Age | Commit message (Collapse) | Author |
|
Signed-off-by: Cathal Corbett <cathal.corbett@arm.com>
Change-Id: Ib733b9fe1a5b6f47dc110c7bb96cbea9d656df0d
|
|
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: Ida88b27affe2942173e4a51eb9259de6d2a1fed1
|
|
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: I3873a59e84d7fba1a0fec765d2131576d090c0b5
|
|
Signed-off-by: Colm Donelan <colm.donelan@arm.com>
Change-Id: Id046063d479d3f4c2bf03d983e651d34f5486c73
|
|
* Add rescales before and/or after ops when using int8
Signed-off-by: Kevin May <kevin.may@arm.com>
Change-Id: Ic9704f91147a1a439411511c7d57d0aa52b93e26
|
|
Signed-off-by: Cathal Corbett <cathal.corbett@arm.com>
Change-Id: Ifd8a2e11fbbd19baaf0ceb232417c2450fdece18
|
|
Signed-off-by: Matthew Bentham <Matthew.Bentham@arm.com>
Change-Id: I559111f479b577695ef71000c62a704cbe636238
|
|
Fix issue building ExecuteNetwork when building opaque delegate
and not classic delegate.
Signed-off-by: Matthew Bentham <Matthew.Bentham@arm.com>
Change-Id: Ie313344e19477e7e7110f6f713a54de047d2d93d
|
|
Signed-off-by: Colm Donelan <colm.donelan@arm.com>
Change-Id: Ib027a36c6c10cd37fb461af29163999bd1764be7
|
|
* Creates a numpy parser helper header
* Adds ability to parse numpy file in PopulateTensorWithData
* Reuse ExNet compare-output flag to compare against npy golden files.
* Reuse ExNet write-outputs-to-file flag to write output to npy file.
Signed-off-by: Cathal Corbett <cathal.corbett@arm.com>
Signed-off-by: Ryan OShea <ryan.oshea3@arm.com>
Change-Id: I52df822f72f6ce9d191ac4bd26ca5718ccaa7a4a
|
|
* Needed for ACL 24.05.01
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: Ib77f5cc2c3f7a7bca71312bd97e9cf610a80beee
|
|
Signed-off-by: Cathal Corbett <cathal.corbett@arm.com>
Change-Id: I0f9ae70bce4daf96f17ee29e80914dc299e2a7d7
|
|
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: I8a687ef952afbe871d214cdf157e8858429ef763
|
|
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: Iea780536e343acd853e367a50caeef53b1decd99
|
|
* Cross-compiling from scratch on Linux for Android cmake won't find any headers or libs because
find_lib and find_path apprend the SYSROOT to the specified paths
* Resolves MLCE-1294
Change-Id: Id92297a96a536d343e4b951fd96f1f51ea97f4a3
Signed-off-by: Pablo Marquez Tello <pablo.tello@arm.com>
|
|
* Add layers missing in PyArmNN
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: Ia821105f9d235dcf7f9472e54849d268e07fb9a9
|
|
The sample apps were not included in the original set of files updates
to account for 24.08 deprecation notices. This cause a nightly failure.
Signed-off-by: Colm Donelan <colm.donelan@arm.com>
Change-Id: Ic96cd3cde383f9f0fd9d1a825b99408f8e17f082
|
|
* Onnx parser.
* Async execution interface.
* Shim and support library.
* Arm NN converter
* GpuFsa backend.
Signed-off-by: Colm Donelan <colm.donelan@arm.com>
Change-Id: Ia9adae4da6d9bd2b92a4f4492a022e8337f57f14
|
|
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: I51cb72edf228e669a2be7d79477927ca5c286996
|
|
* Debug layer supported data types updated
* Added deprecation notices in md files to functionalities that will be removed
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: I8673bdc2d596bfa4de751fc95dae010b195ad0b1
|
|
* The abort is caused during destruction of flatbuffers::ClassicLocale
* Set FLATBUFFERS_LOCALE_INDEPENDENT=0 in delegates and parser so that
ClassicLocale is not included
Signed-off-by: Kevin May <kevin.may@arm.com>
Change-Id: I34584b05998a62bae2263a2281414fcf8c12d668
Signed-off-by: Colm Donelan <colm.donelan@arm.com>
|
|
* Doxyfile updated with project number
* Binary paths updated
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: I9976de564110877ace282854a80fb81e7dd0bd67
|
|
* Fix for Neon IsLayerSupported to properly check for multiple Quantization Scales
Signed-off-by: Orlaith Monahan <orlaith.monahan@arm.com>
Change-Id: I9f4558cbd62ce1657adb5025ac16c2b5d69d12b1
|
|
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: I59fe96b0a272fa6984bfc172bf3e110476f3ce7b
|
|
Signed-off-by: Colm Donelan <colm.donelan@arm.com>
Change-Id: I7d1156812c8765ffccd1cc2cabd4f9450f14f676
|
|
Signed-off-by: Colm Donelan <colm.donelan@arm.com>
Change-Id: I8f036370aa87f8aa54316996aafc5baed18ecc2c
|
|
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: I9d14ac309008b3addbd7c8e6c8424f8df9493d7f
|
|
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: Icb5e73d66ebafda162c7ef57ced7402d0aca5950
|
|
* Multi-Dimensional and Batched Scatter Reference and Dataset Implementation
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: I4bd468a25581f32a292d0c1ea80198f39c470ff9
|
|
* Adding serialize-to-armnn parameter to execute network to serialize
the pre-optimized network to a .armnn file and the optimized network
to a .dot file.
