armnn.git -

Age	Commit message (Collapse)	Author
2019-11-06	IVGCVSW-4038 Convert Strided_Slice Shrink_Axis_Mask Parameter to ACL format	Francis Murtagh
	* Add conversion method to reverse bits in Shrink_Axis_Mask * Add Unit tests for Neon, CL and Reference backends * Fix supportedness of constant layer which is causing error in DeepSpeech Uint8 * Also convert the Begin_Mask and End_Mask Change-Id: I448b083c3463558e8fb5204923ab554cd43264ba Signed-off-by: Francis Murtagh <francis.murtagh@arm.com>
2019-09-16	In CopyTensorContentsGeneric coalesce inner dimensions where possible	Matthew Bentham
	This reduces the number of function calls in the inner loop, and allows for optimised implementations of memcpy to improve bandwidth Signed-off-by: Matthew Bentham <matthew.bentham@arm.com> Change-Id: I7458b45c075c87805242e92e54448b9dd762227f
2019-09-16	Rename variables in CopyTensorContents to assume NHWC	Matthew Bentham
	Change-Id: I533991c8829256570529c18023a5e882878cc85a Signed-off-by: Matthew Bentham <matthew.bentham@arm.com>
2019-08-26	IVGCVSW-3575 Fix DepthwiseConvolution VTS Test Failures	Kevin May
	Failing VTS tests were "NeuralnetworksHidlTest.depthwise_conv2d_" In depthwise convolution there was a difference in weight tensor channel order between the reference and ACL implementations. This specifically related to NCHW. This commit: Adds ReorderWeightChannelsForAcl to WorkloadUtils which will correct the weight tensor channel order. * Add unit tests to detect this problem. Signed-off-by: Colm Donelan <Colm.Donelan@arm.com> Change-Id: Icaeac08e14b3d5da9e222ad2f118db55ebb15d09
2019-08-16	IVGCVSW-3639 Add 5d tensor support	Matthew Jackson
	* Increased MaxNumOfTensorDimensions and fixed issues related to its use * Fixed issues caused by assuming 5d tensors are invalid * Updated ArmComputeTensorUtils for 5d tensors * Added 5d tensor unit tests for add, mul, stack and reshape (needed by IVGCVSW-3527) Signed-off-by: Matthew Jackson <matthew.jackson@arm.com> Change-Id: I5bcd64942d0d04efcc6c5acb240ad4b88e010743
2019-01-04	MLCE-77 Depthwise Convolution with depth multiplier > 1 doesn't work	Matteo 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
2018-12-31	IVGCVSW-2389 WorkloadUtils: Add profiling to tensor mapping.	Sadik Armagan
	Change-Id: Ibe1b27b268011878c7dce3c96efea01402453027
2018-11-02	IVGCVSW-1946: Remove armnn/src from the include paths	Aron Virginas-Tar
	Change-Id: I663a0a0fccb43ee960ec070121a59df9db0bb04e