
Signed-off-by: Matteo Martincigh <matteo.martincigh@arm.com>
Change-Id: I2ba15cebcacafad2b5a1a7b9c3312ffc585e09d6
|