aboutsummaryrefslogtreecommitdiff
path: root/src/armnnTfLiteParser
AgeCommit message (Collapse)Author
2020-03-10IVGCVSW-4482 Remove boost::ignore_unusedJan Eilers
!referencetests:229377 Signed-off-by: Jan Eilers <jan.eilers@arm.com> Change-Id: Ia9b360b4a057fe7bbce5b268092627c09a0dba82
2020-03-04IVGCVSW-4213 Enable split along any dimensionRyan OShea
* Remove check on split dimension Signed-off-by: Ryan OShea <Ryan.OShea2@arm.com> Change-Id: I03b88b8c8f1dcd842d9cc9d783ad7d0aa2c0ed3a
2020-03-03IVGCVSW-4375 Add parser support for TransposeMike Kelly
* Changed TfParser::ParseTranspose to use Transpose instead of Permute * Changed TfLiteParser::ParseTranspose to use Transpose instead of Permute !armnn:2787 Signed-off-by: Mike Kelly <mike.kelly@arm.com> Change-Id: If48f2fb88d97d31d66b6b1e631b41637d8e4c8f0
2020-02-20IVGCVSW-4432 Update Readme for 20.02Sadik Armagan
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: I416b39b0adac1410f854d3ec5b855044bd85e1cc
2020-02-19IVGCVSW-4472 Yolo v3 ExecuteNetwork failingKeith Davis
* Add Debug workload for QAsymmS8/U8 * Change Dequantize tests to test AsymmS8 instead of SymmS8 * Fix incorrect supportedness within RefLayerSupport Signed-off-by: Keith Davis <keith.davis@arm.com> Change-Id: Ie51f1e33c564d46c86bf0150b1addda3fc093d13
2020-02-18COMPMID-3059: Add TF parser support for StridedSliceGeorgios Pinitas
Signed-off-by: Georgios Pinitas <georgios.pinitas@arm.com> Change-Id: I31f25f26a50c9054b5650b1be127c84194b56be7
2020-02-17IVGCVSW-4436 Add ExecuteNetwork test for mobilenet_v2_int8Keith Davis
* Add QAsymmS8 to QueueDescriptor supportedTypes * Add QSymmS8/QAsymmS8 to RefLayerSupport supportedTypes * Some additional comments and refactoring Change-Id: I8567314452e6e8f6f69cb6e458ee147d3fc92fab Signed-off-by: Keith Davis <keith.davis@arm.com>
2020-02-10IVGCVSW-4409 Fix TfLiteParser to handle all datatypes correctlyRyan OShea
* Added check for QAsymmS8 datatype for Per-Tensor quantization Signed-off-by: Ryan OShea <Ryan.OShea2@arm.com> Change-Id: I902aa3863dd5cefdce90e68be8a5750dd6ff9e54
2020-02-07MLCE-139: add capability to align corners for bilinear resizeSang-Hoon Park
* Add parsing of the related parameter to TfLiteParser * Update ResizeDescriptor to store the additional parameter * Update NEON/CL workload to pass the additional parameter. * Update Reference workload to pass and handle the additional parameter. !ComputeLibrary:2538 !ComputeLibrary:2569 !armnn:2612 Signed-off-by: Sang-Hoon Park <sang-hoon.park@arm.com> Change-Id: Id149e1c24c2abed7e9dd81939acf54dfabfcdfd2
2020-01-28IVGCVSW-4335 Add support for per-channel QSymm8 to TfLite parserKeith Davis
Signed-off-by: Keith Davis <keith.davis@arm.com> Change-Id: I52f777f56138a27655a821aff376ecd0d3d23511
2020-01-20Remove use of ArmNN.hpp where it is unnecessary.Matthew Bentham
Signed-off-by: Matthew Bentham <Matthew.Bentham@arm.com> Change-Id: I6c90eab1c6bad76d5c7b3bf094998fa4b454bcd1
2020-01-15Support different flatbuffer libs for debug and releaseRob Hughes
The existing FLATBUFFERS_LIBRARY variable is still honoured, but if not specified then we use CMake's find_library to find the debug and release variants, using PATH_SUFFIXES to help separate debug and release. This is the same approach we use for the armcompute libs. Change-Id: I21e8da3f76669dbfb8dbdf49046f9db46cba50a2 Signed-off-by: Robert Hughes <robert.hughes@arm.com>
2020-01-15IVGCVSW-4193 Add QUANTIZE to the TfLite parserSadik Armagan
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: I53431c70edb64c9283ae556407cc07e54469d8cc
2020-01-13Rename quantized data types to remove ambiguity for signed/unsigned payloadsDerek Lamberti
