aboutsummaryrefslogtreecommitdiff
AgeCommit message (Collapse)Author
2019-01-23IVGCVSW-2394 Update Android Hal Policy for ResizeBilinear IsLayerSupportedSadik Armagan
* IsResizeBilinearSupported function requires outputInfo as well. Change-Id: Ib74241ef2db147bb64fa77287ad0d616a2e4159d
2019-01-23IVGCVSW-2545 Fix android-nn-driver build wrt master Compute LibraryMatthew Bentham
Change-Id: I09b976c6323194ae39a2ce7131be5a407487b863
2019-01-14MLCE-86 Fixing up the problem with the invalid padding clauseÉanna Ó Catháin
Change-Id: I34d8a7f359acc19258a9d6e7f9256f8b33777e20
2019-01-11IVGCVSW-2454 Merge together the pluggable backends work (was in aMatteo Martincigh
separate branch) and master * Minor fixes to make the NN Driver build with the merged changes * Passed missing ReshapeDescriptor to the layer support function !armnn:491 Change-Id: I61fb6ed8df6895bd5a12c6f2b1c322929eebe176
2019-01-07IVGCVSW-2421 Remove the template-based version of armnnUtils::PermuteMatteo Martincigh
in favor of a type-indepent implementation that takes void-pointers * Updated the code to make use of the new version of Permute !armnn:468 Change-Id: I10a5f353ee87822f161a968bb04d18af037fd103
2019-01-02MLCE-77 Depthwise Convolution with depth multiplier > 1 doesn't workMatteo Martincigh
* Changed the weight swizzling to [ M, I, H, W ] as now required by ArmNN !armnn:460 Change-Id: I7c25e7ab3e1efc47d7db3f2b57e17382ea8b36cf
2018-12-31MLCE-82 Add Compute Library NEON mean to Android.bpMatthew Bentham
Change-Id: I0ca7da989d72ed9847b8045ce0476d16a04fa941
2018-12-21IVGCVSW-2166 Update NnapiSupport.txt for the new AndroidNN 1.1 operations.Sadik Armagan
Change-Id: Ic402c0ee003b55cc0f14f4bb4a3a17a87558fb04
2018-12-20IVGCVSW-1202 SPACE_TO_BATCH_ND integrate Arm Compute CLSadik Armagan
* Updated HalPolicy::ConvertSpaceToBatchNd function set the values instead of add. Change-Id: I4b334819c79169fa5949998ffc828ee77c714bc6
2018-12-19Update Android.bp file for latest CL pinNattapat Chaimanowong
Change-Id: Ic1eb5397951cf05651f769da1b00b7a910ed2427
2018-12-17Updated the Android.bp file to build the latest CL masterMatteo Martincigh
Change-Id: Ib7e21bc5e818a13f208c037fdf2453343d2141ef
2018-11-18IVGCVSW-2127- Update HAL Policy for mergerbranches/android-nn-driver_18_11narpra01
* Remove permutation when concat axis is inner most * Add additional parameter to IsMergerSupported as changed in armnn !armnn:151 Change-Id: Ie214c9573f242d8f04d58fc61621ad3831991d9a
2018-11-15IVGCVSW-2092 Port LSTMCell::Eval to ArmNNMatteo Martincigh
* Refactored the LSTM unit tests to avoid unnecessary copies * Added new AddTensorOperand convenience function * Fixed some required arguments in some tests * Added new files to Android.bp !armnn:124 Change-Id: I77ed22f2692d8aa46884b9ee31e48403f7299545
2018-11-15IVGCVSW-2080 Fix documentation in NnapiSupport.txt (Remove unsupported)Ferran Balaguer
Change-Id: I15abc32914ddd9c36d9e31ecf40f938304a07fd6
2018-11-15IVGCVSW-2088 Add a converter method for STRIDED_SLICE to the V1.1 section of ↵Sadik Armagan
