aboutsummaryrefslogtreecommitdiff
AgeCommit message (Collapse)Author
2019-06-21IVGCVSW-3322 Add Quantizer support for TransposeConvolution2DLayerexperimental/transpose_conv2dAron Virginas-Tar
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com> Change-Id: I26997d7770585055b2b3256baad2800a4c5ed7e8
2019-06-21IVGCVSW-3330 Parse dilation parameters for DepthwiseConvolution2d in ↵Aron Virginas-Tar
Deserializer * Added code for reading parameters dilationX and dilationY to Deserializer::ParseDepthwiseConvolution() * Updated serialization unit tests to check for dilation params for both Convolution2d and DepthwiseConvolution2d Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com> Change-Id: Id03629866009e799cf7daf8b7bdafc73d158d9bb
2019-06-21IVGCVSW-3321 Add serialization support for TransposeConvolution2dLayerAron Virginas-Tar
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com> Change-Id: If0c8f3662d5e03696f97040abed784c0fbcdbc6f
2019-06-21IVGCVSW-3291 Add L2Normalization epsilon value to serializationFerran Balaguer
Signed-off-by: Ferran Balaguer <ferran.balaguer@arm.com> Change-Id: Icfff3fb596a03c126a42b1d0c254a68e498df734
2019-06-21IVGCVSW-3319 Add frontend support for TransposeConvolution2d LayerAron Virginas-Tar
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com> Change-Id: Ic06f63f1eff255e697facf319e2ac4c83d782e7c
2019-06-20IVGCVSW-3193 Update bounding box value of MobileNet SSD after refactorNarumol Prangnawarat
Convolution2d and DepthwiseConvolution2d to use Encoders and Decoders Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com> Change-Id: Ic87b8ce6f68343983f3c825902425516cbb23b06
2019-06-20IVGCVSW-3212 Refactor RefBatchNormalizationWorkloadMatteo Martincigh
* Refactor the reference batch normalization workload to avoid unnecessary function calls and to improve readibility Change-Id: I49d78dcac7bad36f57bd1eb196c12dbad01cc893 Signed-off-by: Matteo Martincigh <matteo.martincigh@arm.com>
2019-06-20IVGCVSW-3248 Refactor reference BatchToSpace workloadFrancis Murtagh
* Add Decoders and Encoders to workload to make it data type agnostic * Merge float32 and Uint8 into single workload Change-Id: I8adfa1898a63f13889eaaf55a31c26fd1e2d7ee8 Signed-off-by: Francis Murtagh <francis.murtagh@arm.com>
2019-06-19IVGCVSW-3269 Add Serialization support for the new Prelu Activation layerEllen Norris-Thompson
* Adds serialization/deserialization support * Adds related unit test Signed-off-by: Ellen Norris-Thompson <ellen.norris-thompson@arm.com> Change-Id: I600322b03e51f443cbcd9262bb27e36e5fd95ae5
2019-06-19IVGCVSW-3270 Add Quantizer support for the new Prelu Activation layerMatteo Martincigh
* Implemented VisitPreluLayer * Added unit test for Prelu layer quantization Change-Id: I0442053f69608a400d295654b103cfd2429a0341 Signed-off-by: Matteo Martincigh <matteo.martincigh@arm.com>
2019-06-19IVGCVSW-3271 Add unit test for dilated DepthwiseConvolution2dTeresa Charlin
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: I0e7132f61001f7b2a9fad3d7b21acf2558c01df4
2019-06-19IVGCVSW-3231 Add reference workload support for SpaceToDepthKeith Davis
* Added reference workload for SpaceToDepth * Added unit tests for float32 & uint8 * Minor sort refactoring to RefWorkloads.hpp to alphabetical order Change-Id: I2e01f8101650e2aae102a8a32bc0064f067141ab Signed-off-by: Keith Davis <keith.davis@arm.com>
2019-06-19IVGCVSW-3268 Add Reference workload support for the new Prelu Activation layerMatteo Martincigh
