aboutsummaryrefslogtreecommitdiff
AgeCommit message (Collapse)Author
2018-12-04COMPMID-1824 Disable logging completely when building with logging=0Michalis Spyrou
Change-Id: Ie0d5387c0546045e14e62c84c03894a9b0339585 Reviewed-on: https://review.mlplatform.org/335 Reviewed-by: Pablo Marquez <pablo.tello@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2018-12-04COMPMID-1807: Implement ResNet12Georgios Pinitas
Change-Id: I10696b7835eb8ab74ddd5611a278ac0b39d879ca Reviewed-on: https://review.mlplatform.org/333 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Anthony Barbier <Anthony.barbier@arm.com>
2018-12-04COMPMID-1803: Add mobilenetv2 qasymm8 exampleGeorgios Pinitas
Change-Id: Ic9f3d3b4ed452efd1bea4d79d235350c8e521bc9 Reviewed-on: https://review.mlplatform.org/312 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Giuseppe Rossini <giuseppe.rossini@arm.com> Reviewed-by: Anthony Barbier <Anthony.barbier@arm.com>
2018-12-04COMPMID-1820: (Nightly) NEON/DepthConvertLayer/F16_to_F32 failsGeorgios Pinitas
-Removes shift from depth conversion tests. -Changes Cast tolerance between float conversions to zero Change-Id: I6c456f7d910eb3c02069f1e4d5df7b257d6d784e Reviewed-on: https://review.mlplatform.org/341 Reviewed-by: Anthony Barbier <Anthony.barbier@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2018-12-03COMPMID-1710 (3RDPARTY_UPDATE): Remove top_n from get_output_accessorIsabella Gottardi
Change-Id: I9bbe40f8c5c99dfc057d4d5ba4c2fcb193fc99f3 Reviewed-on: https://review.mlplatform.org/336 Reviewed-by: Anthony Barbier <Anthony.barbier@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2018-12-03COMPMID-1819 Add option to build library with -fno-exceptionsMichalis Spyrou
Change-Id: I3de6bb33746d52f8d8c337ab7776eccee8c205fb Reviewed-on: https://review.mlplatform.org/328 Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com> Reviewed-by: Pablo Marquez <pablo.tello@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2018-12-03COMPMID-1497: Use reshaped B strategy in GEMM by defaultAnthony Barbier
NELSTM, NEFullyConnectedLayer(For quantised types only), NERNN and NEWinogradLayer were all defaulting to on-the-fly reshaping of B Fixed a bug in GemmInterleaved: it was ignoring the 'multis' dimension of the tensor to allocate the memory for B reshaped Change-Id: I7b30f7f57fc65d6a03cccde0bf5515a811f17b54 Reviewed-on: https://review.mlplatform.org/323 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
2018-11-30COMPMID-1717: CL: Implement Maximum, Minimum, SquaredDifferencegiuros01
Change-Id: Ice653e48211053bd3cd20a693bd76de6b4efc370 Reviewed-on: https://review.mlplatform.org/270 Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2018-11-30COMPMID-1728 CL: Implement ArgMax/ArgMinMichalis Spyrou
Change-Id: I7eae2e55cc0b0b7bbebb7617299daaca6f75f40c Reviewed-on: https://review.mlplatform.org/292 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
2018-11-30COMPMID-1815 Remove templates from NEFillborderKernel and create ↵Michalis Spyrou
INESimpleFunctionNoBorder Change-Id: Ia9fdc75b23e9a6208058f8406fb7b5fcd917de2c Reviewed-on: https://review.mlplatform.org/311 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com>
2018-11-29COMPMID-1811 (3RDPARTY_UPDATE): Rework benchmarksGeorgios Pinitas
Change-Id: I02a4ea0270e1776daf8ac1084f28dd054257be4a Reviewed-on: https://review.mlplatform.org/309 Reviewed-by: Pablo Marquez <pablo.tello@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2018-11-29COMPMID-1451: Enable FP16 runs on graph examples.Georgios Pinitas