the ModelToINetworkConverter * Added Converter function for StridedSlice operator to 1.1:HalPolicy !armnn:121 Change-Id: Ida911c2ebeae9b7af708a5e4f492e97ac0d336cb
2018-11-15IVGCVSW-2080 Fix documentation in NnapiSupport.txtFerran Balaguer
Change-Id: Id369a2a70863fabaa60ee11849b5449dd95e25a7
2018-11-14IVGCVSW-2099 Add batch_to_space_nd Conversion Method for HAL V1.1Éanna Ó Catháin
!armnn:117 Depends-On: Ib1c16d871f0898a1caeb6629c1fee6380a773e14 Change-Id: Ie912f018542c69aa9f051e83d3f317145429cca8
2018-11-12IVGCVSW-2097: Document support for BatchToSpaceNdÉanna Ó Catháin
Change-Id: Ie567d55da21ef931ca3ee93fcec61d6196b6b4eb
2018-11-12IVGCVSW-1981: Edit HAL Policy for NHWC Pooling2DMatteo Martincigh
* Removes permutes of tensors for Pooling2D, as NHWC is now supported by Arm NN. Change-Id: I48417c91f387b6f73bc071e473828f2ee5949332
2018-11-12Added new ACL file to Android.bp needed to build the driver againstMatteo Martincigh
the latest CL master (0cf77981fadb883b97efec112e115450873e64c3) Change-Id: Icbc3a870e058534ff759489b63fbe7bd4502b962
2018-11-09IVGCVSW-2096 Document support for SPACE_TO_BATCH_NDNattapat Chaimanowong
Change-Id: I9cb4159a4f8e2bccd350bc1a705534203a8edf62
2018-11-09IVGCVSW-2094 Add converter method for SPACE_TO_BATCH_ND to V1.1 section of ↵Nattapat Chaimanowong
the HalPolicy Change-Id: Ibe9ccf814e437c238e474e1f6eac5b1a8db1c8df
2018-11-08IVGCVSW-1972 - Update HAL Policy Convolution2d to use NHWC data layoutexperimental/nhwc-previewnarpra01
Change-Id: I0e967b46b213a3b122e9d6aa564d909d2c546b00
2018-11-07Added missing file in Android.mk to build the NN Driver with the latest CL pinMatteo Martincigh
!armnn:46 Change-Id: I76177ce9eaa5c1132d3e15158844c2fb4a44d57c
2018-11-01IVGCVSW-2084: Edit HAL Policy NHWC DepthwiseConvolutionJames Conroy
Change-Id: Iee54c42e9abd927447d958377f3aee266a60ca5d
2018-10-29IVGCVSW-1986 Modify HAL Policy for Resize BilinearMohamed Nour Abouelseoud
Specified NHWC data layout in ResizeBilinear in HAL policy Change-Id: I0160ec992b595a39ece6d8b060393c5067e8d3a5
2018-10-29IVGCVSW-1065 Allow MODEL_OUTPUT as input to another layerMatthew Bentham
Change-Id: I24fe0916847ec713abf952b9ea911693a692d440
2018-10-25IVGCVSW-2051 Added unit tests in the Android NN Driver for the newMatteo Martincigh
Mean layer * Added unit tests (in a new file test/1.1/Mean.cpp) * Refactored ArmnnDriverImpl to remove redundant tags in the log messages * Modified AddInputOperand to accept a quantized input tensor Change-Id: Ie037ce426777daab28b0501124e1cc8686ad6184
2018-10-25IVGCVSW-2062: Add unit test for TRANSPOSEsaoste01
Change-Id: I12e462c9a0a3613f0158f73929c566f53d1b3c76
2018-10-25IVGCVSW-2049 Create the CL Mean Float workloadMatteo Martincigh
* Refactored HalPolicy::ConvertMean * Added sanity checks when parsing the Mean operands Change-Id: Iea19556adb957b200e7fd01022a87230aaaf7157
2018-10-25IVGCVSW-2049 Create the CL Mean Float workloadMatteo Martincigh
* Added the missing CLReduceMean.cpp file to the Android mekfile Change-Id: Ieaf7c056d6a5e705999a1daef63f5e78d5db3a37
2018-10-25IVGCVSW-2065 - Modify HAL Policy for Normalization to use NHWC data layoutnarpra01
Change-Id: Ic60c4dacb55bcf2514f011a8e844e7b8f7b13560
