aboutsummaryrefslogtreecommitdiff
path: root/src/armnnUtils
AgeCommit message (Collapse)Author
2019-11-08IVGCVSW-4067 Change LayerGuid to use ProfilingGuidjaneil01
* Refactoring to enable ProfilingGuid * Add profiling includes to Android.mk Signed-off-by: Jan Eilers <jan.eilers@arm.com> Change-Id: Ieb25e15e3dc302eb42817d824ad8411ac76dcfe8
2019-11-07Escape angle brackets in dot file labelsRob Hughes
This was a bug that meant invalid dot files were produced due to MemCopy layers having a name including "->". Change-Id: If9f5b13d433f6a7328bf0ad8c7ec89cdce2462b0 Signed-off-by: Rob Hughes <robert.hughes@arm.com>
2019-11-06IVGCVSW-3837 Add support for per-axis quantization to reference ↵Aron Virginas-Tar
Convolution2d workload Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com> Change-Id: I0ac08ba4864d48e6f64c4ac645dad8ea850be112
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
2019-11-04IVGCVSW-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
2019-11-01GitHub #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
2019-10-28Fix 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
2019-10-25IVGCVSW-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
2019-09-16IVGCVSW-3694 Add ArgMinMax implementation for RefNarumol Prangnawarat
* Add ArgMinMax implementation * Add utility function to get number of elements between axis * Add utility function to get unsigned axis * Unit tests for ArgMinMax function Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com> Change-Id: I7bc3d610dda9526190187eb87394a8ed7a4b5cdd
2019-09-12IVGCVSW-3663 Add utility function to expand tensor dimensionNarumol Prangnawarat
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com> Change-Id: I54d2416be305db7d3fc15fb3123694ad6740b27d
2019-07-15MLCE-103 Add necessary enhancements to ModelAccuracyToolSiCong Li
* Evaluate model accuracy using category names instead of numerical labels. * Add blacklist support * Add range selection support Signed-off-by: SiCong Li <sicong.li@arm.com> Change-Id: I7b1d2d298cfcaa56a27a028147169404b73580bb
2019-07-02IVGCVSW-3307 Introduce RefTensorHandleMatthew Bentham
Use it for intermediate tensors on reference backend. Lays the groundwork for memory management in the reference backend. Change-Id: I7d3ee132cac31bde70ae6e1b815f4f0b03d550a6 Signed-off-by: Matthew Bentham <Matthew.Bentham@arm.com>
2019-06-25MLCE-103 Fix out-of-bound bug in ModelAccuracyCheckerSiCong Li
* Inside method AddImageResult, the number of generated output may exceed the size of m_TopK. Limit the check to the size of m_TopK. Signed-off-by: SiCong Li <sicong.li@arm.com> Change-Id: Ic7513ca27a283ef6d098d5aa0a94b4f17ff04f66
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>
2019-06-05IVGCVSW-3142 Refactor DataLayoutIndexed and TensorBufferArrayViewMatteo Martincigh
for convenience * Added GetIndex method to DataLayoutIndexed * Refactored TensorBufferArrayView::Get to use the new method Change-Id: Iae08b2761bddeda9e935b25e6bc4985f2d386cd3 Signed-off-by: Matteo Martincigh <matteo.martincigh@arm.com>
2019-05-08IVGCVSW-2833 Add Dynamic QuantizationJim Flynn
Change-Id: Iba91e3f3625639f01d66f81a9f3e419e0e285d66 Signed-off-by: Jim Flynn <jim.flynn@arm.com>
2019-05-08IVGCVSW-2900 Adding the Accuracy Checker Tool and testsÉanna Ó Catháin
Change-Id: I4ac325e45f2236b8e0757d21046f117024ce3979 Signed-off-by: Éanna Ó Catháin <eanna.ocathain@arm.com>
2019-05-07IVGCVSW-3038 Move MakeInputTensors to armnnUtilsJim Flynn
Change-Id: I4352a645badde788b9e33b3675a9cc9c0fc3dc33 Signed-off-by: Jim Flynn <jim.flynn@arm.com>
2019-05-02IVGCVSW-3039 Unify BindingPointInfo declarationsJim Flynn
Change-Id: I3deb2b9a37e8a8f8f2ed93c64ed0656ae911e24c Signed-off-by: Jim Flynn <jim.flynn@arm.com>
2019-01-25IVGCVSW-2563 Fix bug in TfLiteParser::ParseConcatenationNattapat Chaimanowong
Change-Id: I8fbf27b383a821e062f72809cc2e269fcd18851c
2019-01-24IVGCVSW-2503 Refactor RefElementwiseWorkload around Equal and Greaterkevmay01
* Remove Equal and Greater from RefElementwiseWorkload * Create RefComparisonWorkload and add Equal and Greater * Update ElementwiseFunction for different input/output types * Update TfParser to create Equal/Greater with Boolean output * Update relevant tests to check for Boolean comparison Change-Id: I299b7f2121769c960ac0c6139764a5f3c89c9c32
2019-01-23IVGCVSW-2515 Fix compilation when TfParser is disabledMatthew Bentham
Change-Id: Ia0019134f76764cd4fe6ed9dc1423b8aba411d33
2019-01-22IVGCVSW-2467 Remove GetDataType<T> functionNattapat Chaimanowong
Change-Id: I7359617a307b9abb4c30b3d5f2364dc6d0f828f0