* Added reference workload for the PReLU Activation layer * Added factory methods * Added validation support * Added Int16 support * Added unit tests Change-Id: Ic950d908c5e0a335dccd2960a3ffab0f8b599876 Signed-off-by: Matteo Martincigh <matteo.martincigh@arm.com>
2019-06-19IVGCVSW-3299 Add Uint8 Support to Model Accuracy CheckerFrancis Murtagh
* Seperate ExecuteNetwork main function into standalone application * Include NetworkExecutionUtils header and remove duplicate functions * Add uint8 and int32 support to ModelAccuracyChecker Change-Id: I5fb4bc147232f8388f37eea7db5130b04fd215d1 Signed-off-by: Francis Murtagh <francis.murtagh@arm.com>
2019-06-19IVGCVSW-3288 Add L2Normalization epsilon Neon workload supportFerran Balaguer
Signed-off-by: Ferran Balaguer <ferran.balaguer@arm.com> Change-Id: I938d97e6a2bfab8ff5f4548efeeaa43b7f5ccda2
2019-06-18IVGCVSW-3234 Ensure that Quantizer allows different quantization scalesNarumol Prangnawarat
on inputs and output of Concat layer Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com> Change-Id: Idd79e44dbf49345aced3ddeeb8a53c9776f9f5d5
2019-06-18IVGCVSW-3234 Add unit test for Concat with different quantization paramsNarumol Prangnawarat
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com> Change-Id: Ia655b1b6c5f57d2b7c0d9dd17be342cd01f36c09
2019-06-18IVGCVSW-3264 Add Unit Test for Dilated Convolution2d to armnnTeresa Charlin
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: I60da1414ab41ea196cdebc27f0f014a502274fa8
2019-06-17IVGCVSW-3267 Add Arm NN front end support for the new Prelu Activation layerMatteo Martincigh
* Added new PreluLayer class * Made necessary changes to ILayerSupport, ILayerVisitor, etc. * Added unit tests Change-Id: Ifcfb78e823bb5a245ed1dad15290d2f60115c882 Signed-off-by: Matteo Martincigh <matteo.martincigh@arm.com>
2019-06-17IVGCVSW-3286 Add epsilon Reference workload supportFerran Balaguer
Change-Id: I5cabbf9d1ef3858be68d6820d14845e512128c5b Signed-off-by: Ferran Balaguer <ferran.balaguer@arm.com>
2019-06-17IVGCVSW-2779 Fix Android Q buildMatteo Martincigh
* Removed names of unused variables, as they cause the Android Q build to fail Change-Id: I4b091d6af05a67ce0aa4fcde3c5048a4a75798fc Signed-off-by: Matteo Martincigh <matteo.martincigh@arm.com>
2019-06-17IVGCVSW-3219: Add QSymm16 support to the ResizeBilinear Reference workloadEllen Norris-Thompson
* Adds CreateWorkload and LayerTests for QSymm16 * Updated ResizeBilinearQueueDescriptor::Validate function * Reimplemented RefLayerSupport::IsResizeBilinearSupported Signed-off-by: Ellen Norris-Thompson <ellen.norris-thompson@arm.com> Change-Id: Id9d14d3b41d26ac3d51227ab248ce8cca9dc9969
2019-06-17IVGCVSW-3273 ArmnnQuantizer: UnimplementedException thrown for: ↵Nikhil Raj
VisitNormalizationLayer Change-Id: Ic2929635c1c15c09f493053b2e64ddfbab2fe217 Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
2019-06-17IVGCVSW-3222 Extend Mean ref workload to support QSymm16James Conroy
* Added support for QSymm16 in Mean ref workload * Added unit tests for QSymm16 Mean Signed-off-by: James Conroy <james.conroy@arm.com> Change-Id: I600b15069ff4a4531666c6bc7fb73187dcebf0ee
2019-06-17IVGCVSW-3221 Refactor Mean ref workload and testsJames Conroy