Change-Id: I4e3269f1dc83ce9278230b6fc70a7981d05c61f6 Reviewed-on: https://review.mlplatform.org/315 Reviewed-by: Surabhi Mehta <surabhi.mehta@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2018-11-29COMPMID-1451: Remove invalid bias inclusion in specialized function.Georgios Pinitas
Fixed Segfault by removing bias iterator from specialized function which assumes no bias being provided. Change-Id: Ic897435ee9427d4359e8ab989a03e951da0d7ce0 Reviewed-on: https://review.mlplatform.org/314 Reviewed-by: Anthony Barbier <Anthony.barbier@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2018-11-28COMPMID-1813: Fix bias == nullptr in NEDirectConvolutionLayerOutputStageKernelGian Marco Iodice
Wrong check in the function Change-Id: I38e4d5f01039c8352c0e83f0711455af85f9c3fe
2018-11-28COMPMID-1710: Fix Link READMEIsabella Gottardi
Change-Id: I3f8175538152cd801c8ed4244a8ae3f75d182997
2018-11-28COMPMID-1716: CL Comparison operationsGeorgios Pinitas
Adds support for Equal,NotEqual,Less,LessEqual,Greater,GreaterEqual Change-Id: If0cdf4aae7f95c94709b195eee485f6663f45909
2018-11-27COMPMID-1720: CL: Implement Tilegiuros01
Change-Id: I2a18f0acea382960a8bc71a8f56928a5998f0dd6
2018-11-27COMPMID-1810: Fix std::stoul in MemUtils.cppGian Marco Iodice
Change-Id: Icadce1298f9e52dc6f4b0adc1556ede9dd9a2a2e
2018-11-23COMPMID-1647 NENormalizationLayer IN_MAP_2D support for NHWC for FP32/FP16Michalis Spyrou
Change-Id: Id74cc7ba8e5cabee6acd3798d4779f88b1f00a9b
2018-11-23COMPMID-1734: Implement CLSelectGeorgios Pinitas
Change-Id: I49b2e8b4200c9ed654736d9451e4ab9c073b4b10
2018-11-23COMPMID-1451: Fix MemoryManager usage.Georgios Pinitas
-Fixes NEWinogradConvolution memory manager usage -Moves allocations in prepare staged for GEMMDispatchWrapper. Change-Id: Ic1c709ee473eb4968f5a081f2bc26960f882f8db
2018-11-23COMPMID-1458: Mobilenet SSD example.Pablo Tello
Change-Id: I9d4ba7d00d50a84f650f0449faa8a25226068fed
2018-11-22COMPMID-1645 NEL2Normalization for FP32/FP16 & NHWCMichalis Spyrou
Change-Id: I29e35024e29781a6b943b568abec9c73649215e6
2018-11-22COMPMID-1718: Extend DepthConvert to support CastGeorgios Pinitas
Change-Id: I6ee2c0b670727fc808fa636c53ddfaec3a0036c9
2018-11-22COMPMID-1648: CLNormalizationLayer IN_MAP_2D support for NHWC for FP32/FP16Michele Di Giorgio
Change-Id: I49f1d865f5e7562f1d80db849353a89ef77e6a9e
2018-11-21COMPMID-1451 Change PriorBox output to NCHwMichalis Spyrou
Output of Priorbox should be independent of the input data layout and should always be in NCHW format Change-Id: Ie80cd4e51c78945b158c0db1af1923bdf8d7ea7b
2018-11-21COMPMID-1451 Fix macros in SpaceToBatchMichalis Spyrou
Change-Id: I95fdf5bd85becfe081f6ae587284f3b294681308
2018-11-21COMPMID-1451: Fix Test documentationIsabella Gottardi
Change-Id: I62d937533967b29505d3ac8a51b513f0c6de8cd0
2018-11-21COMPMID-1800: (Nightly) Mismatches in SC9863 board for NEON FP16Michele Di Giorgio
Fixes for: - ReduceMean, reduction on the X axis for FP16 with 8 elements was performed only up to a certain point. The fix now takes into account the number of elements of the vector and does as many reductions as necessary. - YOLOLayer, activation for FP16 has to be performed on 32 bits until the FP16 approximations is fixed. Change-Id: I75373f4edd37de476e6fe1a56de3ef386b65c619
2018-11-21COMPMID-1451 (Nightly) L2Normalization sigkillMichalis Spyrou
NHWC reduction on 0 axis requires a lot of memory. Testing only axis 1 and 2 for now. Change-Id: I82e16a27b6dfc6b426e6294cde63c3d88cb41a09
2018-11-21COMPMID-1088: Use IMemoryRegion in interfaces where possibleGeorgios Pinitas
-Simplifies import memory interface -Changes the used of void** handles with appropriate interfaces. Change-Id: I5918c855c11f46352058864623336b352162a4b7