2019-01-14IVGCVSW-1656 Add Mean support to Tf ParserFerran Balaguer
Change-Id: I3d31d6b72be1984acdb51fd9e7b5488a7aa5d832
2019-01-07IVGCVSW-2421 Remove the template-based version of armnnUtils::PermuteMatteo Martincigh
in favor of a type-indepent implementation that takes void-pointers * The new implementation requires the size of the type to be passed to the function * Updated all the usages accordingly * Removed the old implementation no longer used !android-nn-driver:469 Change-Id: I37f4e6d62a38fbb8ec8c39bb559a2c54c83365d4
2019-01-04MLCE-77 Depthwise Convolution with depth multiplier > 1 doesn't workMatteo Martincigh
* Unified ArmNN's weight format to [ M, I, H, W ] for the depthwise convolution * Added conversion utilities to permute/reshape the weights as appropriate when using CL and Neon backends * Updated the reference implementation of the convolution * Updated the relevant unit tests accordingly !android-nn-driver:459 Change-Id: I07d0818efa9d1ca1e5dad82983aac1fe78eadb18
2019-01-02IVGCVSW-2353 Ignore control inputs in TensorFlow parsernarpra01
* Allow control inputs from TensorFlow graph but ignore them in ArmNN graph. * Add utility function to test ArmNN graph structure. * Add ArmNN graph structure tests in TensorFlow paresr to ensure that control inputs are ignored in ArmNN graph as well as their inputs that are not used anywhere else. Change-Id: Ib0ea0d2df85e3fc79b748fa4c9d20e0649352bc1
2018-12-05IVGCVSW-2264 Move DataLayoutIndexed to armnnUtilsMatteo Martincigh
* Since DataLayoutIndexed is now required in the TF parser, this changes move it to the armnnUtils library so that it'll be accessible by the armnnTfParser * Modified CMake files and Android.mk files accordingly Change-Id: Ie2620359ef288aeff64cb9e9bec068a466eee0e9
2018-11-20IVGCVSW-2144: Adding TensorUtils classNina Drozd
* helper methods for creating TensorShape and TensorInfo objects Change-Id: I371fc7aea08ca6bbb9c205a143ce36e8353a1c48
2018-11-19IVGCVSW-2167: Run parser unit tests on the reference backend onlyAron Virginas-Tar
Change-Id: Ib11c3d36c7109198da7266955414580e8fb916b5
2018-11-02IVGCVSW-1946: Remove armnn/src from the include pathsAron Virginas-Tar
Change-Id: I663a0a0fccb43ee960ec070121a59df9db0bb04e
2018-10-25IVGCVSW-2058: Remove ARMCOMPUTE(CL/NEON)_ENABLED and ARMCOMPUTENEON_ENABLED ↵Aron Virginas-Tar
from src/armnnUtils/ParserPrototxtFixture.hpp Change-Id: Ief836fb80c4c966f1b76c9429d4a7fb644ceb73d
2018-10-25IVGCVSW-2067 : dynamically create workload factories based on the backends ↵David Beck
in the network Change-Id: Ide594db8c79ff67642721d8bad47624b88621fbd
2018-10-22IVGCVSW-2019 : replace Compute enum in the backend preferences listDavid Beck
Change-Id: Ie7549fd27378acfa97e68d098e338b8c9d4ea5d2
2018-10-22IVGCVSW-1914 Investigate CONV_2D failure on FP16 on AndroidSadik Armagan
* Round to nearest instead of round to intermediate (default) * Compute Library also round to nearest Change-Id: I0c71e2ffd28e4e662188fd47d26ec8b538d4ba21
2018-10-10IVGCVSW-1929: Fix for this defect (QASYM8 no scale)jimfly01
* Now hand in an optional vector of strings to Optimize function in which errors/warning messages are placed. * Optimize function changed to check outputs of each layer. If they are Quantized 8 bit but the scale has not been set an error message is added for each such output. * Unit test modelled on defect report added to exercise the fix. !android-nn-driver:152483 Change-Id: If9901f5324a516f1ab62858266b38f98dae16201
2018-10-10IVGCVSW-1913: Fix for ValidationTest.concat_float_3_relaxedarovir01
* Added RefPermuteFloat16Workload to serve as a fallback when CL does not support the required permute configuration for FP16 * Move Half.hpp to armnnUtils as the utils library should not be including private header files from the armnn library Change-Id: Ibf0f698451e8406f7ed7cce470dab60b6d16361d
2018-10-10IVGCVSW-1787 Add Support for Concatenation on TfLite parserSadik Armagan
* Concatenation Parser function added to the TfLite Parser Change-Id: I42a42cd765ea09a30841c66b1942b9e09a876b10
2018-09-17IVGCVSW-1807 : change license text in file headersDavid Beck
All changes are the same: // // Copyright © 2017 ARM Ltd. All rights reserved. -// See LICENSE file in the project root for full license information. +// SPDX-License-Identifier: MIT // Change-Id: I37eae011411133663ca9d2b059714d92f8bf8e24
2018-08-31Release 18.08telsoa01
2018-05-23Release 18.05surmeh01
2018-03-29Release 18.03surmeh01
2018-03-09Release 18.02telsoa01
Change-Id: Id3c11dc5ee94ef664374a988fcc6901e9a232fa6
generated by cgit v1.2.1 (git 2.23.0) at 2024-06-29 18:28:34 +0000