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
|
|
profiling common
!android-nn-driver:5691
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: Ib71af0831e324ac6bd27b1a36f4a6ec1a703b14a
|
|
* Added checks to SerializerStrategy::CreateTensorInfo to handle situations
where a shape has some unspecified dimensions
Signed-off-by: Mike Kelly <mike.kelly@arm.com>
Change-Id: Idc64bfdabd5677c73a5c64f0c8e80156f3aae8e2
|
|
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 support for Signed64 to flatbuffer's schema & updated source tree
* Added support for Signed64 to TFLite Delegate
* Added support for Signed64 to Serializer
* Added support for Signed64 to Deserializer
* Added unit test for ArgMinMax to Deserializer
* Deprecated m_Output_Type from the ArgMinMaxDescriptor: the output type
is solely determined by the DataType of the output Tensor
* Fixed issue where RefArgMinMaxWorkload could output data using
the wrong DataType
* Added Signed64 to RefLayerSupport::IsArgMinMaxSupported as a supported
type
Signed-off-by: Mike Kelly <mike.kelly@arm.com>
Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com>
Change-Id: Ib622c052a1f8aa3e658262f8bde5a6881a8cbe10
|
|
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
|
|
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: Id0c1ce0ae8946bbc061f5c1f7a7798d3033e6ce4
|
|
* excluding our top level readme
Signed-off-by: Jan Eilers <jan.eilers@arm.com>
Change-Id: I45b156c248178a141b8497dcc4d09148b67bf406
|
|
The field m_DimensionsSpecificity in TensorShape was not being serialized
and deserialized following implementation of type 1 dynamic tensors.
* Update schema.
* Add to Serializer and Deserializer.
Signed-off-by: Colm Donelan <Colm.Donelan@arm.com>
Change-Id: I7ddbdaf54c8f4b988c6cb300f90ba848a94bdad0
|
|
Signed-off-by: Jan Eilers <jan.eilers@arm.com>
Signed-off-by: Finn Williams <Finn.Williams@arm.com>
Signed-off-by: Francis Murtagh <francis.murtagh@arm.com>
Change-Id: Id7bc8255a8e3f9e5aac65d510bec8a559bf37246
|
|
* Updated ParseReduce() function in TfLiteParser to read correct axis data
* Remove unused m_TargetWidth and m_TargetHight from ReduceDescriptor
* Updated the ArmNN Serializer Schema
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: I98b6e00ccba1d8ea8c845cb1ae28840e42339629
|
|
* Removes support.md files from all parsers. Lists of supported
operators are now kept in doxygen only
Signed-off-by: Jan Eilers <jan.eilers@arm.com>
Change-Id: I137e03fdd9f41751624bdd0dd25e2db5ef4ef94f
|
|
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>
|
|
* Not using the README.md files directly because it doesn't seem to
be possible to get the content of readme.md combined with the content
of the support.md files in one page
Signed-off-by: Jan Eilers <jan.eilers@arm.com>
Change-Id: I1e5073761f3af8a8d498385f3f7586334e7b29ec
|
|
Signed-off-by: Finn Williams <Finn.Williams@arm.com>
Change-Id: I01c7bd314219e58f71505dcb787d606dbded914a
|
|
* Added generated schema file to the source tree
* Updated the ANdroid.mk file to pick up the Serializer/Deserializer source
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: I12c2bf2ae7aa12374c60e671ff3a97eac5b7f161
|
|
* Adding delegate readme.md and TensorFlowLiteDelegateSupport.md
Change-Id: I1b8012440cf4cd6120902ad69c5b3a2a5e410d71
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
|
|
* 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
|
|
* Replaced with armnn/utility/NumericCast.hpp
* Exclusions in TypeUtils.cpp and QuantizerVisitor.cpp
* Excluded as requires float implementation in NumericCast.hpp
Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com>
Change-Id: I5c4c60e7028e1a51bf9379457278d253fd37bc70
|
|
Change-Id: I3c317e835aba5feafda240393ca26b6aebe8d655
Signed-off-by: Derek Lamberti <derek.lamberti@arm.com>
|
|
* 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
|
|
* 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
|
|
!android-nn-driver:3302
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: Ifbc49acb5272f8a36719bb68676e44817190537d
|
|
Signed-off-by: Keith Davis <keith.davis@arm.com>
Change-Id: Icae26505d0e378ee5ffb3e92b35d78d48b369d2e
|
|
* Added new fill layer
* Added visitor tests
Signed-off-by: Ryan OShea <Ryan.OShea2@arm.com>
Change-Id: Iea677014866b4f2d514004623f59ee83f3c0eef8
Signed-off-by: Keith Davis <keith.davis@arm.com>
|
|
* Added AlignCorners and HalfPixelCenters to Resize and ResizeBilinear
* Updated Serializer and Serializer tests
!android-nn-driver:3280
Signed-off-by: David Monahan <david.monahan@arm.com>
Change-Id: Ice3bb448c239b04323854641525bfe0808c03b2e
|
|
* Add Transpose to SerializerSupport.md
* Remove ResizeBilinear as it is deprecated layer
* Add EXP and SPLIT_V to TensorFlowLiteSupport.md
* Add transpose to TensorFlowSupport.md
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
Change-Id: I05b0411b61c1b74b27b4669e81fa8ce521bb4190
|
|
* Adds serialization/deserilization for QLstm.
* 3 unit tests: basic, layer norm and advanced.