2018-10-22IVGCVSW-2020: Add converter method for TRANSPOSE to the V1.1 section of ↵saoste01
HalPolicy * Updating SQUEEZE with comments from TRANSPOSE Change-Id: Iec48c5d583fecc5e72082d7de0fc8b1becfd84d7
2018-10-22IVGCVSW-1875 Proper support for NHWC L2NormalizationMatteo Martincigh
* Removed input/output swizzling from ConvertL2Normalization Change-Id: I623d878617614aec4d1f41556839808e6184a350
2018-10-22IVGCVSW-1998 : fix for missing initialization in the driverDavid Beck
Change-Id: I5b1209a871d0a848bb1fdfba5228f181e6968004
2018-10-22IVGCVSW-2007: Fix SQUEEZE error in vts testssaoste01
Change-Id: I5475932be49419e630627ba042ea6a70151b78e7
2018-10-22IVGCVSW-1998 : preparation for ArmNN separate backendsDavid Beck
* to auto-register backend factories we need static global varibles to be initialized which only happens if not omitted by the linker * the whole-library option makes sure we include the whole ArmnN library in the driver !armnn:153399 Change-Id: Idd2fc67ecc848e1b9be75da0e3ceace9bfa0061d
2018-10-22IVGCVSW-1930: Simplifying the driver conversion function for Pooling2d,Éanna Ó Catháin
removing the conversion to splitter layer if pool is 1x1. Change-Id: Iea3af08652dd6fd1e6820ef43d9101d38c230b5e
2018-10-22IVGCVSW-1961: Add converter method for SQUEEZE to V1.1 section of HalPolicysaoste01
Change-Id: I15dffef32d394b13e57df134000b7dca4b8788af
2018-10-12IVGCVSW-1929: Optimize function signature changejimfly01
* Optimize now returns reasons for failure !armnn:152481 Change-Id: I1cd7f5796b3c469e9baecbed80e392ac74e40ef4
2018-10-12IVGCVSW-1964: Replace optional biases with home-grown Optionalarovir01
!armnn:151777 Change-Id: Ib7eba10f05810c03d7384256828bfd0c23bb6bba
2018-10-12IVGCVSW-1886 - adding converter method for PadNina Drozd
!armnn:151190 Change-Id: I37eb70543f23b0ef2f6027998413c62784d9b181
2018-10-12IVGCVSW-949 Update docs wrt recent Uint8 supportMatthew Bentham
Change-Id: Ie01c1293fc4ecfdf19ef06162a62801c453d3ecd
2018-10-12IVGCVSW-1863 Support NHWC for L2NormalizationMatteo Martincigh
* Added L2NormalizationDescriptor to ConvertL2Normalization !armnn:150051 Change-Id: I622d7a8af2bfd27e7d4543a24c59e53988cb5d82
2018-10-12IVGCVSW-1201 - Connect input and output tensor to Mean layernarpra01
Change-Id: I848db966d249a086cd139c407cefced111aa707a
2018-10-12IVGCVSW-1924: advancing clframework pointerjimfly01
!builder:149820 Change-Id: I1b3deb81f9dcb976cae6ec4bccc3149e43ae7d28
2018-10-12IVGCVSW-1814 - Add ConvertMean functionality to HalPolicynarpra01
Change-Id: I04b6150bb490a25fa7bf2da68c339ca5f1fe75de
2018-09-18IVGCVSW-1805: model converter functions for the Android 1.1 SUB operatorDavid Beck
Change-Id: I939cb8d26766c93ee8e3c92909d69549328b0ea7
2018-09-18Removed no longer used source fileMatteo Martincigh
Change-Id: I8f90179ed85a8253785b574499c2f9f4898069d4
2018-09-18IVGCVSW-1806 More Android NN Driver refactoringMatteo Martincigh
* Changed #if defined to #ifdef * Simplified the Android ML namespace resolution * Fixed the relative path in some include directives Change-Id: I46e46faff98559c8042c1a4b8b82007f462df57d