Signed-off-by: Colm Donelan <colm.donelan@arm.com>
Change-Id: Ia12cf0b08d36334127264ea3fcc8e64b65f06dae
|
|
* Disable SME2 Gemm kernel selection in case results needs to be accumulated
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: I3d2d096e05f6b294d0393055b574c4f8dbc07c96
|
|
were generated.
* input_<GUID>
* constant_<GUID>
* intermediate<output slot>_<GUID>
* output<output slot>_<GUID>
Input and constant do not need output slot as input layers as well as
constants only have one output slot, therefore with the GUID is enough
to make them unique.
This was the case for constants, but for inputs we were adding the input
slot, which is not needed.
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Signed-off-by: Cathal Corbett <cathal.corbett@arm.com>
Change-Id: I07393fc60f3135337b59a9780aa3a263a995fc9c
|
|
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Signed-off-by: Cathal Corbett <cathal.corbett@arm.com>
Change-Id: I520a9d6cc95faeefaf82947a0547292e869aa523
|
|
* Use ComputeSplitAxis in SplitOperator in tosaCommon mappings
* Fix TosaRef split tests, that were missing outputInfos
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Signed-off-by: Cathal Corbett <cathal.corbett@arm.com>
Change-Id: Ib577eacdc6399242f37d25494e208aa56db6334c
|
|
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Signed-off-by: Cathal Corbett <cathal.corbett@arm.com>
Change-Id: I70f81d17b696c30bf7a06491281184c4ddb8afc1
|
|
* TosaConv2d
* TosaQuantization
* TosaRescale
Signed-off-by: John Mcloughlin <john.mcloughlin@arm.com>
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: I6c7ceca1f7df62896b41a84e6a6448afd8c32b74
|
|
* https://github.com/ARM-software/armnn/pulls
* Bumps version from 10.0.1 to 10.2.0
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: I06844bbf5e725e91712dc33efdc8c39a6f4a1e0c
|
|
Signed-off-by: Colm Donelan <colm.donelan@arm.com>
Change-Id: I75ee45444cd2f7b895e564e78c29fe67c1a8a4fc
|
|
Signed-off-by: Colm Donelan <colm.donelan@arm.com>
Change-Id: Ie2054393188c6099ecee2e09b7008860b9a7178c
|
|
* Added Comparison and LogicalBinary to AddBroadcastReshapeLayer
optimization.
Signed-off-by: Colm Donelan <colm.donelan@arm.com>
Change-Id: I4f4bafb961daf63a733be9a1f17067fd246607ad
|
|
Currently Arm NN will fail to load models containing quantization
scale value of zero.
Signed-off-by: Colm Donelan <colm.donelan@arm.com>
Change-Id: Ifefcee1279b8667da63d1aa7d42e5d44875f9fbe
|
|
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: I36b717455f8c327ae487871ba34a1ea447df2bcf
|
|
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: Icbb8e789a842c355382ec94ffdc0672c6386c059
|
|
* Keep the order of the operators in TosaRef, so that const ops go first
* Remove IsLayerSupportedTosaReferenceConstantUnsupported and open ticket in MLTOSA
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: Ifaa6c26dd8ad7d531f1691320d8c731956b910aa
|
|
* pointing to ACL release_candidate
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: I15852a37ab17fda3dc6d284fcaa2ede7e4958111
|
|
Change-Id: I03c26ab763ec306a6efe31f9b4e0b1c058589bf7
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
|
|
* pointing to ACL release_candidate
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: I70e5bdce18510bb6904a03f4401e20b3a95572c8
|
|
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: I76bffae3d2954dc03448018ba754acd34f3334e4
|
|
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: Id1f3dacb09cfa8542c0821230f0c383ed1c63130
|
|
Adding some human readable information to the "Inferences began" and
"Inferences ended" printouts to make them clearer.
Signed-off-by: Colm Donelan <colm.donelan@arm.com>
Change-Id: I00b2b75a9da19c27fd33574e3bb0b9a1d8e5c5b5
|