Age | Commit message (Collapse) | Author |
|
* Added Implementation of the Tile Operator Workload to Neon
* Added calls to the existing unittests
* Added Documentation
Signed-off-by: David Monahan <david.monahan@arm.com>
Change-Id: I0030ffe514215c79f5629d20671254dde9bec452
|
|
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: I752a77b58006c733309e649e050cea38cd295626
|
|
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: Ic2c3a89b89f44f111e5a184c83db89ea1cb52976
|
|
* create implementation header
* add copyright notice
* add pragma once and anonymous namespace
* create network function declaration
* complete body of network function
* create end-to-end function declaration
* complete body of end-to-end function
* add references to tests for supported data types
Signed-off-by: Declan-ARM <decmce01@arm.com>
Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com>
Change-Id: I376e48efd8b6ca9e0e0b05b516be599c0acdbd16
|
|
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: Ide1a4a5bdff5bad369fd810be1b661539ed853ef
|
|
* Fix error in InferOutputShapes
Signed-off-by: Cian McGriskin <cian.mcgriskin@arm.com>
Change-Id: I1b38285d82d22715c6502dc63b7bab981e3258e4
|
|
* Added parsing functions to the serializer and deserializer
* Added Tile and its Descriptor to the ArmnnSchema.fbs
* Added a Unittest
Signed-off-by: David Monahan <david.monahan@arm.com>
Change-Id: I72e638d26038c9b118cd82f633af462fd19e2b34
|
|
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Signed-off-by: Cian McGriskin <cian.mcgriskin@arm.com>
Change-Id: I0afb2403fee11c5c1e58ea65e2525e99594d8f2d
|
|
* On Neon we cannot remove a Reshape if it's connected to a
SplitterLayer.
* Removed clause 5 in SplitterLayer which could erroneously prevent
the use of Subtensors in certain circumstances.
Signed-off-by: Mike Kelly <mike.kelly@arm.com>
Change-Id: I437eb5d3ede25329a4d11d12c3fb1aec2e76efb6
Signed-off-by: Mike Kelly <mike.kelly@arm.com>
|
|
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: Ia96c3bd9b7fd78bfdbf74476f0bb943735bd6694
|
|
* Follow up review to clean up whitespace and copyright errors mentioned
in https://review.mlplatform.org/c/ml/armnn/+/9885
* Added BinaryElementwiseOperation to .dot files
* Refactored ConnectedToSplitterWithMoreThan4Dims function to more
generally useful ConnectedToLayerType function
Signed-off-by: Mike Kelly <mike.kelly@arm.com>
Change-Id: I0e3d0895888f3a3f0a9758ce30bc031aba50812b
|
|
* Fix failing CTS test
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: I044ea654c63c511ac47bb720004e95703402b645
|
|
* There's currently a problem with using a non const bias value in
CLConvolution2d. We will block it for the moment.
Change-Id: Iedccea44931a8826e2c1b295bbc46592d8ac3ef8
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
|
|
* There's currently a problem with using a non const bias value in
NeonDepthwiseConvolution. We will block it for the moment.
Signed-off-by: Colm Donelan <colm.donelan@arm.com>
Change-Id: Ifd206cfd25a2305a80f8b0a88e07747e79468d18
|
|
* There's currently a problem with using a non const bias value in
NeonConvolution2d. We will block it for the moment.
Signed-off-by: Colm Donelan <colm.donelan@arm.com>
Change-Id: Ia020cf48f7d5e0642f7763e82501f06ad89945d8
|
|
* Adding support for ReverseV2 in the classic and opaque delegates
* CMake files updated
* Tests added
* Gpu/Cpu Acc tests compiled out until functionality is written
Signed-off-by: Tracy Narine <tracy.narine@arm.com>
Change-Id: I8b41b7e71f2e28e5ea8dddbd00657900e6d7ab9a
|
|
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: Ibabb80f2ece0e0ad2314ebb45fea051667b82b8d
|
|
* Added check to ensure that Reshapes are not removed on Neon if they are
before or after a SplitterLayer and have more than 4 dimensions.
* Moved NCHW check to a function to reduce clutter.