!android-nn-driver:2572 Change-Id: I8fe52ceb09987b3d05c539409510f535165455cc Signed-off-by: Derek Lamberti <derek.lamberti@arm.com>
2020-01-03IVGCVSW-4246 Clean build of parsers with -WextraDerek Lamberti
Change-Id: Ib00f185b431ab74fd9425d8f478bd2ddb182f74b Signed-off-by: Derek Lamberti <derek.lamberti@arm.com>
2019-12-31Replace Schema.s with generated .cpp fileRob Hughes
This removes the dependency on an assembler (which must support .incbin). Instead we use xxd as a custom build command to generate a .cpp file which is included in the build. This makes it possible to build on Windows, for which you need cp.exe (from GNU Core Utils) and xxd.exe (from Vim). Change-Id: I3a929640b1fdbfc27e2c38abd05bf3a298245ba5 Signed-off-by: Robert Hughes <robert.hughes@arm.com>
2019-12-31Some build fixes for MSVCRob Hughes
Change-Id: I749430918b1268786690c3c8dc9fa2a9542d5d1d Signed-off-by: Robert Hughes <robert.hughes@arm.com>
2019-12-10IVGCVSW-4191 Add DEQUANTIZE to the TfLite ParserFinn Williams
!armnn:2421 Change-Id: Icdb02b7248ed408c3c8ad2e3e38df5b7cda1c545 Signed-off-by: Finn Williams <Finn.Williams@arm.com>
2019-12-05Replace boost logging with simple loggerDerek Lamberti
!referencetests:214319 * Reduces arm nn binary size ~15% * Also fixed test logging black hole issues Change-Id: Iba27db304d9a8088fa46aeb0b52225d93bb56bc8 Signed-off-by: Derek Lamberti <derek.lamberti@arm.com>
2019-12-05IVGCVSW-4179 Add RESIZE_NEAREST_NEIGHBOUR to the TfLite parserSadik Armagan
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: I6359a8a405c86aef04cde75404393dd4ee917fa5
2019-11-29IVGCVSW-4209 Create a public API for the ArmNN UtilsMatteo Martincigh
* 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
2019-11-19IVGCVSW-1530 Add TfLite slice parser and fix transpose perm vector creationjosh minor
* TfLite slice parser and relevant tests added * TfLite transpose parser logic added to translate Tf/np permutation vector definitions to Armnn definitions * TfLite transpose parser no permute data test modified to include data for default permutation vector when none specified Signed-off-by: josh minor <josh.minor@arm.com> Change-Id: Iebd30971bd180593dc6b8f0d5be1d1bc61a3a5bf
2019-10-31GitHub #292 Move BackendRegistry.hpp to the public APIMatteo Martincigh
* Moved to BackendRegistry.hpp include/armnn * Updated makefiles and sources accordingly Signed-off-by: Matteo Martincigh <matteo.martincigh@arm.com> Change-Id: I4d83abb581d523218a880c879fcf30c9611f7fd7
2019-10-25IVGCVSW-4018 Move QuantizeHelper.hpp to armnnUtilsAron Virginas-Tar
* Moved QuntizeHelper.hpp to armnnUtils * Reordered parameters for QuantizedVector and added default values for qScale and qOffset to make life easier when using the function for non-quantized types such as Float16 Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com> Change-Id: I28c263dfa425f1316feccb4116839a84f5d568e5
2019-10-24IVGCVSW-4007 Add StandInLayer for unsupported operations in TfLiteParserAron Virginas-Tar
* Fixed bug in custom operator support that caused all custom operators to be parsed as a DetectionPostProcessLayer * Added support for handling unsupported operators (built-in or custom) by replacing them with a StandInLayer in the generated network * Added options to TfLiteParser to control whether we want to use StandInLayers when we encounter unsupported operators, or we prefer to throw a ParserException as until now Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com> Change-Id: I125a63016c7c510b1fdde6033842db4f276718c4
2019-10-22IVGCVSW-3669 Fix TfLiteParser to set Splitter layer outputs' quantization paramsFrancis Murtagh
Signed-off-by: Francis Murtagh <francis.murtagh@arm.com> Change-Id: I6c69f1f2f0f9c49ddada57b41d5802919ea14b25
