Age | Commit message (Collapse) | Author |
|
* Changed documentation for fast_math to add warning about possibly reduction in precision.
Signed-off-by: Mike Kelly <mike.kelly@arm.com>
Change-Id: If954471efc6aef702e8490585571815d9e19b3fc
|
|
* 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>
|
|
Signed-off-by: James Ward <james.ward@arm.com>
Change-Id: Ia4ff69f2c8dd538ad7845053dc7a690f434c381c
|
|
Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com>
Change-Id: I79f12ba33b3ca58cdc4be531ffbf72fa20690792
|
|
Signed-off-by: David Monahan <david.monahan@arm.com>
Change-Id: I9331d590e71fc479979c11be9dc750d6435f12bc
|
|
* Fixed the tensorflow build issue.
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: I608c55fdf76ff4d436434c0a50b5368923d2ddb4
|
|
* Required update to cxxopts v3.0 for unrecognised options to work.
Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com>
Change-Id: If1803731474e42580d663c802a1f3ff240fadffe
|
|
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
Signed-off-by: Jim Flynn <jim.flynn@arm.com>
Change-Id: Ie5ecfa67e4763d0c058905592fe2e2fd7315f85c
|
|
* 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
|
|
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: I054f0b71d4e9581c637fa09e40f6b661e58e39f3
|
|
* Removed from ModelAccuracyTool-Armnn and ImageCSVFileGenerator
* Fixed formatting in ImageCSVFileGenerator
Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com>
Change-Id: I09dfca27813582cc48f46d0507680368ed823a9c
|
|
Signed-off-by: Jim Flynn <jim.flynn@arm.com>
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
Change-Id: Id2227c58809b84c7a7af61f7c0d88ad7d45ce558
|
|
* Required to fix issue in TfLiteMobilenetQuantized-Armnn.cpp
Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com>
Change-Id: I3a465f62e3d656c9626113da6223e4fa26b535a6
|
|
* 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
|
|
* 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
|
|
* 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
|
|
* Set use_padding to false in neon workload
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: Ia5367de331efe1d28dea4dfbefc0713720da81f9
|
|
* 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>
|
|
* 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
|
|
* 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
|
|
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: I0b8f698f20889eb09b7c881d7daadbd05f8db3c7
|
|
* 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
|
|
* Added Unit Tests to capture all combinations.
Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com>
Change-Id: I04db920a5f5f485dc00b2f16582cf7e0bbef3ef2
|
|
* replaced with fmt::format
* one case required std:stringstream instead
Signed-off-by: James Ward <james.ward@arm.com>
Change-Id: Ife7c4cf5f143e43373f42edf6124158af132abc5
|
|
* replaced with fmt::format
* one case required std::stringstream instead
Signed-off-by: James Ward <james.ward@arm.com>
Change-Id: Ica9a7eb4e7bed04aa03172058dd9e3d10efc8548
|
|
Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com>
Change-Id: I1b2ba4fcaebbafb70693b83b40b79db0071b4522
|
|
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: Ie2371f743e2ae87617693052d3887a4e6732accc
|
|
Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com>
Change-Id: I9d43e347021634022a875fc4526baa438c467df0
|
|
Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com>
Change-Id: I4f06a414d6bd5f18c2ced882ac518052ed371cfc
|
|
Change-Id: I1a6df60683cc51fcd9739b6dc98f1e722becf045
Signed-off-by: Robert Hughes <robert.hughes@arm.com>
|
|
* LargeGraph_TENSOR_INT32_Rank4/26
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: I9d07444db56e26c13a77bf022938644ed7953d6b
|
|
Signed-off-by: Finn Williams <Finn.Williams@arm.com>
Change-Id: Ie0cf69b2cd76d6ecedab43d3d9ae267d23bbc052
|
|
* 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
|
|
* 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
|
|
* 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
|
|
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: I86f5848e895536334e3c6353e721ced871a192e0
|
|
* 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>
|
|
* add mapbox/variant third party package
Signed-off-by: James Ward <james.ward@arm.com>
Change-Id: I181302780edd9dace40f158a11327316a12ce69a
|
|
* 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
|
|
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: Ib0b28b3840eb8c8d38ad32e1a572cd9a75ff8a82
|
|
* Replaced with armnn/utility/NumericCast.hpp
Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com>
Change-Id: I14e89c00cd1dd607315113d5b8ca56c2e9f6c363
|
|
Signed-off-by: Francis Murtagh <francis.murtagh@arm.com>
Change-Id: Ieffc1f3db548bc01ea0127a0d60659f0b0783ce3
|
|
Change-Id: Id8bd0a0418be31d975b944b54bbacb25051ffb2e
Signed-off-by: Finn Williams <Finn.Williams@arm.com>
|
|
*Cosmetic changes on ClQLstmWorkload
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: I61f55343263e623aaae042d8dfe8c294540e98f1
|
|
* 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
|
|
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>
|
|
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: Id8e240a711064c48e4bdb9b1236198647e365a7f
|
|
* 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
|
|
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: I3601db66ea270d6799627ac96ec95a9008d6942f
|
|
* Added Security Issues section with email address.
Signed-off-by: Mike Kelly <mike.kelly@arm.com>
Change-Id: If1ccfd3c7847cac0a09b6ec72fdfacba0011455e
|