* Renamed RefMeanFloat32Workload and RefMeanUint8Workload to RefMeanWorkload, updated references to reflect this change. * Refactored RefFloorWorkload to use Decoders/Encoders, to support the use of multiple data types. * Deleted reference Unit8 Mean tests as they were duplicates of the Float32 tests. Refactored these tests to support multiple data types and updated references. * Adjusted the values used in the tests' input tensors so that they are more like floating point numbers e.g. change 1.0f to 1.5f. * Replace size_t with unsigned int in Mean ref workload, for better compatibility with the Encoder/Decoder, removed some unnecessary casts after this. * Added ValidateTensorDataTypesMatch() function to WorkloadData.cpp, added CreateIncorrectDimensionsErrorMsg function to RefLayerSupport.cpp. * Added passing and failing tests for ref IsMeanSupported. Signed-off-by: James Conroy <james.conroy@arm.com> Change-Id: Id3d44463d1385255c727a497d4026d21a49e7eb2
2019-06-17IVGCVSW-3285 Remove out of date check from ↵Aron Virginas-Tar
RefLayerSupport::IsDilatedDepthwiseConvolutionSupported Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com> Change-Id: Ie8d0247a65774e4e9717501439014dd0e973f9f3
2019-06-17IVGCVSW-3218 Refactor the Reference Workloads for the ResizeBilinear layerEllen Norris-Thompson
* Refactored ResizeBilinear Reference Workloads to combine Float32 and Uint8 files Signed-off-by: Ellen Norris-Thompson <ellen.norris-thompson@arm.com> Change-Id: I725a830f4c4755a7d3a37ca68e31e44e7eb267cb
2019-06-14IVGCVSW-3278 Cl and Neon TensorHandles inherit from common base interfaceDerek Lamberti
Change-Id: Ia68da09d8f0fb0a04af9cb61062d7edaa5f1b887 Signed-off-by: Derek Lamberti <derek.lamberti@arm.com>
2019-06-14MLCE-121 Github: Build error on GCC 9Mike Kelly
* Fixed an error encountered when building on GCC 9 error: moving a local object in a return statement prevents copy elision * Fixed failures in unit tests due to std::initializer_list handling in GCC 9 Change-Id: I4bfdd2113dfedcecd29479ee556e4ae22278755d Signed-off-by: Mike Kelly <mike.kelly@arm.com>
2019-06-14IVGCVSW-3225 Add QSymm16 support for Rsqrt workloadnikraj01
Change-Id: I83b8494af24ff271dc4cd609944a1c5c55c405e0 Signed-off-by: nikraj01 <nikhil.raj@arm.com>
2019-06-14IVGCVSW-3275 Add Uint8 support for L2NormalizationFerran Balaguer
Signed-off-by: Ferran Balaguer <ferran.balaguer@arm.com> Change-Id: I7f2bcf0596a4f654166aad9657bc7084f55e7451
2019-06-14IVGCVSW-3229 Refactor L2Normalization workload to support multiple data typesFerran Balaguer
Signed-off-by: Ferran Balaguer <ferran.balaguer@arm.com> Change-Id: I848056aad4b172d432664633eea000843d85a85d
2019-06-14IVGCVSW-3224 Add Uint8 support for Rsqrtnikraj01
Change-Id: I45598fc9b6d408b19d8d050e64c12b1d48535fa3 Signed-off-by: nikraj01 <nikhil.raj@arm.com>
2019-06-12IVGCVSW-3217 Refactor the Layer tests for ResizeBilinear to make them genericEllen Norris-Thompson
* Refactored the ResizeBilinear tests so can be used for both Float32 and Uint8. * Moved to .hpp file and renamed tests accordingly. Signed-off-by: Ellen Norris-Thompson <ellen.norris-thompson@arm.com> Change-Id: Icf79b0616db0c307cfcf94747fe0a6d4343588bd
2019-06-12IVGCVSW-3261 Add Quantizer support for SpaceToDepth layerAron Virginas-Tar
Change-Id: Ic08e38fe10ca1abd79c6e4b1a83dc9a929686b56 Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com>
2019-06-12IVGCVSW-3260 Add serialization support for SpaceToDepthAron Virginas-Tar
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com> Change-Id: Ie0d9561437ff5da8fa4db81fee1e70bd18c47034
2019-06-12IVGCVSW-3010: Unit Test for Activation Workload for Float32 and Uint8konsof01
Unit tests for following Activations have been added *Relu *SoftRelu *LeakyRelu *Abs *Sqrt *Square *Tanh Signed-off-by: Konstantin Sofeikov <konstantin.sofeikov@arm.com> Change-Id: I2812a24842400c8b2c2d87933fbe1eca8c66e911