2019-10-22Fix Unpack in TfLiteParser missing quantization parametersNarumol Prangnawarat
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com> Change-Id: I026e4880013fa4ed83b6c4643dda7e4d100014a5
2019-10-18Github #275 Generate versionned librariesMatteo Martincigh
* Improved parsing of the ArmNN's version at compile time * Reading the version directly from the Version.hpp file, to make sure not to break any build made with a different build system than CMake (or Ninja) * The version macro is set in the Version.hpp just like before, so setting it from the command line is no longer necessary !android-nn-driver:2126 Signed-off-by: Guillaume Gardet <guillaume.gardet@arm.com> Signed-off-by: Matteo Martincigh <matteo.martincigh@arm.com> Change-Id: I0820094607734d283ded030e4ded0ae6f5889c86
2019-09-27IVGCVSW-3909 Fix Transpose perm vector not parsed by Tflite parserKevin May
* Add permute vector to descriptor if present * Refactor test to check with and without permute vector Signed-off-by: Kevin May <kevin.may@arm.com> Change-Id: Ic8d882bb0f982fd00bb2854c18ea316b1b2cde2b
2019-09-17IVGCVSW-3879 Fix output shape inference formula for TransposeConvolution2dAron Virginas-Tar
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com> Change-Id: I766f4297b9daa26edacc2079fe62a083ba2fa68f
2019-09-10IVGCVSW-3712 Add Transpose into TfLite ParserKeith Davis
Signed-off-by: Keith Davis <keith.davis@arm.com> Change-Id: I94e975ede3876c812f0f26b040e8c50a5597f86a
2019-08-27IVGCVSW-3507 Removed partially supported networksMike Kelly
* FCRN and FSRCNN aren't supported on all backends yet. Signed-off-by: Mike Kelly <mike.kelly@arm.com> Change-Id: Ibaddfba731224aac24de05c225fb94efd3fe7f94
2019-08-23Fix Windows build:Rob Hughes
* CMake "install" commands require a RUNTIME argument for platforms with DLLs (e.g. Windows). * Replace use of non-standard variable length array with vector * Remove unnecessary #include of unistd.h * Add #ifdefs to dynamic backend code to disable for non-Unix platforms where you can't use dlopen etc. We could implement this properly for Windows later using LoadLibrary etc., but for now erroring is fine. * Add missing #include of <algorithm> Change-Id: Ic8ef5fd599b37bf8772510157b6e479819f6a1eb
2019-08-21IVGCVSW-3507 Fix error in list of tested networks for Tf and TfLite parsersAron Virginas-Tar
* Move DeepSpeaker, FCRN and FSRCNN from TensorFlowSupport.md to TensorFlowLiteSupport.md Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com> Change-Id: I82d508d3599073eb8f6638994a91f46b4b95c247
2019-08-21IVGCVSW-3507 Revise and update readmes for 19.08Aron Virginas-Tar
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com> Change-Id: I3da43122240fda7864e0932d47b3efeea8bbed40
2019-08-21IVGCVSW-3650 Fix Transpose Convolution inputs in TfLite parserMatthew Jackson
* Reordered and edited inputs in ParseTransposeConv method * Updated test cases to reflect changes Signed-off-by: Matthew Jackson <matthew.jackson@arm.com> Change-Id: Icd090cf6ab340eed4f098ef8641daf7c6e0d0949
2019-08-20IVGCVSW-3650 Add TfLite Parser support for Transpose Convolution layerMatthew Jackson
* Added ParseTransposeConv to TfLite Parser * New TransposeConv test file * Updated documentation for supported Transpose Convolution Change-Id: Id7356d8525556805c164af693ae2b16f6a8492fa Signed-off-by: Matthew Jackson <matthew.jackson@arm.com>
2019-08-16IVGCVSW-3639 Add 5d tensor supportMatthew Jackson
* Increased MaxNumOfTensorDimensions and fixed issues related to its use * Fixed issues caused by assuming 5d tensors are invalid * Updated ArmComputeTensorUtils for 5d tensors * Added 5d tensor unit tests for add, mul, stack and reshape (needed by IVGCVSW-3527) Signed-off-by: Matthew Jackson <matthew.jackson@arm.com> Change-Id: I5bcd64942d0d04efcc6c5acb240ad4b88e010743