Signed-off-by: Mike Kelly <mike.kelly@arm.com>
Change-Id: I45d97634484e8dc0ca7675c23481caf84eb3fe90
|
|
* This updates checks in pyarmnn to new version
* Updates documents to newer version
Change-Id: If1321ea4e74a10993b205cce1d3618844b0ddc06
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
|
|
* The SplitterLayer did not use the Overridden TensorInfos when
calculating whether or not to use SubTensors.
Signed-off-by: Mike Kelly <mike.kelly@arm.com>
Change-Id: I675b27c546c6ed720c76f4b9d868ebe32f914c70
|
|
Layer with 2 inputs
* Changing ReverseV2 to use two inputs
* This is required by the backends
* The ReverseV2Descriptor was removed
* Tests updated
* Added a Run<> templatefor inputs with different data types
Signed-off-by: Tracy Narine <tracy.narine@arm.com>
Change-Id: I22f947de829b4b3da6bda3a74f4ffdef4052cc25
|
|
* We updated Arm NN version in https://review.mlplatform.org/c/ml/armnn/+/9885
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: I37e771be66ca7b907b08648a6bb07de4f0036ae3
|
|
* Added optimization to remove reshapes for Neon and Ref Backends
by using overridden TensorInfos
* Added ability to delete Subgraphs during Optimization
* Fixed naming error in NeonEndToEndTests and CLEndToEndTests
* Added LayerNameAndTypeCheck for testing.
* Fixed error where layers were not marked as altered when removed in
CLBackend
Signed-off-by: Mike Kelly <mike.kelly@arm.com>
Change-Id: I1ac25cd4ec9821470d961831ae2c8d24882276cc
|
|
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: I5760da9be2ed63fdfbdd5d3d7b771c310592798d
|
|
* Refactor all functions to convert Add, Div, Maximum, Minimum, Mul
and Sub to use ElementwiseBinary layers instead
* Add POW Operation support
* Add REDUCE_PROD Operation support
Signed-off-by: Kevin May <kevin.may@arm.com>
Change-Id: I8c91980e585f7ff2561610084e7c6b48fb278171
|
|
* Check to round to closest finite FP16 value when convert FP32 to FP16
* Unit tests to be added
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
Change-Id: If3b982ff3030379ac33c47d4be13edb0bda679f6
|
|
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: I59c7fd0127650d2e675dc7e315f81ca296286667
|
|
* Remove warning on constant layer optimization being run on layer without
constant tensor
* Remove warning on bias quantization scale not being equal to
(InputScale x WeightScale)
Signed-off-by: Ryan OShea <ryan.oshea3@arm.com>
Change-Id: I87e97127dc0fd45812bfada1c7dfcc3d5f5cdecc
|
|
* Add Reshape layers before and after to extend support for 3D tensors, as ACL only supports 4D tensors for those layers
* Add Unit Tests
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: I4431185ce3a3b2f595d2a79bdda7095212d1c52d
|
|
* Support for ReverseV2 for the serializer and deserializer added
* Tests added
* CMake files updated for the build
* Fixed an issue with the operator_list documentation for Resize and ReverseV2
Signed-off-by: Tracy Narine <tracy.narine@arm.com>
Change-Id: If396f55ecdd763d6f91c51707809f4bd58715cec
|
|
* Fix for 2 VTS tests named CacheSavingAndRetrievalNonZeroOffset
Signed-off-by: Kevin May <kevin.may@arm.com>
Change-Id: Id8e02b6383be5706311583aab3f507b5bb43c0bb
|
|
Signed-off-by: Kevin May <kevin.may@arm.com>
Change-Id: I17e49ee167a208d9810eedbb0d3a220b66d34aa7
|
|
Signed-off-by: David Monahan <david.monahan@arm.com>
Change-Id: I4c464797d80f7c2ad21429838c07d4e5e34308f6
|
|
* Added ReverseV2 support to TFLite Parser
* Added ReverseV2 TFLite Parser unit tests
* Updated Parser Docs
Signed-off-by: Tianle Cheng <tianle.cheng@arm.com>
Change-Id: Idb9a9213f75cd6cf01509a5d06ea5772cf56ac5b
|
|
Even though we're using C++ 17 we still do a Debian buster build. This
prevents using some new libraries. In this case std::filesystem.
