aboutsummaryrefslogtreecommitdiff
AgeCommit message (Collapse)Author
2019-11-05IVGCVSW-4065 Refactor the IPacketBuffer smart pointersMatteo Martincigh
* Added convenience "using" statement for the unique pointers to IPacketBuffer * Replaced all the occurrencies in the code Signed-off-by: Matteo Martincigh <matteo.martincigh@arm.com> Change-Id: Iffec3a425ffbc1ecb23012971563a48139eb32eb
2019-11-05IVGCVSW-3836 Add support for Int32 per-axis scalesAron Virginas-Tar
* Added ScaledInt32PerAxisDecoder implementation * Added new case for Signed32 in MakeDecoder that returns a ScaledInt32PerAxisDecoder if the tensor info has multiple quantization scales Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com> Change-Id: I8b3c11091644da993044d2a0fe2aba6b06b5af56
2019-11-05IVGCVSW-3843 Add support of per-axis quantization to BuildArmComputeTensorInfoAron Virginas-Tar
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com> Change-Id: I0bb0e9da306eee3e19dc9967a6c8bb01da998deb
2019-11-04IVGCVSW-3835 Create Encoder and Decoder for QSymm8PerAxisKeith Davis
* Add QuantizedSymm8PerAxis to armnn DataType (types.hpp) and * Add Quantize and Dequantize template for int8 in TypeUtils to be able to compute QSymm8 of the weight * Create PerAxisIterator for per-axis quantization * Create QSymm8PerAxisDecoder * Create QSymm8PerAxisEncoder Signed-off-by: Keith Davis <keith.davis@arm.com> Change-Id: Ibcfe0288a197b7ee50b543bdbd77b7edb8a547c2
2019-11-04Add fp16 support for dequantizeJan Eilers
* Changed RefDequantizeWorkload to use Encoder/Decoder * Added related unit tests for Cl, Neon and Ref Signed-off-by: Jan Eilers <jan.eilers@arm.com> Change-Id: Ic2fd4103090dd2127c6859b49305736f7b2dfb05
2019-11-04Make onnx parser to support TanH / Sigmoid / LeakyRelu layersTee Jung
Signed-off-by: Jung Tae-young tee.ty.jung@openedges.com Change-Id: I44d24b525b78b8d3fee0197abda7bd667eb04d83
2019-11-04Fix crash issueTee Jung
* armnnOnnxParser makes tensorInfo from graph->value_info but PyTorch does not add weight/bias tensor information to graph->value_info so tensorInfo of const tensor should be extracted from graph->initializer Signed-off-by: Jung Tae-young tee.ty.jung@openedges.com Change-Id: Ib2656dd25abc522012cf413e843fe03949cb2eb0
2019-11-04Match shape in between initializer and tensorTee Jung
* Added extra dims definition for the second dimension of the weights Signed-off-by: Jung Tae-young tee.ty.jung@openedges.com Signed-off-by: Matteo Martincigh <matteo.martincigh@arm.com> Change-Id: Ifeeff5c3d4733dbb9c246242fc4b796eb4d515a5
2019-11-01Better error reporting for unconnected layersMatthew Bentham
Change-Id: I3c461e5449cf4bfa94d6d5e8dee03c210f2734e5 Signed-off-by: Matthew Bentham <Matthew.Bentham@arm.com>
2019-11-01IVGCVSW-4050 Add backward compatibility deserialization test for ResizeBilinearAron Virginas-Tar
* Added test SerializeResizeBilinear to ensure that ResizeBilinear layers are serialized as Resize layers * Added test EnsureResizeBilinearBackwardCompatibility to ensure the Deserializer is still able to deserialize an old binary that contains a ResizeBilinear layer and that it creates the correct equivalent Resize layer from it Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com> Change-Id: If227c5f1f3d027dff7d8f306dee97fd488755a72
2019-11-01IVGCVSW-3698 Add EndToEnd Layer test for ArgMinMaxNarumol Prangnawarat
* Add EndToEnd test implementation for ArgMinMax * Add EndToEnd tests for Ref * Fix output data type of ArgMinMax in WorkloadFactory Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com> Change-Id: I6d07d25bb96ab21422584284046222257ddee43c
2019-11-01Increase tolerance for bias scale quantization calculation for ResNet50v2ricbur01
Signed-off-by: Richard Burton <richard.burton@arm.com> Change-Id: I033ef445fa8e5ae825cfde29927b88e97e20f093
2019-11-01GitHub #292 Build the ML-examples using only ArmNN's public frontend APIMatteo Martincigh
* Refactoring of some of the public API headers Signed-off-by: Matteo Martincigh <matteo.martincigh@arm.com> Change-Id: I9006fe49945b10a6b83908b05aa4a6556639b491
2019-10-31Fix bug in deserializitaion of ResizeLayerAron Virginas-Tar
* Fixed return value for armnnSerializer::ResizeMethod_Bilinear in ToResizeMethod() Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com> Change-Id: If5ea0fbfec6986d11c409f7072390b8c65805aa9
2019-10-31IVGCVSW-4049 Fix potential threading issue with the SendCounterPacket threadFinn Williams
Signed-off-by: Finn Williams <Finn.Williams@arm.com> Change-Id: I311270dac0ba90b04e3488572e6b045546114a12
