aboutsummaryrefslogtreecommitdiff
path: root/src/armnnTfLiteParser
AgeCommit message (Collapse)Author
2021-09-23IVGCVSW-6181 patch to allow building against tflite > v2.3Jim Flynn
Change-Id: I292add699b2af32fab87b98929fe6fee79fdf356 Signed-off-by: Jim Flynn <jim.flynn@arm.com>
2021-09-21Revert "IVGCVSW-6181 patch to allow building against tflite > v2.3"Jim Flynn
This reverts commit fc8d434bb318aebb433a2f6d8ce9c066cd9c1b1e. Reason for revert: Causes failures in the armv8 builds need to back out and fix again later Change-Id: I5ccdbb622caaa6413de41e1ee073f38dcabff7d8
2021-09-15GitHub #577 slice layer does not handle a size of -1Mike Kelly
* Added support for size of -1 A size of -1 is treated as size = dimension - begin Signed-off-by: Mike Kelly <mike.kelly@arm.com> Change-Id: I4e381a3794852ec45be029028e2d29bc87791635
2021-09-15IVGCVSW-6181 patch to allow building against tflite > v2.3Jim Flynn
Change-Id: I4199239228f7d5f4c819a7fe04cca059a830bf1f Signed-off-by: Jim Flynn <jim.flynn@arm.com>
2021-09-03IVGCVSW-6262 Add support for Reduce ProdTeresa Charlin
* Tflite parser * Tflite delegate * Serializer * Deserializer * Ref, CpuAcc and GpuAcc workloads Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: I601a9ee1680b372c7955d9a628857d08c3cfd377
2021-09-02IVGCVSW-6294 Added support for LRN to TfLiteParserMike Kelly
* Added support for LRN to TfLiteParser Signed-off-by: Mike Kelly <mike.kelly@arm.com> Change-Id: Ia34441a4adeecd1f17c65af047d6c207729703ec
2021-08-06Replace use of non-standard variable length arraysRob Hughes
Replace these with a std::vector for portability Change-Id: Ia6b0dc9360446ef8bba0baa88c61b4c400fcd799 Signed-off-by: Rob Hughes <robert.hughes@arm.com>
2021-08-06IVGCVSW-6119 ConstTensorsAsInput: FullyConnectedMatthew Sloyan
* Constant weights and biases are now stored as Constant layers. * Updated Serializer, Deserializer and unit tests to reflect this. * Updated TfLiteDelegate, TfLiteParser and OnnxParser. * Updated Schema with IsConstant and ConstantTensorsAsInputs. * Updated Ref backend to handle constant weights and bias as inputs rather than reading from member variables. * Added dynamic or constant input EndToEnd tests. !android-nn-driver:5959 Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com> Change-Id: Ibf3cf437df1100e4b322b0d303c575c6339f9696
2021-08-05Fix for gcc 9.3.0 compiler warningJim Flynn
Change-Id: I6368925a19ee11d67b1b153cf1e7dc64eca11077 Signed-off-by: Jim Flynn <jim.flynn@arm.com>
2021-07-21IVGCVSW-6176 Add support for shape_signature in the tflite parserFinn Williams
* tflite shape_signatures will now be the preferred way to detect dynamic tensors * add test utility to the parser that converts a model's tensors to dynamic * by default tests will run a dynamic version of the model in addition to the original * fix dynamic shape inference of unpack operator * reactivate and fix quantize test * add shape inference to expand dims Signed-off-by: Finn Williams <Finn.Williams@arm.com> Change-Id: If11ba19d813cd3590707583dff1e4eb0e6412a1d
2021-07-21NNXSW-3081 Move Filesystem.hpp and Threads.hpp to public includeRob Hughes
!android-nn-driver:5966 Change-Id: Ice0b4d2872bb0e09bfc0763034a206c3a8f24af4 Signed-off-by: Rob Hughes <robert.hughes@arm.com>
2021-07-21Fixed RunTest's TfliteParser with boolean outputBruno Goncalves
Tests for TfLiteParser are not working when the expected outputs have boolean type Signed-off-by: Bruno Goncalves <bruno.slackware@gmail.com> Change-Id: I16890f82e8e581f53e6e8464668c5adf3374bf2f
2021-07-21Added comparison operators to TfLiteParserBruno Goncalves
