Age | Commit message (Collapse) | Author |
|
* Ref workload
* Cl workload
* Neon workload
* Serializer
* Deserializer
* Remove boost include from TensorTest.cpp
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: I498548169cc77609c55cf3105f1de5a7429772cf
|
|
* This change is necessary because tflite uses a [1,H,W,I*M] format
and uses the I*M dimension for per axis quantization. Our previous
layout [M,I,H,W] can't handle the correlating quantization scales.
* Updates Onnx-, TfLiteParser and TfliteDelegate
* Updates the CpuRef, CpuAcc and GpuAcc backends
* Adjusts unit tests
* Adds test to ensure models with old layout can still be read and
executed
* Adds conversion function to previous layout [1,H,W,I*M] --> [M,I,H,W]
which can be used by backend developers
!android-nn-driver:5553
Signed-off-by: Jan Eilers <jan.eilers@arm.com>
Change-Id: Ifef23368b8c3702cf315a5838d214f7dc13c0152
|
|
* Used doctest in ArmNN unit tests
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: Ia9cf5fc72775878885c5f864abf2c56b3a935f1a
|
|
* Replaced all instances of boost::multi_array with flat vectors.
* Updated LayerTestResult struct with new member variables.
* Updated CompareTensor function to compare flat vectors and the shape.
* Removed MakeTensor function from TensorHelpers.hpp.
* Removed GetTensorShapeAsArray function from LayerTestResult.hpp.
* Removed boost::array usage.
* Removed boost::extents usages.
* Removed boost::random usages.
Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com>
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: Iccde9d6640b534940292ff048fb80c00b38c4743
|
|
* Remove concurrent flag from ExecuteNetwork as it is possible
to deduce if SimultaneousIterations > 1
* Add void RunAsync()
* Refactor some unit tests
Change-Id: I7021d4821b0e460470908294cbd9462850e8b361
Signed-off-by: Keith Davis <keith.davis@arm.com>
Signed-off-by: Kevin May <kevin.may@arm.com>
|
|
Signed-off-by: Colm Donelan <Colm.Donelan@arm.com>
Change-Id: Ic0a2e62e3808caf89ee429ec184d947a04340248
|
|
Signed-off-by: Keith Davis <keith.davis@arm.com>
Change-Id: Icc0d131c8ee2e9748e2f14762a75962b39c10f9d
|
|
* Generalises ConstCpuTensorHandle and inherited
classes by removing 'Cpu' from aliases.
* New renamed classes: ConstTensorHandle, TensorHandle,
ScopedTensorHandle, PassthroughTensorHandle,
ConstPassthroughTensorHandle.
Signed-off-by: James Conroy <james.conroy@arm.com>
Change-Id: I1824e0e134202735fb77051f20a7252f161dfe16
|
|
* Add new class ManagedConstTensorHandle to Unmap when out of scope
* Integrate into existing layers that have constants
* Add unit tests
Signed-off-by: Francis Murtagh <francis.murtagh@arm.com>
Change-Id: I0a05e14e438804b37e9862e76b5ca329483f6b45
|
|
* Added multithreaded StridedSliceEndToEndTest
Signed-off-by: Finn Williams <Finn.Williams@arm.com>
Change-Id: I4579db7b5959e0a22256f1bda00238c22e611dec
|
|
IVGCVSW-5415 Add TfLiteParser support for CAST
* Added front end support for CAST, including support in the
Reference workload, Serialization, Deserializtion, Unit tests, and
TfLiteParser.
Signed-off-by: mathad01 <matthew.haddon@arm.com>
Change-Id: Iaf670ca5912a21ed6bc84f7f83a68b42154846bb
|
|
* Added thread safe execution mechanism for armnn
* Removed duplicate function bool Compare(T a, T b, float tolerance)
* Added StridedSliceAsyncEndToEndTest
* Fixed memory leak
Signed-off-by: Mike Kelly <mike.kelly@arm.com>
Change-Id: I2d367fc77ee7c01b8953138543e76af5e691211f
|
|
TfLiteDelegate support for FullyConnected Operator'
* Added front-end support for non-const weights for FULLY_CONNECTED operator
* Added FULLY_CONNECTED end-to-end test
* Updated FULLY_CONNECTED operator support in TfLite Arm NN Delegate for non-const weights
* Updated the version numbers
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: Iffa5b9aa9297aca4c02d923cce4636c88ac21faa
|
|
Debug layers are given names based on the layer they take their input from.
If a layer has multiple outputs then one debug layer will be attached to
each output. Therefore all these debug layers would have identical names
making them hard to distinguish when debugging. This patch includes the
output slot index which the debug layer takes its input from when creating
the name.
