Age | Commit message (Collapse) | Author |
|
* 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
|
|
Change-Id: Icf7ef88a2eaef80ec32cc718b0ca9d26e830ed07
|
|
Factor out new BuildArmComputeReductionCoordinates function
from CL backend into ArmComputeTensorUtils.
Update NEON LayerSupport and WorkloadFactory objects
Change-Id: Icc975ec699199bffafbdb207323df509d35e1e04
|
|
Technical debt work towards adding some new Neon workloads
Change-Id: I08ab6dd14d0e89d4ebc8a878fb69caa5681012bf
|
|
Change-Id: Iddae3486641d2d195827ae4e0a9dfa3f7ccd65e3
|
|
Change-Id: I0d69a72df9e348cbeca690926485c050499d1051
|
|
Unit tests not yet added as need Compute Library a84faffd.
Change-Id: Ica16df493e8d6a76da9d1f74bf43b8403f9dff62
|
|
* 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
|
|
* Changed NeonL2Normalisation to use NEL2NormalizeLayer to
normalise along the channel axis in either NCHW or NHWC format
Change-Id: Ibaf119b6a3de3c0f80f94b1c5fe9a356cf1fbd0e
|
|
Includes a temporary workaround for COMPMID-1813
Change-Id: I3e5217281be072d5b61788ab8a75e818bbc5d247
|
|
Change-Id: If8d8087d9d365e467d3ca9bf9c40d7219cb75cfd
|
|
* Add ClMergerWorkload and NeonMergerWorkload to call ACL for innermost concat axis
* Modify layer support to call ClMergerWorkloadValidate and NeonMergerWorkloadValidate when concat axis is inner most
* Add m_ConcatAxis to MergerDescriptor
* Modify MergerQueueDescriptor::Validate to check sub tensor only when using subtensor
!android-nn-driver:166
Change-Id: I56676b43964c8d6d726387b41b3cc34a512c0f0a
|
|
* Remove check for preferDirectConvolution
* Remove IsNeonDirectConvolutionPreferred
* Remove unused tests and functions
Change-Id: I3f0868f41403ec5fa740889e7bdcb4415ad77bda
|
|
* Changed ClL2Normalisation from using CLNormalizationLayer
to use CLL2NormalizeLayer to normalise along the channel axis
in either NCHW or NHWC format.
Change-Id: I399cbee408a277d1ef8c6c85ebcbd86d6c3e407b
|
|
* Ported Google's LSTM implementation to RefLstmFloat32Workload
* Fixed the code throughout because of an error in the docs around the
scratch buffer size
* Updated IsLstmSupported
* Added the unit tests
!android-nn-driver:127
Change-Id: I5577b7e39ca52df1a7f102a9b437df6aa99520b6
|
|
Change-Id: I663a0a0fccb43ee960ec070121a59df9db0bb04e
|
|
* Adds implementation to plumb DataLayout parameter
for Pooling2D on CpuRef.
* Adds unit tests to execute Pooling2D on CpuRef
using NHWC data layout.
* Refactors original tests to use DataLayoutIndexed
and removes duplicate code.
Change-Id: Ife7e0861a886cf58a2042e5be20e5b27af4528c9
|
|
Change-Id: I962e986607e5d045cd97b9eaeaea2f5ae624db35
|
|
Change-Id: I411d02949524eb802672d83ee281300c34b007c8
|
|
Change-Id: Id3d8137d60b14e93863ad5b6db752a7f6ef9b7fb
|
|
Change-Id: I147dbf6811f84ec4588264d636a36efc8ec56f72
|
|
ILayerSupport interface
Change-Id: I03985ff678acf9393680340638a2e1f425b9966f
|
|
!android-nn-driver:153490
Change-Id: I1c2a5f942e3a1c3626e093c90545ca27c64ba5e8
|
|
Change-Id: Ib831f02ab6b5d96f1a959187d8f3e694e6257ae5
|
|
Change-Id: I558a9a007604afc55e536d877f8da7d0215cc9c3
|
|
Change-Id: I4b3247fc7c5eb1c0cec5cf22c56d4c7a3f36d51a
|
|
Change-Id: I65129a72d7585776797cfe0947a2a0f1f483b72f
|
|
Change-Id: Iace26e575d8eca50cc81a881b7bb5be46b00f1dc
|
|
Change-Id: I90bf3baaad725d121ca864b7a7bb0c74abb69daf
|
|
Change-Id: I3e6e5b9a62f30d03c05bd7178adea8f4c8275da8
|
|
Change-Id: I284a9aa6865cdbd6975c54b011d2cec15a174e79
|
|
Change-Id: I564a743b4d90ae5364c5958eed3fbfba97782b80
|
|
Change-Id: I9059a292e47867df82a5efbba5808fd264949ec9
|
|
Optional<std::string&> in IsLayerSupported implementations
Change-Id: I2f054f0dcff9bdc86ee90c55b3e94c6b4ae25085
|
|
!android-nn-driver:151788
Change-Id: Ibdc41d09b8df05e7a0360dcb8a060860dfb1bd99
|
|
* Added simple convolution Unit test
* Set the data layout correctly in workloads
Change-Id: Ie71b8415f6abc392a84900fc4438b7416fbb558a
|
|
Change-Id: I107d732760dd8662e2ee9a5e7ebb5baf61c45246
|
|
* Added NHWC unit test implementation
* Programmatically selected the channel dimension when creating
the ACL Normalization layer info
* Set the input/output data layout in the constructor of the L2Normalization
workload
Change-Id: Ie69f1a360022c29d1a3a3808c1f26b69243fa8f9
|
|
Change-Id: Iea941c1747454f5a4342351e4e82b10ffb9ccbbd
|
|
* 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
|
|
* moving backends/ClWorkloads to backends/cl
* and moving pure Cl workload related code to
backends/cl/workloads
Change-Id: I019a3c6b4da5e7a23074bf03fb057e63199ad129
|
|
* Added L2NormalizationDescriptor struct with m_DataLyaout member
* Updated all IsL2NormalizationSupported calls to take a descriptor
as an argument
* Updated L2NormalizationLayer to take a descriptor as an argument
!android-nn-driver:150116
Change-Id: I0459352d19cfd269bc864a70cf73910bf44fdc01
|
|
Change-Id: I33dce72bb0f1e25425dc058d6213a7cdf56eecd2
|
|
armnn:149855
Change-Id: I26e8cf83422a65049386a5ebdb6d0001627aefaa
|