E.g. Equal, NotEqual, Greater, GreaterOrEqual, Less and LessOrEqual Signed-off-by: Bruno Goncalves <bruno.slackware@gmail.com> Change-Id: Id56ef3cc19cc5c5daa19354010c9f25766e5fd00
2021-07-15Fix some compile warnings & errorsRob Hughes
* Fix type of literals * Add explicit casts * #include missing headers * Replace use of non-standard u_int8_t * Remove name of unused variables * Fix DLL export macro - this was broken when some of the exporting headers were moved to a different library. Change-Id: Ie569c8df41a077b46c608798f39526352e2aeb3a Signed-off-by: Rob Hughes <robert.hughes@arm.com>
2021-07-01IVGCVSW-6075 Add ParseExpandDims to TfliteParserTeresa Charlin
* Add ExpandDims tests in tfliteparser * Add support for negative axis to squeeze Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Signed-off-by: Finn Williams <Finn.Williams@arm.com> Change-Id: I604c9b4ac6514895e9e3d4d85c2937e797d288e0
2021-06-18MLCE-510 Add CpuRef Shape Operator to ArmNNKeith Davis
* Add TfLiteParser and delegate support Signed-off-by: Keith Davis <keith.davis@arm.com> Change-Id: Id3219ba7cc7128b5e73de2c7d8d076a40dcce9c5
2021-06-16IVGCVSW-5826 Change weights layout for depthwise to [1,H,W,I*M]Jan Eilers
* This change is necessary because tflite uses a [1,H,W,I*M] format and uses the I*M dimension for per axis quantization. Our previous layout [M,I,H,W] can't handle the correlating quantization scales. * Updates Onnx-, TfLiteParser and TfliteDelegate * Updates the CpuRef, CpuAcc and GpuAcc backends * Adjusts unit tests * Adds test to ensure models with old layout can still be read and executed * Adds conversion function to previous layout [1,H,W,I*M] --> [M,I,H,W] which can be used by backend developers !android-nn-driver:5553 Signed-off-by: Jan Eilers <jan.eilers@arm.com> Change-Id: Ifef23368b8c3702cf315a5838d214f7dc13c0152
2021-06-11IVGCVSW-5963 'Move unit tests to new framework'Sadik Armagan
* Used doctest in ArmNN unit tests Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: Ia9cf5fc72775878885c5f864abf2c56b3a935f1a
2021-06-02IVGCVSW-5962 Remove boost::multi_arraySadik Armagan
* Replaced all instances of boost::multi_array with flat vectors. * Updated LayerTestResult struct with new member variables. * Updated CompareTensor function to compare flat vectors and the shape. * Removed MakeTensor function from TensorHelpers.hpp. * Removed GetTensorShapeAsArray function from LayerTestResult.hpp. * Removed boost::array usage. * Removed boost::extents usages. * Removed boost::random usages. Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com> Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: Iccde9d6640b534940292ff048fb80c00b38c4743
2021-05-27IVGCVSW-6079 Fix circular dependencyNarumol Prangnawarat
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com> Change-Id: I29793ece7b6bfc015c643be3ed16529ab50f0d7d
2021-05-25IVGCVSW-3649 Add Prelu with different alpha dimension test to TfLiteParserNarumol Prangnawarat
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com> Change-Id: I982ecd66ea3ed4d88934cd8254832eecb4a7adb4
2021-05-25IVGCVSW-3649 Add TfLite parser support for Prelu layerNarumol Prangnawarat
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com> Change-Id: I3dedcc86efe1a67c709d9da636953e2fc400107b
2021-05-18IVGCVSW-5964 Removing some remaining boost utility usages from tests.Colm Donelan
* Adding a basic PredicateResult class to replace boost::test_tools::predicate_result * Replacing all uses of boost::test_tools::predicate_result with the new armnn::PredicateResult class * Replacing use of boost::test_tools::output_test_stream output with std::ostringstream in ProfilerTests.cpp Signed-off-by: Colm Donelan <Colm.Donelan@arm.com> Change-Id: I75cdbbff98d984e26e4a50c125386b2988516fad