Change-Id: I09eaa8a7edad9bfdf678b4778cf740340013126c
Signed-off-by: Rob Hughes <robert.hughes@arm.com>
|
|
!android-nn-driver:5042
Signed-off-by: Kevin May <kevin.may@arm.com>
Change-Id: Ia1ce8b839e81b46428ba0f78463e085e5906958d
Signed-off-by: Francis Murtagh <francis.murtagh@arm.com>
Signed-off-by: Finn Williams <Finn.Williams@arm.com>
|
|
* Added TfLiteParser support for REDUCE_MIN and REDUCE_MAX operators
* Added ACL workloads support for REDUCE_MIN, REDUCE_MAX, and REDUCE_SUM operators
* Added TfLite Delegate support for REDUCE_MIN, REDUCE_MAX, and REDUCE_SUM operators
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: I8085d59946bfd4ab78a59a61f899031ae53371a8
|
|
Signed-off-by: Kevin May <kevin.may@arm.com>
Change-Id: I52448938735b2aa678c47e0f3061c87fa0c693b1
|
|
This patch addes ReduceSum operation support for reference backend,
which computes the sum of elements across dimensions of a tensor.
Changelog v1:
- Fix file header descriptions.
Chagelog v2:
- Fix line limit issue.
- Fix type conversion issue.
Changelog v3:
- Remove tabs.
- Modify newly added file headers.
Changelog v4:
- Symbol on header isn't allowed so drop it from newly added file headers.
Changelog v5:
- Remove tabs, fix the use of brackets and align lines correctly.
Changelog v6:
- Add serializer and deserializer support.
Changelog v7:
- Fix build error add missed code.
Changelog v8:
- Rename ReduceSumDecriptor to ReduceDescriptor
- Update m_KeepDims field data type to bool on ReduceDescriptor
- Add ReduceOperation field to ReduceDescriptor
- Rename ReduceSumLayer to ReduceLayer
- Update ReduceLayer to use ReduceDescriptor
- Update ReduceLayer::ValidateTensorShapesFromInputs() function
- Rename RefReduceSumWokload to RefReduceWorkload
- Update workload to use ReduceDescriptor
- Update workload to use Decoders and Encoders
- Remove ReduceSum.hpp and ReduceSum.cpp
- Added Reduce.hpp and Reduce.cpp
- Move Mean.cpp (which is implementing REDUCE_MEAN) functionality to Reduce.cpp
- Update RefMeanWorkload to call Reduce function with ReduceOperation::Mean argument
- Remove Mean.hpp and Mean.cpp
- Update the Serializer/Deserializer ArmnnSchema.fbs for ReduceLayer, ReduceDescriptor, and ReduceOperation
- Update Serializer and Deserializer for serializing/parsing ReduceLayer
- Added TfLiter parser Sum test for REDUCE_SUM operator
- Make corresponding changes on front-end and Ref backend to support REDUCE_SUM operator
Changelog v9:
- Fixed build errors.
Change-Id: I8c8e034f3df73f9565b3c18eff51ecca6c542195
Signed-off-by: Inki Dae <inki.dae@samsung.com>
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
|
|
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
Change-Id: I85f0c30757043f8c27c78d607f0f9dbbdd35b9fb
|
|
* Add Boolean support for Reshape
* Use LogicalUnary factory and data type for LogicalNot
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
Change-Id: I8e072fde200b7716556ae67f79616458cf98ff20
|
|
* Add frontend and reference implementation for logical
ops NOT, AND, OR.
* Unary NOT uses existing ElementwiseUnary layer and
ElementwiseUnary descriptor.
* Binary AND/OR uses new layer LogicalBinary and new
LogicalBinary descriptor.
* Add serialization/deserializion support and add missing
ElementwiseUnary deserializer code.
* Add additional Boolean decoder in BaseIterator.hpp.
Signed-off-by: James Conroy <james.conroy@arm.com>
Change-Id: Id343b01174053a166de1b98b6175e04a5065f720
|
|
Signed-off-by: Keith Davis <keith.davis@arm.com>
Change-Id: I0a07dea96a86849701ba387dbea148909a6d729b
|
|
This patch adds int32 and int64 ArgMax op support.
Current ARMNN already has ArgMax op but not used, and
it doesn't support int64 output type.
So this patch adds a new type, Signed64, and also adds
ArgMinMax computation function for int64 type support.
In default, output tensor type of ArgMax op is int64 in case of
tensorflow lite model so this patch makes a proper function - ArgMax op
for int64 or int32 - to be called according to parsed output_type value.
With this patch, ARMNN supports both types - int64 and int32 - for
ArgMinMax op.
Changelog v1:
- Check if output data type of ArgMinMax op is valid or not.
- Use template function to support int32 and int64 types of ArgMinMax function.
- Keep using Signed32 as default data type of m_Output_Type.