2019-10-31Github #277 Add option to use shared boost librariesMatthew Bentham
Pass -DSHARED_BOOST=ON to cmake to link dynamically to boost. This makes it possible to use standard package-installed boost libraries in a native build. Change-Id: I6cbd72fae8b0cf8ae07f4382ab0510854c1623fd Signed-off-by: Matthew Bentham <Matthew.Bentham@arm.com>
2019-10-31Github #220 Mention deprecated Caffe features in the Caffe parser READMEMatthew Bentham
Change-Id: I443dcc9545392a0b17ffd700d2f14cbed64d35e7 Signed-off-by: Matthew Bentham <Matthew.Bentham@arm.com>
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
2019-10-31IVGCVSW-3842 Add per-axis quantization support to ↵Aron Virginas-Tar
ValidateBiasTensorQuantization() * Altered the function to validate all the scale values in the bias tensor info when per-axis quantization is enabled * Added unit test to check if ValidateBiasTensorQuantization() works as intended Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com> Change-Id: I676d17690cda6bbdd41da5fdbaa50a3d3b5fd102
2019-10-31IVGCVSW-4039 AndroidQ (HAL 1.2) driver support for Fp16Sadik Armagan
* Call ACL Validate function for validating Floor operator on CL backend Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: I2206ec86de6eabd18c12d023116d1f4c24487e0d
2019-10-30IVGCVSW-4037 Add a CreateNamedTypedChildEntity methodNarumol Prangnawarat
* Added new method to the TimelineUtilityMethods class * Added unit tests * Code refactoring * Skipped the 0 when generating a dynamic GUID for testing purposes Signed-off-by: Matteo Martincigh <matteo.martincigh@arm.com> Change-Id: Ic2c8033ad010e07b0f8b7971ce653263e21c6f97
2019-10-30IVGCVSW-4036 Add CreateNamedTypedEntity functionNarumol Prangnawarat
* Add CreateNamedTypedEntity function * Add NameEntity function * Add TypeEntity function * Unit tests Change-Id: I3cc27157a0b41c8709b0a468f93b58b63a1ad8d1 Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
2019-10-30IVGCVSW-3831 Add support of per-axis quantization to TensorInfoAron Virginas-Tar
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com> Change-Id: Iea09539c92d51e546fbad8b2903b59fc08d66618
2019-10-30IVGCVSW-4035 Add a CreateTypedLabel functionMatteo Martincigh
* Create new utility function in the TimelineUtilityMethods class * Added unit tests Signed-off-by: Matteo Martincigh <matteo.martincigh@arm.com> Change-Id: I63704b94d5cc6861e4e160de2aae4ae497699dd2
2019-10-29Add GetResizeMethodAsCString() function to TypesUtils.hppAron Virginas-Tar
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com> Change-Id: Id00eeb7f5e833226aee5e03f8711ab2ae5a84e30
2019-10-29Refactor Resize layer testsAron Virginas-Tar
* Move implementations to newly created source file ResizeTestImpl.cpp, leave only the declarations in the header * Reduce code duplication by extracting common code into a generic implementation template Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com> Change-Id: Ib8aa395e5fb4470b26cbe943c177f6b64c860a93
2019-10-28IVGCVSW-4033 Provide a utility method to send the 'well known'Matteo Martincigh
labels and event classes * Added utility method SendWellKnownLabelsAndEventClasses * Added unit tests Signed-off-by: Matteo Martincigh <matteo.martincigh@arm.com> Change-Id: Id8ec0d0eb6861feb8b61731e656d1571effc904a
2019-10-28IVGCVSW-4031 Provide well known profiling GUIDsJim Flynn
Change-Id: Ibf99b025f51503e8937012b655aad74698f32e38 Signed-off-by: Jim Flynn <jim.flynn@arm.com> Signed-off-by: Matteo Martincigh <matteo.martincigh@arm.com>
2019-10-28Fix ExecuteNetwork no longer printing out the inference results,Matteo Martincigh
breaking some of the nightly builds * The TensorPrinter must be called regardless of the value of the output tensor files, it will automatically handle an empty file path by only printing the results to the console * Code refactoring Signed-off-by: Matteo Martincigh <matteo.martincigh@arm.com> Change-Id: I548ec7cf6d51badf78643c9a6c1c56ea9200142b
2019-10-28Fix names of quantized types in GetDataTypeName()Aron Virginas-Tar
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com> Change-Id: I485b7f1823a5eb1bb3832a7853d80a3fa00319fb
2019-10-28Refine SerializeDeserializeQuantizedLstm for the validation ofalanhsu5678
NELSTMLayerQuantized in ACL Change-Id: I663874da474722a191e55f6c7f6bc127a72fc485 Signed-off-by: alanhsu5678 <gg9662558@gapp.nthu.edu.tw> Signed-off-by: Matteo Martincigh <matteo.martincigh@arm.com>
2019-10-26Bug fix on serialization of tensor with qsymm16 typeTee Jung
