Age | Commit message (Collapse) | Author |
|
* A recent change in ONNX now forces the data types to be indicated by the
integer corresponding to their original enum value
* The new values are taken from the TensorProto_DataType enum at onnx.pb.h:153
Change-Id: I6054611795a7edb11463396eaefc4dd7e27261a0
|
|
Change-Id: I72d94fff4cdad2c62dff98c8fd52eba78a1908f0
|
|
* Fixed invalid conversion issues to onnx::TensorProto::DataType
Change-Id: If8f1cef1d02a22cfecf24135a960923d3ad0e14c
|
|
Kernel position within the layer is part of the kernel name
Change-Id: I3b9ee870fbd0db025f1515c81245f917189ae884
|
|
Change-Id: I0d69a72df9e348cbeca690926485c050499d1051
|
|
Unit tests not yet added as need Compute Library a84faffd.
Change-Id: Ica16df493e8d6a76da9d1f74bf43b8403f9dff62
|
|
NEFillBorderKernel may not be issued for some activation workloads
depending on the version of the Compute Library.
Change-Id: I01b8960f9eb7a0192cd351eddbb416ac05248b34
|
|
* Removed the input swizzling when the concatenation dimension is 3
in ParseConcat in the TF parser
* No longer using the helper ProcessConcatInputTensorInfo, where
the input was being swizzled if the concatenation dimension was 3
* Added a new convenience constuctor to TensorShape that initializes
a shape to all zeros given only the number of dimensions
Change-Id: I82a207e41bddc5fea21a0b5a38eafa24ad75d1c2
|
|
Change-Id: I87c53c78dd033871dbc543550a61d2d535e752ac
|
|
Change-Id: Ib2e5de2a057da57ef77a9f5c4367d699d4773294
|
|
* Also added unit test Sub.cpp
Change-Id: I6d23c11ae894ee433cd28ffdf0248b14e01b0131
|
|
Change-Id: I0d02faf188f441f017967057f16f4661d321978a
|
|
* Remove input swizzling from ParsePooling2D and add parameterized
tests for NCHW, NHWC and Padding="SAME".
Change-Id: I4786fcc31b6ac46bf19d887f007963eb924f0f9f
|
|
as validation assumptions should not be made and
should be handled by the backend
Change-Id: I1565daeb0abfdc0bb01981eab2a1937a5af7976e
|
|
* Fix for a signedness error in Android 32 builds
Change-Id: Id909ee2d50f376782de3b80aaef503e08f6d1268
|
|
Change-Id: I6b26c681989ef815752186f027a245ef8da7aea2
|
|
Change-Id: If5ef3dc426bd6fa5aab342dcece6e99f86e65dba
|
|
* Removed the input swizzling when the data layout is NHWC
* Split the unit test into NHWC and NCHW cases
Change-Id: I6b9fef70bc4ba5e01d14cbfaea3c842a289b0a0e
|
|
* Removed the input swizzling when the data layout is NHWC
* Permuting weights depending on the data layout used
* Added getter methods to ParsedConstTfOperation to get the tensor
info and the storage memory area, needed for swizzling the weights
* Added unit tests for both NHWC and NCHW data layouts
Change-Id: I6543900c594417df630b2663d8551158b93b7836
|
|
* Add ExpandDims operation to TfParser.cpp
Change-Id: Ifa756ae0667c11e3b6daec8f6dd4e54cac88d16a
|
|
* Also added unit test armnnTfParser/test/Pad.cpp
* Added missing 'Pad' entry to GetLayerTypeAsCString(LayerType)
* Fixed the RefLayerSupport.IsPadSupported, now it returns true
* Small fix in Optimize. Only resolve stringstream to string once
Change-Id: Ieaa1886858a48cd761ac5f30454f73e44bdd4b8f
|
|
* 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
|
|
Change-Id: Ib84e5bde39d706c5125e0f84577195fc61107a4a
|
|
Change-Id: I017ca6c23b62a8978982de0ca4ad204cb8cf7c67
|
|
* Extended Maximum operator support in TF Parser
* Added extra unit tests for Maximum operator in TF Parser
Change-Id: I68edb43b2a3105507f2f5f028ff0e35206965dca
|
|
Change-Id: I5455b720565248ff94278e76887d63f8434a7b58
|
|
* Enable Maximum workload
Change-Id: I5f7786ff66f135f0c74935dbf5861e5a4239bcc8
|
|
* Changed NeonL2Normalisation to use NEL2NormalizeLayer to
normalise along the channel axis in either NCHW or NHWC format
Change-Id: Ibaf119b6a3de3c0f80f94b1c5fe9a356cf1fbd0e
|
|
* Updated Revision number in the get_compute_library.sh to after the
implementation of COMPMID-1645 NEL2Normalization for FP32/FP16 & NHWC
Change-Id: Id9f437e833aafdb83c76bec1ba3fe79fdbab1a69
|
|
Change-Id: Id7302c6b1df995ebe6eb8eb94bab38bee1b31b0b
|
|
Change-Id: I03fa374fd9692d98257de709f8c3ad0a49c88b95
|
|
workloads and workload functions
Change-Id: I6f3fce12a55f7d38ceafcdfcd6b5181bf56e2c09
|
|
Change-Id: I8964f5e8978c2d2a07734a381e3f7c656c22456a
|
|
Change-Id: Ic772acf481caed6e8a6b99f68a63dfc2a34c24dc
|
|
Includes a temporary workaround for COMPMID-1813
Change-Id: I3e5217281be072d5b61788ab8a75e818bbc5d247
|
|
Change-Id: Ifeacc0adb4547c72537b9ea7a61bf3c4ec3673fa
|
|
Change-Id: Ib2bf543fc4f855da94eb1d34a91637f7868321cd
|
|
Change-Id: I40acb42360bfcda09485efb2a54144d8e35bdafb
|
|
* Wrap Resize function call with conditional checking
if height and/or width need to be changed.
Change-Id: Ic33c3ed29cc985c147d29db8e9dd237ab9c741d1
|
|
* Removed the usage of g++-5 as we can build it using later versions
Change-Id: I073c84868c8619aeb5e4bd3006b87d10b7fec37e
|
|
* Removed confusing mention of Anaconda and CuDNN and reworded
Change-Id: I2e4d86704c6564b2d18cec191246edd15cde0905
|
|
Change-Id: Icc1de9b69d7bb74b6bf5a6a6f315cf07fe2c5223
|
|
Change-Id: I26fb13717f64c942b2648702c52be18be856042d
|
|
guides
Change-Id: Ia040a6accb4ae07156b2e1ad0ebef12423f647ed
|
|
Change-Id: Ifa88a879dd239f60ab27330d6b73859393828ef0
|
|
Enabled subtraction broadcasting tests for CL/NEON
Enabled Uint8 subtraction tests for CL
Change-Id: Id36c1530f967c77f5633616e8f491cac9547724b
|
|
Change-Id: I3a6077ad9ded9002aea9c888daab68b6452bd235
|
|
Change-Id: I2d5f017917b1c773ff3da96ab28de415c1e77c0d
|
|
* Add CommonTestUtils
* Add end to end layer test implementation
* Add example usage for Merger layer on Ref, Cl, Neon
Change-Id: I8931136288cd68b80bcdad8f5ae087ae1a70a60a
|
|
Change-Id: I4887e3509a7f406c80f7eb55c04bdf62395c6cf6
|