2018-11-20COMPMID-1646: NEResizeBilinearLayer NHWCGeorgios Pinitas
-Adds NHWC support for FP16 Change-Id: I61addf8efecf511ac8cd5f8aa9afc3e09c476aaf
2018-11-20COMPMID-1799 (Nightly) CLL2NormalizeLayer mismatchesMichalis Spyrou
Changed random distribution to [1, 2] as values close to zero generate mismatches. Change-Id: I4a00fc4f445b123dea624dd8459efce945f06126
2018-11-20COMPMID-1777: Output queued and flushed timestamps tooAnthony Barbier
Change-Id: I376d29aa6ec1b52d978c4d49de63c6713d6036e3
2018-11-20COMPMID-1801 : (Nightly) CLWinogradConvolutionLayer FP16 mismatchesVidhya Sudhan Loganathan
FP mixed precision support added to GEMM kernel used for fp16 winograd conv on Midgard GPUs Change-Id: I1619beb025fc484a1ac9d3e528d785edabbc7ee6
2018-11-20COMPMID-1451: Fix CLBatchToSpace static validation methodMichalis Spyrou
Change-Id: I770b044b67d93510ef65e556905135b34be7ea0a
2018-11-20COMPMID-1798: Update doxygen for 18.11Isabella Gottardi
Change-Id: I5f99e448e208be6ca819bf4ab2c7b367c874d3f5
2018-11-20COMPMID-1458: DATA_UPDATE SSD mobilenet weights.Pablo Tello
Change-Id: I4c84a3156114d973fcff22a6b86a3c0044502fc8
2018-11-19COMPMID-1644: NEDepthwiseConvolution for FP16 NHWCGeorgios Pinitas
Change-Id: I6e7dee8bd615a5eff01c523f208a218574ee5eab
2018-11-19COMPMID-1458: DATA_UPDATE Added SSD mobilenet npy files.Pablo Tello
Change-Id: Ieb6f0638174ea1deb8b457d8df81511651a246a9
2018-11-19COMPMID-1065 : Create documentation explaining how to add new functions / ↵Vidhya Sudhan Loganathan
kernels Change-Id: I98183f95814442b6f3dbb67a1bdae99df05b9b01
2018-11-19COMPMID-1065: Added link to dev-repo to README and added missing presentationAnthony Barbier
Change-Id: I88c4a3b55943ed3bcf63cad63b0c7570770c2056
2018-11-19COMPMID-1065: Created a list of the existing FunctionsAnthony Barbier
Change-Id: I54a3f34aa3657396e931f18c81af2941d3b56903
2018-11-19COMPMID-1750: Add PriorBox operator to graph API.Pablo Tello
Change-Id: I5d2ed5dcc342abff8124762f7bdee587cdf20032
2018-11-16COMPMID-1451: Fixes for BoundingBoxTransformgiuros01
- Fixing a bug for which we did not scale the boxes before transforming them - Adding the correct_transform_coords option to BoundingBoxTransformInfo Change-Id: I40281254bcf87e7c8583c119e99562414fe59822
2018-11-16COMPMID-1451: (3RDPARTY_UPDATE) Fixes for GenerateProposals graph node and ↵Michele Di Giorgio
BoxWithNMSLimitKernel COMPMID-1792: Accuracy issue in CLGenerateProposals This patch does the following: - Some fixes for GenerateProposals function and tests - Adapting BoxWithNMSLimitKernel to only accept U32 tensors as keeps_size - Update 3rdparty - Adds a small tolerance for a GenerateProposals test Change-Id: Ia8ec1cdfe941fe05003645e86deb9ea6a6044d74
2018-11-16COMPMID-1266 : Add support for FP16 in CLWinogradConvolutionLayer: 5x5 kernelsVidhya Sudhan Loganathan
Introduced F32 accumulation for F16 winograd gemm and output transform WinogradConvolution will be available for F16 only if fast math flag is enabled Change-Id: I215593c205236a0f9669218437bb40b184ec6a4f
2018-11-16COMPMID-1785: Support for 4D tensor in CLFlattenLayerKernelGian Marco Iodice
With this patch we are able to dispatch a single GPU job also in case of batched-flatten Change-Id: I755e7af29d44b24f67fa04bad3c9b7646e8deefc
2018-11-16COMPMID-1793 CLL2Normalization mismatchesMichalis Spyrou
Increase tolerance for FP16 Change-Id: I88f95da5471bbceb7449f453e2e33cf0bc4da23e
2018-11-16COMPMID-1791 CLPriorBox clCreateKernel errorMichalis Spyrou
Change-Id: I2c2250669829e399fdc2363f729dc5e68d8aac17
generated by cgit v1.2.1 (git 2.23.0) at 2024-06-25 05:34:23 +0000