Change-Id: Icbdcac8a53d5931f25f8aa77c7422aa0b8ae94d4
Signed-off-by: Francis Murtagh <francis.murtagh@arm.com>
|
|
* Descriptors added for ReverseV2
* Layer definition added
* Input validation added
* Reference workload implementation for ReverseV2 added
* Reference layer unit tests made for ReverseV2
* CompareTensors method updated to support comparison between empty tensors
* CMake and other build files updated
Signed-off-by: Tianle Cheng <tianle.cheng@arm.com>
Change-Id: I805738454421309fda77c44218a8df171d68dc18
|
|
Even though we're using C++ 17 we still do a Debian buster build. This
prevents using some new libraries. In this case std::filesystem.
Signed-off-by: Colm Donelan <colm.donelan@arm.com>
Change-Id: Icdf3460cb5dd0e3ed2f07fccc5b89bd8975d488d
|
|
* Updated calls to use the new function
From:
GetInputSlot(n).GetConnection()->GetTensorInfo();
To:
GetInputSlot(n).GetTensorInfo();
* Added UnitTests
Signed-off-by: Mike Kelly <mike.kelly@arm.com>
Change-Id: I43184cc05e4472011b9347aaa820eb8deb1cd4a0
|
|
working with `-T delegate` flag
* Removed original SetInternalProfilingParams
* Added Undefined Profiling DetailsMethod for delegateOptions
* Replaced with if / else block to handle DetailsOnly and DetailsWithEvents
Signed-off-by: Declan-ARM <decmce01@arm.com>
Change-Id: Id0c91892732c5c6b59696a43c6a73a22cbfffa09
|
|
* Implement the "-C" command line option of executenetwork.
* Add a FileComparisonExecutorFile which will read tensors from
a previously written text file and compare them to the execution
output.
Signed-off-by: Colm Donelan <colm.donelan@arm.com>
Change-Id: I8380fd263028af13d65a67fb6afd89626d1b07b8
|
|
* this line is used earlier to initialize subgraphPtr
Signed-off-by: Francis Murtagh <francis.murtagh@arm.com>
Change-Id: Iff24da2acab33e59460455977e221066973532a2
|
|
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
Change-Id: I89dd22298eb2fd12dd2d146200ac4ed7a0d3dfe7
|
|
* Download CMake 3.19 before building Flatbuffers
Signed-off-by: John Mcloughlin <john.mcloughlin@arm.com>
Change-Id: Ib7e897e3d4a5636e5e14a7bf3c593efa7982c4e2
|
|
* activationInfo passed in directly to configure() rather than part of matMulInfo
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: I546def1c1e1cabaf50629f7d78ae0ba459766ed4
|
|
If you pass a file name without an extension as the -m parameter to
execute network it won't be able to determine the parser to use. This
results in a segmentation fault.
Signed-off-by: Colm Donelan <colm.donelan@arm.com>
Change-Id: I91821a5abd50b65b8d60409aa9a807013e0b0e6a
|
|
* Removed Ubuntu 18.04 check for CMake 3.19 install
Signed-off-by: John Mcloughlin <john.mcloughlin@arm.com>
Change-Id: Ie1ffab5cc967849188e0684c7086296710d6d731
|
|
in CpuRef
* Both layers were assuming 4D tensors, now 3D is supported too.
* Remove some unnecessary includes
* Add Unit Tests
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: I7bdd11e4936a27cd97ec65fd915e6ccaa1494cff
|
|
* Currently Doxygen was failing with error XML Parsing Error: duplicate attribute
in main. This is due to an obsolete align attribute
* Fixed some minor warnings by closing the Third part tools table
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: I08a0d734ee07aef6617aa23c6fbbc05fb20bdfe5
|
|
Signed-off-by: Francis Murtagh <francis.murtagh@arm.com>
Change-Id: I3f2bc1afc9873ed111b756717b2e86acce268598
|
|
* This commit fixes partially the ticket.
In ToTensorInfo() we assume batch is 1 when it is unknown.
We call OutputTensorInfoFromInputs() to amend this assumption/
However, this does not work for reshape layer.
Therefore, we have to calculate the output shape in the ParseExpandDims().
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: Iedc32a44b4ec0d8b7d2cc0b08f38f0776402f7bd
|