aboutsummaryrefslogtreecommitdiff
AgeCommit message (Collapse)Author
2018-10-10IVGCVSW-1821 - taking out scale factor again as it's polluting the ↵Nina Drozd
WallClockTimer interface Change-Id: Ia90b709ddfff321dbc218add4ab19737f68a44bf
2018-10-10IVGCVSW-1821 - update NEON workload utils to use timers in correct order, ↵Nina Drozd
updated units used in NeonTimer Change-Id: I593af42bd2930dd9d147354b706087e3ac260fe9
2018-10-10IVGCVSW-1927 Add Neon 8-bit FullyConnected supportkevmay01
Change-Id: Idf4cc7a9a7d3261b9eceb653b999257506cdae76
2018-10-10IVGCVSW-1924: Fixing clframework version update compile errjimfly01
* Changed run_workloads function invocation to run_workloads_tagged * Also ClMultiplication now supports QASYMM8 !builder:149820 !android-nn-driver:149821 Change-Id: Id76446aeccf5c0eaae2fd62da34c54a374cc4daa
2018-10-10IVGCVSW-1910 Add data layout parameter for DepthwiseConvolutionNikhil Raj
Change-Id: Ia14c9d8c0a38b669a7589e63d74424e398790e54
2018-10-10IVGCVSW-1921: move common Acl code to a separate folderDavid Beck
Change-Id: I400be8e7c0cc5a31eb9d2a7396da145d50d51b6e
2018-10-10IVGCVSW-1881 Add PadLayer to ArmNNMohamed Nour Abouelseoud
Change-Id: Ib70883a20fa7b82bfb090aa98cc51a6d645b5722
2018-10-10IVGCVSW-1888 Plumb data layout parameter for Convolution2DFrancis Murtagh
* Added the DataLayout parameter to the Convolution2dDescriptor * Added the DataLayout parameter the Convolution2dQueueDescriptor * Set the DataLayout on the Descriptor in CreateWorkload() * Added overloaded factory methods for CreateTensorHandle() * Updated BuildArmComputeTensorInfo() to take DataLayout parameter. * Updated handles to take DataLayout parameter * Updated (Cl/Neon)Convolution2dWorkloadValidate * Updated (Cl/Neon)Convolution2dFloatWorkload * Updated (Cl/Neon)Convolution2dUint8Workload Change-Id: I8410668b3d727ca587bee66755cc4c4c78422f1f
2018-10-10IVGCVSW-1897 : Android support for pluggable backendsDavid Beck
Change-Id: I9143485f542d58307a604248200a4ecf839ff39a
2018-10-10IVGCVSW-949 Further simplify InitializeArmComputeClTensorDataMatthew Bentham
Remove the overload that takes a raw pointer and always pass a ConstTensor reference Change-Id: I8fbff8dd5c260e7cdf4a3c51eb54cc5f3f6e874c
2018-10-10IVGCVSW-949 Simplify use of IntialiseArmComputeClTensorDataMatthew Bentham
Change-Id: I556881e34f26e8152feaaba06d99828394872f58
2018-10-10IVGCVSW-1897 : build infrastructure for the src/backends folderDavid Beck
Change-Id: I7ebafb675ccc77ad54d1deb01412a8379a5356bb
2018-10-10IVGCVSW-949 Remove unnecessary includesMatthew Bentham
Change-Id: I923fd5d03e53187c18ac05e2cde90d43604f3821
2018-10-10IVGCVSW-949 Refactor - clean up includes of ClWorkloadUtils.hppMatthew Bentham
Move ClWorkloadUtils.hpp into ClWorkloads and reduce the number of places that include it Change-Id: Iac661be34c185d6208ca75509155b049c24293ca
2018-10-10IVGCVSW-949 Add 8-bit fully connected supportMatthew Bentham
Change-Id: I0953bb8dbc4b76001f207e37c8c2742a6ebd888b