2021-05-05IVGCVSW-5826 Add per channel testsJan Eilers
* with Conv2D for tflite parser and delegate * with TransposeConv for tflite parser Signed-off-by: Jan Eilers <jan.eilers@arm.com> Change-Id: I8d1ed1f3388c6eace436d0e6fd5869451c6e7830
2021-05-04IVGCVSW-5882 Turn off Bias when data location equals -1mathad01
* Fix bug in stack layer which causes some models to seg fault. * Turn off bias input data if data location in TfLite file is set to -1. Signed-off-by: mathad01 <matthew.haddon@arm.com> Change-Id: I0db8cfe04874979382edcf2bed336339700e3538
2021-04-22IVGCVSW-5418 ExecuteNetwork test for MobileBERTmathad01
* Removed check in TfLiteParser and Delegate that requires both weights and biases to be constant or non-constant simultaneously * Updated TfLiteParser FullyConnected layer test to properly use non-constant weights * MobileBERT Float32 model now runs on TfLiteParser Signed-off-by: mathad01 <matthew.haddon@arm.com> Change-Id: I1d75eea466caa90cd695ad353160362df2f69483
2021-04-21IVGCVSW-5842 Remove cross-wiring in depthwiseJan Eilers
* 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
2021-04-15IVGCVSW-5829 Segfault in tflite-parser, int8 modelsMatthew Sloyan
* Updated ParseSplit TfLiteParser function to read correct axis data. * Improved validation in ParseSplit and ParseSplitV function. * Added TensorFlow BOOL support to TfLiteParser. * Added supported ElementWiseUnary operators to TfLiteParser E.g. ABS, LOGICAL_NOT and RSQRT. * Removed ParseExp and ParseNeg function implementation in favour of reusable ParseElementWiseUnary function. * Removed Exp.cpp and Neg.cpp files and moved tests to ElementWiseUnary.cpp. Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com> Change-Id: Ibce36e3ce4d95755dda88abc2ddde1e07e62c5e2
2021-04-12IVGCVSW-5410 Add front-end support for CASTmathad01
IVGCVSW-5415 Add TfLiteParser support for CAST * Added front end support for CAST, including support in the Reference workload, Serialization, Deserializtion, Unit tests, and TfLiteParser. Signed-off-by: mathad01 <matthew.haddon@arm.com> Change-Id: Iaf670ca5912a21ed6bc84f7f83a68b42154846bb
2021-04-09IVGCVSW-5804 TfLiteParser fails to correctly parse ArgMinMaxMatthew Sloyan
* Fix for GitHub#523. * Updated ParseArgMinMax function to read correct axis data. * Improved validation in ParseArgMinMax function. * Added ARG_MIN support to TfLiteParser. * Added ArgMinMax unit tests for TfLiteParser. Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com> Change-Id: Ib4ce1a7c66e210c47859a130c4896aac958f2654
2021-04-09MLCE-328 Serializer/Deserializer does not support Signed64Mike Kelly
* Added support for Signed64 to flatbuffer's schema & updated source tree * Added support for Signed64 to TFLite Delegate * Added support for Signed64 to Serializer * Added support for Signed64 to Deserializer * Added unit test for ArgMinMax to Deserializer * Deprecated m_Output_Type from the ArgMinMaxDescriptor: the output type is solely determined by the DataType of the output Tensor * Fixed issue where RefArgMinMaxWorkload could output data using the wrong DataType * Added Signed64 to RefLayerSupport::IsArgMinMaxSupported as a supported type Signed-off-by: Mike Kelly <mike.kelly@arm.com> Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com> Change-Id: Ib622c052a1f8aa3e658262f8bde5a6881a8cbe10
2021-04-07IVGCVSW-5422 Add per-channel quantization tests to depthwiseJan Eilers
Signed-off-by: Jan Eilers <jan.eilers@arm.com> Change-Id: Ie51ce20540e5e7a704ce2b4be4e8cf64f91ea990
2021-03-25IVGCVSW-5741 Update FullyConnected in TfLiteParser to support NonConstWeightsFinn Williams
