Age | Commit message (Collapse) | Author |
|
Added support for dilation in DepthwiseConvolution2d in the
Neon and CL backends.
Change-Id: Ie1522b498c07f80d6efcf9dc79e926c8cfa06ca5
Signed-off-by: Pablo Tello <pablo.tello@arm.com>
|
|
+ Update clframework pin
+ Cl and Neon Merger workloads updated to use MemoryLayout agnostic API
+ Workloads only use sub-tensor optimization if ALL input tensors are sub-tensors
+ Refactor LayerSupportCommon code to be a bit more succinct
Change-Id: Ib61ad4ccbd767e924dff07e61022e0cda4069828
Signed-off-by: Derek Lamberti <derek.lamberti@arm.com>
|
|
!android-nn-driver:968
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com>
Change-Id: I03ccb4842b060a9893567542bfcadc180bbc7311
|
|
* Compute Softmax Acl axis for Cl and Neon
* Add unittests for Softmax in 3D and 4D
* Correct input and output layer names in CaffeSqueezeNet inference test
Change-Id: I2d369d9a2db19c40f2af3341039dd33f0c5637b1
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
|
|
*Padding was not in format expected by Cl
Change-Id: Id0de3fd2b306e31d555e2d67bc4406e5302dcd3b
Signed-off-by: Nattapat Chaimanowong <nattapat.chaimanowong@arm.com>
|
|
* Added Logistic tests in ClLayerTests
* Removed check for QuantisedAsymm8 in CLActivationWorkload
Change-Id: I6950e18109504d8426b727cb6b7d19898c899024
Signed-off-by: Finn Williams <finn.williams@arm.com>
|
|
Change-Id: I7eb3b2e712dbaa5c13f6cf3a1da63df4d2bd4de5
|
|
whats done in the constructor.
Change-Id: I9488cebd63767c0c51d9ee6333d5aaf0e4a85847
|
|
* Added CL unit tests
Change-Id: Ia4af49b133774141384a177f5b042e65764bf682
|
|
* 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
|
|
Factor out new BuildArmComputeReductionCoordinates function
from CL backend into ArmComputeTensorUtils.
Update NEON LayerSupport and WorkloadFactory objects
Change-Id: Icc975ec699199bffafbdb207323df509d35e1e04
|
|
!android-nn-driver:428
Change-Id: I42e59ad96d2c80f46b085182855d34b710a74dfe
|
|
* Added CLMaximumWorkload implementation
* Added CL unit tests
Change-Id: I922c83fe25d17be21a5d0f4e861038463cb09789
|
|
* Added ACl Implementation to ArmNN
* Added helper function for setting CL Strided Slice arguments
Change-Id: Ie10d387fdb054027ea9b8782743d270bb72949c1
|
|
Change-Id: I0d69a72df9e348cbeca690926485c050499d1051
|
|
Change-Id: Ic772acf481caed6e8a6b99f68a63dfc2a34c24dc
|
|
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
|
|
* 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
|
|
DataLayout (3*3 Optimization)
Change-Id: Icfc137201c52e2c856076b7795572cc4ba75cc95
|
|
Change-Id: I663a0a0fccb43ee960ec070121a59df9db0bb04e
|
|
the unit tests
* Created the ClFloatWorkload class
* Added ClMeanValidate validation function
* Added helper function to convert the reduction axes from the ArmNN
format to ACL's
* Added workload tests
* Added some unit tests
* These changes need the CL pin to be pointing at least to revision
88d871028eeae57f9e4536d0329110eccb5e2890 (COMPMID-1574 Implement
ReduceMean in OpenCL)
!android-nn-driver:155033
Change-Id: I694fd36be0458c90e158172afde045fcc88c32ae
|
|
* Added wrapper function around arm_compute::IFunction::run() that catches
cl::Error and wraps it into an armnn::RuntimeException
* Added MakeWorkload template inside ClWorkloadFactory that catches
cl::Error and wraps it into an armnn::RuntimeException
* Replaced cl::Error with armnn::RuntimeException in catch statements inside
LoadedNetwork
Change-Id: I2340f41ae02b8db1d7ef5157824a50e7410854e3
|
|
ClLstmFloatWorkload::Execute()
Change-Id: Ia3f895474b54e73711feb9795e7d47cbd61f13a3
|
|
* 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
|
|
* Added RefPadWorkload implementation
* Added unit tests and applied them to CL and Ref backends
* Fixed a bug in ClPadWorkload
Change-Id: I8cb76bc9d60ae8a39b08d40f05d628e3b72f6410
|
|
!android-nn-driver:153490
Change-Id: I1c2a5f942e3a1c3626e093c90545ca27c64ba5e8
|
|
Change-Id: I558a9a007604afc55e536d877f8da7d0215cc9c3
|
|
Change-Id: I3e6e5b9a62f30d03c05bd7178adea8f4c8275da8
|
|
Change-Id: I5349629bc5b36e5b5029a158bf888c09c3bda4b0
|
|
Change-Id: Iaa3158487b58964d8a3b98acadde7c10172a3860
|
|
Change-Id: I8580f5d1612567a3b02cfccfd1f8d0f196eeda93
|
|
Change-Id: I200adcef35b861a412e7beef8043d5c7dddba443
|
|
* Adds implementation to plumb DataLayout parameter
for ResizeBilinear on CpuRef.
* Adds unit tests to execute ResizeBilinear on CpuRef
using the NHWC data layout.
* Adds DataLayoutIndexed API, allowing easy access to
the Channels, Height and Width of a tensor based on
its data layout. This reduces code duplication.
* Refactors original ResizeBilinear implementation and
tests to use the DataLayoutIndexed API when required.
Change-Id: Ic2b8916cdd2e370d070175547079d774daf6d7bf
|
|
Change-Id: Ib2c9fe56c59aedabeff899a81a0afe260bd57c9f
|
|
Change-Id: Ibd12e04abe71015f31ee36a7f0a2416cb625cdad
|
|
Change-Id: I8182f781369956ca96562777f170ef677f831e4e
|
|
Change-Id: Ic16c4505bac9c9025856aa4eac1127ad957c9d75
|
|
Change-Id: I9059a292e47867df82a5efbba5808fd264949ec9
|
|
Optional<std::string&> in IsLayerSupported implementations
Change-Id: I2f054f0dcff9bdc86ee90c55b3e94c6b4ae25085
|
|
Change-Id: I8bc11c93759605e21cc52f44d032c32a0be63658
|
|
!android-nn-driver:151788
Change-Id: Ibdc41d09b8df05e7a0360dcb8a060860dfb1bd99
|
|
Change-Id: Iaa99500bfa8cea846f57636590698f9c8a8c2de0
|
|
* Added simple convolution Unit test
* Set the data layout correctly in workloads
Change-Id: Ie71b8415f6abc392a84900fc4438b7416fbb558a
|
|
* 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
|
|
* Refactored ClResizeBilinearFloatWorkload so that
ConvertDataLayout is executed once only.
Change-Id: I3961847eaab65caa696c61fad665dc042556f098
|
|
Change-Id: Iea941c1747454f5a4342351e4e82b10ffb9ccbbd
|
|
* Added data layout parameter to ResizeBilinear
descriptor, in order to support NHWC.
Change-Id: Ifdbc4529127b7329a056d0a68e2e42b175aeea4a
|