Change-Id: I7a8e7e38dd9e5acc81464571d8b4d51378fc7f14
Signed-off-by: Inki Dae <inki.dae@samsung.com>
|
|
the tests for layers Q,R & T
Signed-off-by: Finn Williams <Finn.Williams@arm.com>
Change-Id: I6fc613d31785298a0b7ed18f1abdd59bafed1e8e
|
|
NO_DEPRECATE_WARN
* Done for all elementwise layers, Activation, BatchNorm, BatchToSpace
Signed-off-by: Keith Davis <keith.davis@arm.com>
Change-Id: Id1d15a0960233026aecf7a07e0d3f006e07e4abf
|
|
the tests for layers M-P
Signed-off-by: Finn Williams <Finn.Williams@arm.com>
Change-Id: I324eee7d750e30f714e0d346b7da7b69866ff935
|
|
the tests for layers between G-L
Signed-off-by: Finn Williams <Finn.Williams@arm.com>
Change-Id: I197351a479fb211787bd12a73c9618d2ded95898
|
|
for all layers between C-D
Signed-off-by: Keith Davis <keith.davis@arm.com>
Change-Id: I9583adf50e67e63e73833f400d1c50fbff57f60c
|
|
* Refactored Floor and FullyConnected tests
Signed-off-by: Finn Williams <Finn.Williams@arm.com>
Change-Id: Iad87254e638bdcb5d7b334b16ec87a0c981e48a0
|
|
* Re-factored SplaceToDepth, Splitter, Stack and StridedSlice unit tests
to use TensorHandleFactory for creating TensorHandles
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: Ib22bb09cd2120c02c548099eaa06db6e6f00b15e
|
|
* Re-factored SoftmaxTestImpl to use TensorHandleFactory to create TensorHandles
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: I83559a89187bbed0d6f34ca589ea81c694bf5683
|
|
* Re-factored SpaceToBatchNd tests to use TensorHandleFactory to create TensorHandles
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: I096a6e30ecc97dd9b93b206157f16d912085703c
|
|
* Refactored ArgMinMax tests to use TensorHandleFactory instead of WorkloadFactory
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: Ibff0f9370972f9a0a977c05275cb6168f8f88ae5
|
|
* Added new test function to pass in the ITensorHandleFactory
Signed-off-by: Finn Williams <Finn.Williams@arm.com>
Change-Id: I9b2e9250200e092541e29796ec53cabd0b677acf
|
|
* Added functionality to query if TensorHandleFactory supports InPlaceComputation
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: Icf5bfc5f999fc5d03681dcb8cec88d921842458b
|
|
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: Iea9cc3a36021aac4b86ea5d8340dd8eb1f308283
|
|
* Remove default arguments in Neon and CL causing ambiguity
Signed-off-by: Francis Murtagh <francis.murtagh@arm.com>
Change-Id: I314885719a16311b68c7bda37cd54b2ca0d14480
|
|
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: I7e4c752f396833e226d73c3569e195b796fbf482
|
|
* Input layer to be int32 instead of same type as output
* Enable float16 end to end tests
* Neon and Cl layer support check for backend
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: I6bc889077c8da63eeff66bd45730ce5d8783c419
|
|
* Remove QSymm16 support for Floor to match NNApi and disable RefLayerTest
* Return nullptr for floor workload if quantized type
* Fix SimpleAbsTest incorrect output
Signed-off-by: Francis Murtagh <francis.murtagh@arm.com>
Change-Id: I80d9e2fb78777d0a3fc7ce6d12b5eb4af3fd1d3a
|
|
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: Ia8f237a2500986e01843defb75787694a20ba24c
|
|
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: Ic89bcbbd580abe1b05bd26748db704e83cf65bea
|
|
*Add more UnitTests to the reference implemenation.
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: Idbce68baa76b049e5f741f790a5cfd75acb54a95
|
|
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
Change-Id: Ie8acb9c729af4f95488aecf795f45ff12364f9ca
|
|
Signed-off-by: Jan Eilers <jan.eilers@arm.com>
Change-Id: Id9446c30f6a31c5064bab08b40805e463700072c
|
|
* Add Rank front end
* Add Rank reference implementation
* Add Rank serialization support
* Add Scalar serialization support
Signed-off-by: Finn Williams <Finn.Williams@arm.com>
Change-Id: I06e4a468c2a84e79bae2e6c5348596bbbf853b4b
|
|
Signed-off-by: Finn Williams <Finn.Williams@arm.com>
Change-Id: I6592169b74ac4294bc09647879aec0718c641f91
|
|
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
Change-Id: Ideaae5280702aae6c73f3b4e4cee9f71a8386fda
|
|
* Add CL workload for Fill Operator
* Enabled Fill operator tests on CL
* CLFill function does not have validate() function yet
IsLayerSupported() function return true at the moment
* Enabled int32 to tests on backends
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: I9f8cc6d1c86f832ba46a8d170572f4cfcde9ab17
|
|
* Added AlignCorners and HalfPixelCenters Parameters to Resize
* Added Unit Tests
Signed-off-by: David Monahan <david.monahan@arm.com>
Change-Id: I83420a9bcb7beec9073d201448f64eb53090e1f1
|