aboutsummaryrefslogtreecommitdiff
AgeCommit message (Collapse)Author
2020-10-12Load dynamic backends for YoloV3Derek Lamberti
* Optional cmd option to dump optimized model to dot * Optional cmd option to specify dynamic backends path * input is now optional and must exist if given * comparison files now optional and must exist if given Change-Id: I1499c9eb715be3cacdba2c227e1a93dd997f355d Signed-off-by: Derek Lamberti <derek.lamberti@arm.com>
2020-10-12IVGCVSW-5287 Switch tests/MultipleNetworksCifar10 over to cxxoptsJames Ward
Signed-off-by: James Ward <james.ward@arm.com> Change-Id: Ia4ff69f2c8dd538ad7845053dc7a690f434c381c
2020-10-12IVGCVSW-5279 Switch armnnQuantizer over to cxxoptsMatthew Sloyan
Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com> Change-Id: I79f12ba33b3ca58cdc4be531ffbf72fa20690792
2020-10-09IVGCVSW-5291 Fix for Yolov3 producing 0s on NeonDavid Monahan
Signed-off-by: David Monahan <david.monahan@arm.com> Change-Id: I9331d590e71fc479979c11be9dc750d6435f12bc
2020-10-09IVGCVSW-5173 'Upgrade from v1.15 of tensorflow to v2.3'Sadik Armagan
* Fixed the tensorflow build issue. Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: I608c55fdf76ff4d436434c0a50b5368923d2ddb4
2020-10-09IVGCVSW-5282 Switch tests/TfLiteMobilenetQuantized-Armnn over to cxxoptsMatthew Sloyan
* Required update to cxxopts v3.0 for unrecognised options to work. Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com> Change-Id: If1803731474e42580d663c802a1f3ff240fadffe
2020-10-08IVGCVSW-5363 Add Unmap layer and Unmap workloadJim Flynn
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com> Signed-off-by: Jim Flynn <jim.flynn@arm.com> Change-Id: Ie5ecfa67e4763d0c058905592fe2e2fd7315f85c
2020-10-08IVGCVSW-5286 Switch tests/ModelAccuracyTool-Armnn over to cxxoptsMatthew Sloyan
* Fixed two code errors which were causing compiler issues. * Added support for multiple input and output tensors. Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com> Change-Id: I298e4bf52a0b41349adab60295e0f22da3cc057b
2020-10-08Remove Resize from list of layers that need padding in NeonTeresa Charlin
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: I054f0b71d4e9581c637fa09e40f6b661e58e39f3
2020-10-07IVGCVSW-5405 Remove boost::make_iterator_range and boost::to_upper_copyMatthew Sloyan
* Removed from ModelAccuracyTool-Armnn and ImageCSVFileGenerator * Fixed formatting in ImageCSVFileGenerator Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com> Change-Id: I09dfca27813582cc48f46d0507680368ed823a9c
2020-10-07IVGCVSW-5362 Add Map layer and Map workloadJim Flynn
Signed-off-by: Jim Flynn <jim.flynn@arm.com> Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com> Change-Id: Id2227c58809b84c7a7af61f7c0d88ad7d45ce558
2020-10-06IVGCVSW-4488 Update cxxopts to version 3.0Matthew Sloyan
* Required to fix issue in TfLiteMobilenetQuantized-Armnn.cpp Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com> Change-Id: I3a465f62e3d656c9626113da6223e4fa26b535a6
2020-10-06IVGCVSW-5213 Switch armnnConverter over to cxxoptsColm Donelan
* Swap out boost::program_options with cxxopts. * Remove const from argv declaration to conform to cxxopts. * Clean up CLI handling around multiple inputs and shapes. Each input must be specified with its own -i param. Each corresponding -s parameter must be specified too. Signed-off-by: Colm Donelan <Colm.Donelan@arm.com> Change-Id: I01c2683dbca51b2322c98913731ac82a59e400a5
2020-10-06IVGCVSW-5173 'Upgrade from v1.15 of tensorflow to v2.3'Sadik Armagan
* Updated the generate_tensorflow_protobuf script to search for .proto files in tensorflow directory instead of getting from a file * Updated BuildGuideAndroidNDK.md to clone Tensorflow 2.3.1 Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: I8d2b0f0a04327f930784648e9e8f7f25895d53d1
2020-10-06IVGCVSW-5407 Failing UnittestMike Kelly
* The number of error and warning messages will vary depending on the device but will always be greater than 0. Signed-off-by: Mike Kelly <mike.kelly@arm.com> Change-Id: Iee1d12e60d8c88c9116083d7274cea2ec23cb032
2020-10-05Update ACL pin to fc2f6d0427e1d886fcccc68867d1af1ccd96608bTeresa Charlin
