Age | Commit message (Collapse) | Author |
|
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
|
|
This is one of the reasons why the tests in https://review.mlplatform.org/#/c/ml/armnn/+/237/
are failing (but not the only reason).
Change-Id: If485bade2a6dd013cba826cec71d748fc7747249
|
|
* Updated build guide to include instruction to copy
libprotobuf.so.15 into the build folder before moving
to arm64 machine.
Change-Id: Ia20691edc79ff59fa4147eafbbfd3997b2531317
|
|
Change-Id: I55e27c50953c5e3f0b43bcd7aa8643015480181d
|
|
* helper methods for creating TensorShape and TensorInfo objects
Change-Id: I371fc7aea08ca6bbb9c205a143ce36e8353a1c48
|
|
Change-Id: I9bc46e17e11d73ee1a3bc4f9ec07d46be77fcbcb
|
|
Change-Id: Iab9c4952f5478d4805dba56e838f9c33d2b598ee
|
|
* Fixed unsigned to signed conversion error that was
breaking master
Change-Id: I08d79d9bf131eb46ea0495371160698ab59c1721
|
|
* When running the script standalone USERNAME can be unset causing failure
Change-Id: Idb1752117c319c8946426efe8882f03034b2bbbf
|
|
Change-Id: If8d8087d9d365e467d3ca9bf9c40d7219cb75cfd
|
|
* Add LayerTests
* Add WorkloadTests
!android-nn-driver:166
Change-Id: I903461002879f60fc9f8ae929f18784e2d9b1fc1
|
|
Change-Id: Iab6ad04e5c786e4e639578f7b1d1537dd1196e2f
|
|
* 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
|
|
Change-Id: Ib11c3d36c7109198da7266955414580e8fb916b5
|
|
Use CMAKE_THREAD_LIBS_INIT instead of pthread in sample_app.
The separate pthread library doesn't exist on Android.
Change-Id: I9a363ba7d29d2673359349f5f4288844f0550946
|
|
Change-Id: I0042395b46906f70d09a16b4122af3d911f5a53d
|
|
* Added line to README.md explaining the function of the get_compute_library.sh script
Change-Id: If6be1c64443dcd6d0a08a12485de3d38614542f0
|