!armnn:5180 * Remove unnecessary memcopy for non permeuted const tensors Signed-off-by: Finn Williams <Finn.Williams@arm.com> Change-Id: Idc3ce2ac001e7d6be61819279de486f093730383
2021-03-03Point readme files to latest doxygen documentationJan Eilers
* excluding our top level readme Signed-off-by: Jan Eilers <jan.eilers@arm.com> Change-Id: I45b156c248178a141b8497dcc4d09148b67bf406
2021-02-15IVGCVSW-4873 Implement Pimpl Idiom for INetwork and IOptimizedNetworkFrancis Murtagh
!android-nn-driver:5042 Signed-off-by: Kevin May <kevin.may@arm.com> Change-Id: Ia1ce8b839e81b46428ba0f78463e085e5906958d Signed-off-by: Francis Murtagh <francis.murtagh@arm.com> Signed-off-by: Finn Williams <Finn.Williams@arm.com>
2021-02-11MLCE-360 'ReduceLayer InferOutputShape Issue'Sadik Armagan
* Updated ParseReduce() function in TfLiteParser to read correct axis data * Remove unused m_TargetWidth and m_TargetHight from ReduceDescriptor * Updated the ArmNN Serializer Schema Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: I98b6e00ccba1d8ea8c845cb1ae28840e42339629
2021-02-09MLCE-347 'REDUCE_MIN, REDUCE_MAX, REDUCE_SUM Support'Sadik Armagan
* Added TfLiteParser support for REDUCE_MIN and REDUCE_MAX operators * Added ACL workloads support for REDUCE_MIN, REDUCE_MAX, and REDUCE_SUM operators * Added TfLite Delegate support for REDUCE_MIN, REDUCE_MAX, and REDUCE_SUM operators Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: I8085d59946bfd4ab78a59a61f899031ae53371a8
2021-02-08IVGCVSW-4901 Add semantic versioning to Parsers and TfLite DelegateMatthew Sloyan
* Added Version.hpp to all Parsers * Added Version.hpp to TfLite Delegate * Updated CMakeLists to use new versions * Added GetVersion method to parsers and TfLite Delegate Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com> Change-Id: If29e1e6d9e615f9095ec1c01ad47acfff40b1dd5
2021-02-08IVGCVSW-5605 Doxygen: Update parser sectionJan Eilers
* Removes support.md files from all parsers. Lists of supported operators are now kept in doxygen only Signed-off-by: Jan Eilers <jan.eilers@arm.com> Change-Id: I137e03fdd9f41751624bdd0dd25e2db5ef4ef94f
2021-02-04IVGCVSW-5592 Implement Pimpl Idiom for Tf and TfLite ParsersKevin May
Signed-off-by: Kevin May <kevin.may@arm.com> Change-Id: I4a82aca4a2c47b3c598b91bc0075c09397be728a
2021-02-03backends/reference: Add ReduceSum operation supportSadik Armagan
This patch addes ReduceSum operation support for reference backend, which computes the sum of elements across dimensions of a tensor. Changelog v1: - Fix file header descriptions. Chagelog v2: - Fix line limit issue. - Fix type conversion issue. Changelog v3: - Remove tabs. - Modify newly added file headers. Changelog v4: - Symbol on header isn't allowed so drop it from newly added file headers. Changelog v5: - Remove tabs, fix the use of brackets and align lines correctly. Changelog v6: - Add serializer and deserializer support. Changelog v7: - Fix build error add missed code. Changelog v8: - Rename ReduceSumDecriptor to ReduceDescriptor - Update m_KeepDims field data type to bool on ReduceDescriptor - Add ReduceOperation field to ReduceDescriptor - Rename ReduceSumLayer to ReduceLayer - Update ReduceLayer to use ReduceDescriptor - Update ReduceLayer::ValidateTensorShapesFromInputs() function - Rename RefReduceSumWokload to RefReduceWorkload - Update workload to use ReduceDescriptor - Update workload to use Decoders and Encoders - Remove ReduceSum.hpp and ReduceSum.cpp - Added Reduce.hpp and Reduce.cpp - Move Mean.cpp (which is implementing REDUCE_MEAN) functionality to Reduce.cpp - Update