2018-10-10IVGCVSW-1822: Fix CaffeYolo-Armnn error reportingJames Conroy
* Changed message to 'Prediction for test case <N> is incorrect: Expected (<X>) but predicted (<Y>)' Change-Id: Ie54b70683bf5bb26de2f2a6bcf4a162c99ba5474
2018-10-10IVGCVSW-1650 Add Support for Reshape layer on TF Lite parserSadik
* Added Reshape operator support for the TfLite Parser. Change-Id: I64a5650dac089905a402be4a9cb6032aa0d81f00
2018-10-10IVGCVSW-1843: Edit comment to ref correct functionJames Conroy
* Changed comment to reference the function CreateArithmeticWorkloadTest, as the original CreateSubtractionWorkloadTest no longer exists. Change-Id: Ief60e6f3684bd5539d8fb21dd09fc7ef8e8a92f5
2018-10-10IVGCVSW-1880: Add no-op factory implementations of CreatePadjimfly01
* Added PadDescriptor and PadQueueDescriptor * Factory method CreatePad on all backends returning null workloads Change-Id: Ifeb50f9249ea31edfc3586d49b008ea1b5c59ae2
2018-10-10IVGCVSW-1883 Add support for different memory layoutsDerek Lamberti
Change-Id: I6e9973bf25acad980fb4e96af8080ac829db0d28
2018-10-10IVGCVSW-1651 Add Support for Relu on TF Lite parserSadik Armagan
* Added Relu and Relu6 Support for the TfLite Parser. Change-Id: I3cc5e4922910e556f25b633eae6d2d361cea61b5
2018-10-01Fix for Github issue #63Matthew Bentham
Update FindBoost.cmake to version from Kitware/CMake Github cb800eb Change-Id: I3988350a09d5431868d8776fd20fd4493a8dfb1d
2018-10-01IVGCVSW-1802 : fix typoDavid Beck
Change-Id: I1d5c558f6575e5d21c45412c8848e53392cae618
2018-10-01Updated the inception_v3 model taken from official Tfsurmeh01
!devenv:148227 Change-Id: I550c885c125f2fe12951e38d4157276562cb49ec
2018-10-01IVGCVSW-1802 : Neon Sub WorkloadDavid Beck
Change-Id: I1e914b046cd8fd25669390d477f101098fe0d476
2018-10-01IVGCVSW-1813 - Add MeanLayernarpra01
* add MeanLayer functionalities * modify MeanQueueDescriptor to use parameter * add IsMeanSupported placeholder for all backends Change-Id: Ic69a34a61df667849977aad9b38f9a01eef565b5
2018-10-01IVGCVSW-1832: add missing DIV quantized, broadcasting testsDavid Beck
Change-Id: I042b71e77d175163837bf39d5703ada08d25e532
2018-10-01IVGCVSW-1843 : remove duplicate code for Ref Arithmetic workloadsDavid Beck
Change-Id: If94d7b7b06a8c4e2c155b2ab470604a8d20d1027
2018-10-01IVGCVSW-1843 : refactor ClAdditionWorkload and ClSubtractionWorkloadDavid Beck
Change-Id: I0ca9f16217f8e32bb57a49b841611f10dabf021a
2018-10-01IVGCVSW-1804 : add subtraction layer to the public interfaceDavid Beck
Change-Id: I2c1b622b5199000c01af387bb994267c2b91f89c
2018-10-01Added and modified the vanilla tensorflow values for inception and mobilenetsurmeh01
Change-Id: Ib0d59015aa104909f3922f9749e3787e15c7c86e
2018-10-01IVGCVSW-1843 : replacing trivial arithmetic helpersDavid Beck
Change-Id: Iddf637694f1a3a7ef00f006a41b8044a35c7e73c
2018-09-25IVGCVSW-1733 - set enableGpuProfiling in CreationOptions for Runtime if -e ↵Nina Drozd