* Set use_padding to false in neon workload Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: Ia5367de331efe1d28dea4dfbefc0713720da81f9
2020-10-02PyArmNN UpdatesÉanna Ó Catháin
* Updated setup.py to raise error on mandatory ext * Updated examples section of main readme * Added readme to img class * Moved img class to new subdir Change-Id: Iea5f6d87c97e571b8ca5636268231506538840c7 Signed-off-by: Éanna Ó Catháin <eanna.ocathain@arm.com> Signed-off-by: Jakub Sujak <jakub.sujak@arm.com>
2020-10-02IVGCVSW-5297 Remove boost::format from rest of ArmNN.Colm Donelan
* Replacing calls to boost:format with fmt:format. * TensorUtils.cpp added outputShape.reserve call. Signed-off-by: Colm Donelan <Colm.Donelan@arm.com> Change-Id: I4b2ed0f72039df824a2adca9309b8a9bbb158c5b
2020-10-02IVGCVSW-5334 Remove remaining boost::numeric_cast from armnnMatthew Sloyan
* Floating point casts now use armnn::numeric_cast. * Also removed remaining header imports. Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com> Change-Id: I2d37847d67f164fc0a0ae17f34d49ff3d2210c30
2020-10-02Update ACL pin to b84f9d34dbb857ad6113c0c89ad109498fa75fe5Nikhil Raj
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com> Change-Id: I0b8f698f20889eb09b7c881d7daadbd05f8db3c7
2020-10-02IVGCVSW-4997 'Superfluous memcopy workloads'Sadik Armagan
* If Output Layer is already connected to MemCopy Layer do not insert CopyMemGenericWorkload. Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: I9f813be5a3de2bc62d16864edb3eeaf371ef48e0
2020-10-02IVGCVSW-5306 Add floating point type checks to NumericCast.hppMatthew Sloyan
* Added Unit Tests to capture all combinations. Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com> Change-Id: I04db920a5f5f485dc00b2f16582cf7e0bbef3ef2
2020-10-02IVGCVSW-5294 Remove boost::format armnn backendsJames Ward
* replaced with fmt::format * one case required std:stringstream instead Signed-off-by: James Ward <james.ward@arm.com> Change-Id: Ife7c4cf5f143e43373f42edf6124158af132abc5
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
2020-10-01IVGCVSW-5281 Switch tests/ImageCSVFileGenerator over to cxxoptsMatthew Sloyan
Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com> Change-Id: I1b2ba4fcaebbafb70693b83b40b79db0071b4522
2020-10-01Update ACL pin to de2e747de0a63933d0cfcb75739d9460ea7c2ff5Nikhil Raj
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com> Change-Id: Ie2371f743e2ae87617693052d3887a4e6732accc
2020-10-01IVGCVSW-5285 Switch tests/ImageTensorGenerator over to cxxoptsMatthew Sloyan
Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com> Change-Id: I9d43e347021634022a875fc4526baa438c467df0
2020-10-01IVGCVSW-5283 Switch tests/profiling/gatordmock over to cxxoptsMatthew Sloyan
Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com> Change-Id: I4f06a414d6bd5f18c2ced882ac518052ed371cfc
2020-10-01Include layer GUID in SerializeToDot outputRob Hughes
Change-Id: I1a6df60683cc51fcd9739b6dc98f1e722becf045 Signed-off-by: Robert Hughes <robert.hughes@arm.com>
2020-10-01COMPMID-3784 Fix 1 CTS MUL INT32 failure due to using SATURATETeresa Charlin
* LargeGraph_TENSOR_INT32_Rank4/26 Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: I9d07444db56e26c13a77bf022938644ed7953d6b
2020-10-01IVGCVSW-5325 Fix non-channel per axis quantizationFinn Williams
Signed-off-by: Finn Williams <Finn.Williams@arm.com> Change-Id: Ie0cf69b2cd76d6ecedab43d3d9ae267d23bbc052
2020-09-30IVGCVSW-4519 Remove Boost Variant and apply_visitor variantJames Ward
* replace boost::variant with mapbox::util::variant * replace boost::apply_visitor with mapbox::util::apply_visitor * replace boost::get with mapbox::util::get Signed-off-by: James Ward <james.ward@arm.com> Change-Id: I38460cabbcd5e56d4d61151bfe3dcb5681ce696e
2020-09-30IVGCVSW-5295 Remove boost::format from armnn profilingJan Eilers
* Replace all instances of boost::format with fmt::format from armnn/src/profiling Signed-off-by: Jan Eilers <jan.eilers@arm.com> Change-Id: I4722bdde52c740bc9bdce969128074a34a3ee75e
2020-09-30Refactored Optimize(...) function to throw exceptions instead of returning nullMike Kelly