2019-07-22Github #229 Remove unused includeMike Kelly
* experimental/filesystem is unavailable in some versions of LLVM Change-Id: I0136bc911f2607561e8000fe9fa7c07f480554b6 Signed-off-by: Mike Kelly <mike.kelly@arm.com>
2019-07-22IVGCVSW-3368 Add reference support for depthwise multiplier > 3Matthew Jackson
* Remove multiplier check in TfLite parser * Add reference unit test for depthwise multipler of 64, as in DeepSpeaker Signed-off-by: Matthew Jackson <matthew.jackson@arm.com> Change-Id: I787339ab4c4d269333985353d191202d070906ba
2019-07-22IVGCVSW-3383 - Add TfLite Parser support for L2 Normalization layerMatthew Jackson
* Added ParseL2Normalization in TfLiteParser * Added new unit tests L2Normalization.cpp * Added documentation for supported L2 Normalization to TensorflorLiteSupport.md Signed-off-by: Matthew Jackson <matthew.jackson@arm.com> Change-Id: I83ea75d1791ac8a00390aed3e5d0a7b337fcd46d
2019-07-17IVGCVSW-3423 Add TfLite parser support for Stack (Pack) layerMatthew Jackson
* Added ParsePack method * New unit test Pack.cpp * Updated TensorFlowLiteSupport.md with new supported operator Signed-off-by: Matthew Jackson <matthew.jackson@arm.com> Change-Id: I2310b33ee26959b036bb4452a25c90cc1d4cbf20
2019-07-02IVGCVSW-3382 Deprecate ResizeBilinear and use Resize with Bilinear methodAron Virginas-Tar
!android-nn-driver:1451 Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com> Change-Id: Ieedbce1f6e95891137a250fdd07e2f7e4e1f4828
2019-06-03MLCE-124 Fix install target wrt serializer and tflite parserMatthew Bentham
Change-Id: If38336f1678504849edb0134a59daae1c8d9ef92 Signed-off-by: Matthew Bentham <matthew.bentham@arm.com>
2019-05-30MLCE-119: Allow deph multipliers 2 and 3Pablo Tello
We had check in the parser to catch calls where deph_mult > 1, this came from the time when ACL supported only multiplier == 1. Change-Id: Ic21a2cd6a5bb328d43fc9c667e847429a57760b2 Signed-off-by: Pablo Tello <pablo.tello@arm.com>
2019-05-23IVGCVSW-2771 Fix SubTensor error in vgg16 ExecuteNetwork NEONNarumol Prangnawarat
* Add check if Sub-tensors cannot be used, call ACL function * Add computation of SplitAxis from SplitterDescriptor * Add NeonSplitterWorkload functions * Modify IsSplitterSupported to call ACL validate function if sub-tensor cannot be used * Also check if quantization parameters match when using sub-tensors * Add more unit tests for Splitter in TfParser and TfLiteParser Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com> Change-Id: I31e4c7d055117c83c65b598c4125442173242226
2019-05-14Use the new deprecation APIMatteo Martincigh
* Used the new ARMNN_DEPRECATED_MSG macro instead of @deprecated * Refactored the code to no longer use the deprecated methods where applicable !android-nn-driver:1126 Change-Id: Ib0578d3d6fc5a763f5fb922f67ba91fafc7796f6 Signed-off-by: Matteo Martincigh <matteo.martincigh@arm.com>
2019-05-14IVGCVSW-3076 Add ConcatLayer methods to public APIJim Flynn
!android-nn-driver:1120 Change-Id: I5192fa3deb4ea9766d38ad0bf4dfbfa0b4924c41 Signed-off-by: Jim Flynn <jim.flynn@arm.com>
2019-05-13MLCE-101: Adding dilation support in conv and dconvPablo Tello
Added support for dilation in DepthwiseConvolution2d in the Neon and CL backends. Change-Id: Ie1522b498c07f80d6efcf9dc79e926c8cfa06ca5 Signed-off-by: Pablo Tello <pablo.tello@arm.com>
2019-05-02IVGCVSW-3039 Unify BindingPointInfo declarationsJim Flynn
Change-Id: I3deb2b9a37e8a8f8f2ed93c64ed0656ae911e24c Signed-off-by: Jim Flynn <jim.flynn@arm.com>
generated by cgit v1.2.1 (git 2.23.0) at 2024-07-02 02:22:19 +0000