flag is set, false by default, use this globally same as concurrent flag, removed -e option from RunCsvTest options, this is passed in from main Change-Id: I246c2c40b1a113b896be0d41aba528e79ecdba0d
2018-09-25IVGCVSW-1831 - Add dimension check to MeanQueueDescriptor::Validate to check ↵narpra01
if the output dimension is correct from a given input and options. Change-Id: Ibc15d9ea3151a7ba1935feafeb1843ee035e7f2e
2018-09-25IVGCVSW-1801 : Cl implementation for SUBDavid Beck
Change-Id: Ia2e1dda8653197454a50679d49020397f5327979
2018-09-25IVGCVSW-1810 - Add no-op factory implementations of the CreateMean for all ↵narpra01
backend factories Change-Id: Ic1054a32f59659d10f67a6b02527887ccf3c850f
2018-09-25IVGCVSW-1520 Re-enable quantised addMatthew Bentham
Change-Id: I1944242b67e8c4a0e54f1a59377a1d78633edb3f
2018-09-25IVGCVSW-1808 : Updated the network used from Official ↵surmeh01
Tf(http://download.tensorflow.org/models/mobilenet_v1_2018_08_02/mobilenet_v1_1.0_224.tgz) Change-Id: I3a07d7a161c8ac81c6a94cc0b3557ee7fa5e48e5
2018-09-25IVGCVSW-1803 : add Ref Subtraction layerDavid Beck
Change-Id: I4c019d626f9369245eca6d549bbe7a28e141f198
2018-09-25IVGCVSW-1804 : Add Subtraction layer types and placeholdersDavid Beck
Change-Id: Ib9a477e5ce590df74ba05fece77258b9204f6523
2018-09-25MLCE-52 Where has PROFILING gone?Sadik Armagan
* Call the Print() function on the Profiler when profiling is enabled. Change-Id: I4c06ce9bfa961ac8d81d02a516502337d1fbc968
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
2018-09-17IVGCVSW-1807 : add license section to the Readme fileDavid Beck
Change-Id: I3f6823d67436e75b1f451afc6f982777b6b51705
2018-09-17IVGCVSW-1783 refactor add/mul/div layersLes Bell
Change-Id: Ic043030455b3cf8ad7f92fd0a75175c1827a95f4
2018-09-17IVGCVSW-1784: Rename float32 workloads for ACLarovir01
Change-Id: I98bdfe9cb12c663d1d5cfa456e2cc967d70ab22b
2018-09-17IVGCVSW-1521: Updating TensorFlow README.md to contain realdiv operatorsaoste01
Change-Id: Iad169a279c9fc67bd8a44511a646dded8d4ba1aa
2018-09-17IVGCVSW-1779: Updating TF Parser to include the RealDiv operatorsaoste01
Change-Id: I4b193d9119f5aaf41081335df043352953364c87
2018-09-17IVGCVSW-1786 - Division by zeroFrancis Murtagh
* Added logic for different cases of division by zero for ref * Added DivisionByZeroTest * Updated SelectiveComparer to compare NAN and INFINITY Change-Id: Iec6f89264b17a0b03fad5d7ec4b2dafc31fea5df
2018-09-17IVGCVSW-1200 Division layerFrancis Murtagh
*IVGCVSW-1772 Create QueueDescriptors *IVGCVSW-1773 Add a CL implementation of the DivisionWorkload *IVGCVSW-1774 Add Neon implementation of the DivisionWorkload *IVGCVSW-1775 Add a Ref implementation of the DivisionWorkload *IVGCVSW-1776 Add a Division Layer * Added simple division unit tests with broadcasting Change-Id: I05751fb7f868789f6c06f91e8d25e52b4f12ab5e
2018-09-17IVGCVSW-1324: Make biases truly optional for Conv2d and DepthwiseConvolutionarovir01
!android-nn-driver:145961 Change-Id: I039ab0adc61725859514246365b5e5b5fa603eaa
generated by cgit v1.2.1 (git 2.23.0) at 2024-07-04 11:28:08 +0000