* INetwork::Optimize(...) states that the function should throw an exception if it fails but the implementation in Network.cpp returned null in some scenarios instead. This has led to some confusion amongst users. Signed-off-by: Mike Kelly <mike.kelly@arm.com> Change-Id: I358d1293232c9464772aa0e39ab3355e3570c823
2020-09-30Update ACL pin to d6d1b3682a2cdd54bae5498635b108a4b19a045aTeresa Charlin
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: I86f5848e895536334e3c6353e721ced871a192e0
2020-09-30Quantization copy constructorDerek Lamberti
* Fix compiler implicit copy deprecation warning. * Simplify copy operator by removing unnecessary equality comparison. Now just does pointer comparison instead. Change-Id: I9ebe170c637c636919b9d8729a78449148b7f83e Signed-off-by: Derek Lamberti <derek.lamberti@arm.com>
2020-09-30IVGCVSW-4519 Remove Boost Variant and apply_visitor variantJames Ward
* add mapbox/variant third party package Signed-off-by: James Ward <james.ward@arm.com> Change-Id: I181302780edd9dace40f158a11327316a12ce69a
2020-09-29IVGCVSW-5295 Change fmt to be a header-only interface libraryJan Eilers
* Fix non-virtual-dtor warnings in fmt * Fix wrong fmt include in TfParser * Make fmt work in nn-driver * Make fmt a header-only interface library * Link fmt where necessary Signed-off-by: Jan Eilers <jan.eilers@arm.com> Change-Id: I9db7cd9a133a81262cbf79f04fb419ab97b88ea8
2020-09-29Update ACL pin to d175ecea20f5c9e3bff07f7c5d3e4bb5519f7cb9Nikhil Raj
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com> Change-Id: Ib0b28b3840eb8c8d38ad32e1a572cd9a75ff8a82
2020-09-29IVGCVSW-5301 Remove all boost::numeric_cast from armnn/src/profilingMatthew Sloyan
* Replaced with armnn/utility/NumericCast.hpp Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com> Change-Id: I14e89c00cd1dd607315113d5b8ca56c2e9f6c363
2020-09-28IVGCVSW-5326 PyArmnn has hard dependencies on all parsers when using cmakeFrancis Murtagh
Signed-off-by: Francis Murtagh <francis.murtagh@arm.com> Change-Id: Ieffc1f3db548bc01ea0127a0d60659f0b0783ce3
2020-09-28IVGCVSW-5325 Speed up the reference backendFinn Williams
Change-Id: Id8bd0a0418be31d975b944b54bbacb25051ffb2e Signed-off-by: Finn Williams <Finn.Williams@arm.com>
2020-09-25IVGCVSW-4973 Enable QLstm projection unit tests on CLTeresa Charlin
*Cosmetic changes on ClQLstmWorkload Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: I61f55343263e623aaae042d8dfe8c294540e98f1
2020-09-25Update ACL pin to 840a72cc745c60eccbd26fe192b035ec68b2ee41Nikhil Raj
* Change tensor to non const to fix build error caused by ACL fix for QLSTM Signed-off-by: Nikhil Raj <nikhil.raj@arm.com> Change-Id: I7ab0f644dfb3cb3cf21bda73028e9368f3354f4a
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>
2020-09-23Update ACL pint to 1643a45557fde79ee209f55c507860307ffe627cNikhil Raj
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com> Change-Id: Id8e240a711064c48e4bdb9b1236198647e365a7f
2020-09-22IVGCVSW-5318 'Create a Neon/CL Workload Unit Test fast_math option enabled'Sadik Armagan
* Unit test implemented to make sure it returns WINOGRAD * Updated the enable-fast-math option in ExecuteNetwork to be consistent Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: Id64f114ae47966def69a9eef0770a4251ee56a41
2020-09-22Update ACL pin to 34654b2d8dcaf268a9d1bf9e0cdb5ba548ced2b7Nikhil Raj
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com> Change-Id: I3601db66ea270d6799627ac96ec95a9008d6942f
2020-09-21Added Security Issues sectionMike Kelly
* Added Security Issues section with email address. Signed-off-by: Mike Kelly <mike.kelly@arm.com> Change-Id: If1ccfd3c7847cac0a09b6ec72fdfacba0011455e
2020-09-17IVGCVSW-5303 Remove some boost::numeric_cast from rest of ArmNNMatthew Sloyan
* Replaced with armnn/utility/NumericCast.hpp * Exclusions in TypeUtils.cpp and QuantizerVisitor.cpp * Excluded as requires float implementation in NumericCast.hpp Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com> Change-Id: I5c4c60e7028e1a51bf9379457278d253fd37bc70
generated by cgit v1.2.1 (git 2.23.0) at 2024-07-01 09:55:22 +0000