Signed-off-by: Jung Tae-young <naey05@gmail.com> Change-Id: Ie3958c25fae752a8ec010ff6c77e4b625dec1f68
2019-10-25IVGCVSW-4022 Create a DeclareLabel utility functionMatteo Martincigh
* Created new TimelineUtilityMethods class * Created the DeclareLabel utility methods inside the new class * Added unit tests Change-Id: Ife0f7853a556d48206b76baeb3934344a990bee9 Signed-off-by: Matteo Martincigh <matteo.martincigh@arm.com>
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
2019-10-25IVGCVSW-4008 Add profiling mode to ExecuteNetworkAron Virginas-Tar
* Removed the requirement for specifying a data file for each input tensor * Added the possibility to generate dummy tensor data (filled with 0s) if no data files are specified by the user * Warn the user when they request to save the output to a file, but the input was generate, therefore rendering the output useless Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com> Change-Id: I8baed116dcd99fe380e419db322dc7e04ab1c653
2019-10-25IVGCVSW-4032 Update BuildGuideAndroidNDK.md with the TF commit ID that has ↵Nikhil Raj
tf_proto_file.txt Signed-off-by: Nikhil Raj <nikhil.raj@arm.com> Signed-off-by: Aron Virginas-Tar <aron.virginas-tar@arm.com> Change-Id: Id925c136536c3c9182236b253220294bfd4619aa
2019-10-25IVGCVSW-3962 Return 0 for Neon GetExportFlags()James Conroy
* Fixes issue where MemImport workload was being inserted into a graph when changing from a NEON to Ref workload. A MemCopy will now be performed instead. * Improves existing ImportAlignedPointerTest by adding check for expected output. Signed-off-by: James Conroy <james.conroy@arm.com> Change-Id: I606dbbe0166731c62fbe4cc1966c558ade66d6bb
2019-10-25IVGCVSW-4028 Add TimelinePacketWriterFactory to ProfilingServiceJim Flynn
Change-Id: I1baf6ff49fc591577efab8190352f2ae5a7dc5e5 Signed-off-by: Jim Flynn <jim.flynn@arm.com>
2019-10-25IVGCVSW-4027 Add the IProfilingGuidGenerator interfaceJim Flynn
Change-Id: Idfb80d73171aa2b57d4dcf01dc137817cf19d2bd Signed-off-by: Jim Flynn <jim.flynn@arm.com>
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
2019-10-24IVGCVSW-3950 Create SendTimelinePacket interface and classSadik Armagan
* Implemented ISendTimelinePacket interface and its implementation SendTimelinePacket * Implemented TimelinePacketWriterFactory * Implemented unit tests for SendTimelinePacket functions Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: I0a47586437f99510394d4d94589dccfb397d38e5
2019-10-24IVGCVSW-4011 Add Unit tests for StandInLayerColm Donelan
* Added network level unit tests with different number of inputs and outputs. Signed-off-by: Colm Donelan <Colm.Donelan@arm.com> Change-Id: I251296ca98a34f459181fed32343e7c579938eab
2019-10-23Refactor backward compatibility deserialization testsAron Virginas-Tar
* Change C-style arrays to vectors and simplify string construction * Leave whitespace after comma in initializer list Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com> Change-Id: I3adddae61e79cbcd878d13532d4199fc2581a328
2019-10-23IVGCVSW-4010 Add serialization support for StandInLayerAron Virginas-Tar
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com> Change-Id: I2017c15b485b82437c6ffdac4d3112bcc2cbe9e9
2019-10-23IVGCVSW-4013 Test that the quantizer fails gracefullySadik Armagan
* Added Quantizer test for StandIn Layer Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: I48bb9cadb48e20ee8e5b3dcf9e2f9fdb3b68351d
2019-10-23Fix build failures on RPi 4BJammy Zhou
Signed-off-by: Jammy Zhou <jammy.zhou@gmail.com> Change-Id: I12562c4a9671cd43884e7c0c023ca463a99c3aa2
2019-10-22IVGCVSW-4021 Fixing failure in the ExecuteNetworkDynamicBackends testNikhil Raj
Change-Id: I24ecd8ccf3e3c1586abc906f6ee9bdfd652e5c39 Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
2019-10-22IVGCVSW-3995 Add Quantizer support for ComparisonLayerAron Virginas-Tar
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com> Change-Id: Iab9b234d233591391a8e8626b7e8df3b7b0770a0
2019-10-22IVGCVSW-3980 Add ProfilingGuid and ProfilingGuidGenerator APINarumol Prangnawarat
* ProfilingGuid * ProfilingDynamicGuid * ProfilingStaticGuid * ProfilingGuidGenerator API * Unit tests Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com> Change-Id: If950415f059d07d34cf64e13a9b4663dd032ec34
2019-10-22IVGCVSW-4020 Add backward compatibility deserialization test for Equal and ↵Aron Virginas-Tar
Greater Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com> Change-Id: Ic185987e2aba23a857ae59b7115a1c0c53048978
generated by cgit v1.2.1 (git 2.23.0) at 2024-07-02 04:04:23 +0000