2019-06-12IVGCVSW-3258 Add front end support for new SpaceToDepth layerAron Virginas-Tar
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com> Change-Id: Id677e29a734f2b36483d939ad370079bdc11551e
2019-06-11IVGCVSW-3253 Refactor MonotonicClockRaw in WallClockTimerAron Virginas-Tar
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com> Change-Id: I759aaeff4e543c36047698716bd99bac4e4092d3
2019-06-11Github #208 Search for flatc on standard pathsMatthew Bentham
Change-Id: Ib5a77dc4b654c67d79f1f53e783b319c885b5215 Signed-off-by: Matthew Bentham <matthew.bentham@arm.com>
2019-06-11libarmnnQuantizer has references to libarmnn, so use libarmnn for linkGuillaume GARDET
Signed-off-by: Guillaume GARDET <guillaume.gardet@free.fr> Change-Id: Id80d04cca20b470914401246f5cb04dbcb94f00c
2019-06-07IVGCVSW-3228 Fix bias quantization to be INT32 not QAsymm8Francis Murtagh
* Add function to calculate bias tensor quantization scale from input and weights scales. * Change visitor method of Conv2d, DepthwiseConv and FullyConnected to use the new function. * Fix Unit tests to expect correctly calculated quantization parameters. Change-Id: Ic36f47ceea81243c813d74ccf791e984c819cc71 Signed-off-by: Francis Murtagh <francis.murtagh@arm.com>
2019-06-07Github #140 Use snprintf instead of strncpyMatthew Bentham
Change-Id: I4da3b390d60da76754bbab016a656fbaf37d7df5 Signed-off-by: Matthew Bentham <matthew.bentham@arm.com>
2019-06-07IVGCVSW-3237 Add type check to RefLayerSupport::IsDetectionPostProcessSupportedAron Virginas-Tar
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com> Change-Id: I68ff6f3682a93689a890fff46bb1a6ccb1acda20
2019-06-07IVGCVSW-3223 Fix ref convolution performance regressionMatteo Martincigh
* Do not use DataLayoutIndexed::GetIndex for weights and inputs, as it causes a large regression in performance * It turned out that the calculation of the indexes for the weights and inputs was the way it was because of an optimization done many months ago * Reverted the relevant hunks and added some comments so we won't make the same mistake again in the future * Made the GetIndex function inline to speed up other usages Change-Id: I343b2ef0446993086f58b9dea1f0de0ba2d92216 Signed-off-by: Matteo Martincigh <matteo.martincigh@arm.com>
2019-06-06IVGCVSW-3211 Refactor reference Rsqrt workloadnikraj01
Change-Id: Ia413c6b5352dbb3390e7d84e837a542c24ae8813 Signed-off-by: nikraj01 <nikhil.raj@arm.com>
2019-06-06IVGCVSW-3143 Extend the Pooling 2d workload to support QSymm16Teresa Charlin
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: I4026a77377002f4f9c15a923e8fcb7075d700f6e
2019-06-06IVGCVSW-3227 Extend the reference normalization workload to support QSymm16Matteo Martincigh
* Added support for QSymm16 * Added unit tests Change-Id: I7ba57793830bed7958ac9a94e9ac39d6dbe708b5 Signed-off-by: Matteo Martincigh <matteo.martincigh@arm.com>
2019-06-06IVGCVSW-3226 Refactor the reference normalization workloadMatteo Martincigh
* Refactored RefNormalizationFloat32Workload into RefNormalizationWorkload * Added ref support of Uint8 norm workloads * Added workload unit tests for Uint8 Change-Id: I063ce919c267e02a32e739848e49d75fd98a5eb6 Signed-off-by: Matteo Martincigh <matteo.martincigh@arm.com>
2019-06-06IVGCVSW-3142 Refactor reference Pooling2d workloadTeresa Charlin
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: I94c973ab747309c0214268c9c39f6d8f3fc7b255
generated by cgit v1.2.1 (git 2.23.0) at 2024-05-02 04:17:47 +0000