Signed-off-by: James Conroy <james.conroy@arm.com>
Change-Id: I97d825e06b0d4a1257713cdd71ff06afa10d4380
|
|
* Added support for BFloat16 and QAsymmS8 to Serializr.
Signed-off-by: Mike Kelly <mike.kelly@arm.com>
Change-Id: I481af26d5758190ec2e5cd9f9d232d72bcb7acbd
|
|
quantization params
* TensorInfo can have multiple scales and quantization dimension.
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: I0ff02e3766996b6a9da6dc4e92d366bc9505c77d
|
|
* Added new layer QLstm (Android R HAL 1.3)
* Made necessary updates to APIs
* Added unit tests
* This layer is functionally equivalent to the
original unquantized LSTM layer with some
additonal quantization features added. Due
to this, original LstmParams are used for
this layer.
Signed-off-by: James Conroy <james.conroy@arm.com>
Change-Id: I5b7f2d2fb6e17e81573b41a31bc55f49ae79608f
|
|
* Allow per layer quantization from Fp32 to Int8 (QAsymmS8) like TfLite
Signed-off-by: Francis Murtagh <francis.murtagh@arm.com>
Change-Id: I5bbf770aa29d81af3568c15b47d2b2c18e55bb28
|
|
!referencetests:229377
Signed-off-by: Jan Eilers <jan.eilers@arm.com>
Change-Id: Ia9b360b4a057fe7bbce5b268092627c09a0dba82
|
|
* Add a new Activiation type of HardSwish.
* Add CpuRef support and tests.
Signed-off-by: Colm Donelan <Colm.Donelan@arm.com>
Change-Id: I68c3840aa45b7a27d5e416a5d50fe8f99f003ce8
|
|
* Added TransposeLayer
* Added CL, Neon and Ref Workloads
* Added Transpose utilities
* Added Serializer and Deserializer support
* Added Quantizer support
Signed-off-by: Mike Kelly <mike.kelly@arm.com>
Change-Id: I04c755ba7cb5b1edf72b3c9f3c0314878032e3c7
|
|
* Added CpuRef implementation
* Added Unit Tests
* Added Quantizer Test
* Enabled Tests for Neon and CL backends on fp32 only
* Added to Serializer
Signed-off-by: David Monahan <david.monahan@arm.com>
Change-Id: Ic23e1797dbc9352b40678c389d7fe2b836b582ea
|
|
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: I416b39b0adac1410f854d3ec5b855044bd85e1cc
|
|
Signed-off-by: Jung Tae-young tee.ty.jung@openedges.com
Signed-off-by: Matteo Martincigh <matteo.martincigh@arm.com>
Change-Id: I25ceeca70e72fad88ab039aed5a5ab6a7cc08c6c
Signed-off-by: Derek Lamberti <derek.lamberti@arm.com>
|
|
* Added new layer named ElementwiseUnary
* Deprecated existing Abs/Rsqrt layer functions
* Updated existing Abs/Rsqrt test infrastructure to use new layer
* Added boilerplate for new Exp,Neg,Sqrt elemwise op layers
* AbsQuantize test removed pending future commit
* Serialization support added
!android-nn-driver:2550
Change-Id: Ic595c645925e17b45db568187fd05646daf2e87f
Signed-off-by: josh minor <josh.minor@arm.com>
|
|
Also remove it from armnnSerializer and armnnUtils.
In general code within Arm NN should only include exactly what it needs.
This will help keep compile times down, and reduces the need for a
complete rebuild when anything in the public headers changes.
ArmNN.hpp should only be provided as a convenience for user code where the
user doesn't know enough of the API to decide which specific headers
they need.
Signed-off-by: Matthew Bentham <Matthew.Bentham@arm.com>
Change-Id: I4ffcaa7662af4f88a1babf2bf17d03da6f77d665
|
|
!android-nn-driver:2572
Change-Id: I8fe52ceb09987b3d05c539409510f535165455cc
Signed-off-by: Derek Lamberti <derek.lamberti@arm.com>
|
|
Change-Id: Icb1b35ff55fa22103777853e6f49fc282d61750d
Signed-off-by: Derek Lamberti <derek.lamberti@arm.com>
|
|
* Refactoring to enable ProfilingGuid
* Add profiling includes to Android.mk
Signed-off-by: Jan Eilers <jan.eilers@arm.com>
Change-Id: Ieb25e15e3dc302eb42817d824ad8411ac76dcfe8
|
|
* Added test SerializeResizeBilinear to ensure that ResizeBilinear
layers are serialized as Resize layers
* Added test EnsureResizeBilinearBackwardCompatibility to ensure
the Deserializer is still able to deserialize an old binary that
contains a ResizeBilinear layer and that it creates the correct
equivalent Resize layer from it
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com>
Change-Id: If227c5f1f3d027dff7d8f306dee97fd488755a72
|
|
NELSTMLayerQuantized in ACL
Change-Id: I663874da474722a191e55f6c7f6bc127a72fc485
Signed-off-by: alanhsu5678 <gg9662558@gapp.nthu.edu.tw>
Signed-off-by: Matteo Martincigh <matteo.martincigh@arm.com>
|
|
Signed-off-by: Jung Tae-young <naey05@gmail.com>
Change-Id: Ie3958c25fae752a8ec010ff6c77e4b625dec1f68
|
|
* Change C-style arrays to vectors and simplify string
construction
* Leave whitespace after comma in initializer list
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com>
Change-Id: I3adddae61e79cbcd878d13532d4199fc2581a328
|
|
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com>
Change-Id: I2017c15b485b82437c6ffdac4d3112bcc2cbe9e9
|