RefMeanWorkload to call Reduce function with ReduceOperation::Mean argument - Remove Mean.hpp and Mean.cpp - Update the Serializer/Deserializer ArmnnSchema.fbs for ReduceLayer, ReduceDescriptor, and ReduceOperation - Update Serializer and Deserializer for serializing/parsing ReduceLayer - Added TfLiter parser Sum test for REDUCE_SUM operator - Make corresponding changes on front-end and Ref backend to support REDUCE_SUM operator Changelog v9: - Fixed build errors. Change-Id: I8c8e034f3df73f9565b3c18eff51ecca6c542195 Signed-off-by: Inki Dae <inki.dae@samsung.com> Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
2021-01-22MLCE-335 'DEPTH_TO_SPACE and GATHER operator support in TfLiteParser'Sadik Armagan
* Added GATHER operator support to TfLiteParser * Added DEPTH_TO_SPACE operator support to TfLiteParser Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: Id5d3b54e2d850eb9f19417029efbeb73a3029e69
2021-01-20MLCE-336 'TfLite parser and ExecuteNetwork issues'Sadik Armagan
* Report the error thrown Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: If5e5160f43c11a284b919d76b04d9c4d53e9c56c
2021-01-15IVGCVSW-5424 TFLite parser not parsing new TransposeConvDavid Monahan
* Added support for bias vector in TransposeConv to TfLite parser * Added UnitTest Signed-off-by: David Monahan <david.monahan@arm.com> Change-Id: I6483986a9da9216084b4b885b7fd980fc3580fa9
2020-12-17IVGCVSW-5614 Enable Hard Swish and Elu activationsMatthew Sloyan
* Enabled Hard Swish and Elu in TfLiteDelegate * Added support for Elu in TfLiteParser Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com> Change-Id: If09321b58568a98e14cabce610a1586556da041e
2020-12-16IVGCVSW-5595 Fix incorrect padding value for asymmetric quantized typeNarumol Prangnawarat
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com> Change-Id: I85f0c30757043f8c27c78d607f0f9dbbdd35b9fb
2020-11-24IVGCVSW-5347 Update Readme for 20.11Teresa Charlin
* Adding delegate readme.md and TensorFlowLiteDelegateSupport.md Change-Id: I1b8012440cf4cd6120902ad69c5b3a2a5e410d71 Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
2020-10-29IVGCVSW-5265 Remove boost from core ArmNN CMakeColm Donelan
* Remove all but Boost_UNIT_TEST_FRAMEWORK_LIBRARY from ArmNN Cmake files. * Remove references to boost::fpc from old test applications. Signed-off-by: Colm Donelan <Colm.Donelan@arm.com> Change-Id: Ibb1261dee4b971d1788d2805528aa800a8b883ce
2020-10-02IVGCVSW-5296 Remove boost::format armnn parsersJames Ward
* replaced with fmt::format * one case required std::stringstream instead Signed-off-by: James Ward <james.ward@arm.com> Change-Id: Ica9a7eb4e7bed04aa03172058dd9e3d10efc8548
2020-09-24Add int32 and int64 ArgMax op supportInki Dae
This patch adds int32 and int64 ArgMax op support. Current ARMNN already has ArgMax op but not used, and it doesn't support int64 output type. So this patch adds a new type, Signed64, and also adds ArgMinMax computation function for int64 type support. In default, output tensor type of ArgMax op is int64 in case of tensorflow lite model so this patch makes a proper function - ArgMax op for int64 or int32 - to be called according to parsed output_type value. With this patch, ARMNN supports both types - int64 and int32 - for ArgMinMax op. Changelog v1: - Check if output data type of ArgMinMax op is valid or not. - Use template function to support int32 and int64 types of ArgMinMax function. - Keep using Signed32 as default data type of m_Output_Type. Change-Id: I7a8e7e38dd9e5acc81464571d8b4d51378fc7f14 Signed-off-by: Inki Dae <inki.dae@samsung.com>
generated by cgit v1.2.1 (git 2.23.0) at 2024-07-11 03:22:04 +0000