Age | Commit message (Collapse) | Author |
|
Signed-off-by: Cathal Corbett <cathal.corbett@arm.com>
Change-Id: I73a47e513fe2d064ef233b121a68ef2edf0396dc
|
|
Signed-off-by: Colm Donelan <colm.donelan@arm.com>
Change-Id: I17823fb8b6bbabc4da327187167ce9582ee29b32
|
|
* Added all data types to TosaRefPreCompiledWorkload::Execute().
* Generalised IsTosaLayerSupported and fixed Addition support.
* Added Fp16 and Int32 Addition End to End tests.
Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com>
Change-Id: I1f89c310ede33615427343e89bcec7e7bb643fa1
|
|
* Create Simple Addition EndtoEnd test
* Create EndToEndTest file in TosaRef/test directory
* Add AdditionEndToEnd test to CpuRef,CpuAcc,GpuAcc,TosaRef
Signed-off-by: Ryan OShea <ryan.oshea3@arm.com>
Change-Id: Ic44e2b457c25dcb41bb3b17c05cce0e74bf17a80
|
|
* Added FP32 support for TOSA Reference Backend.
* Added main block creation to OptimizeSubgraphView, this will only
occur once.
Change-Id: I169dac50b78e2c693da6327962c9f1d3ae3bd712
Signed-off-by: James Conroy <james.conroy@arm.com>
Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com>
|
|
* Added TosaRefBackend::OptimizeSubgraphView implementation.
* Generalised TosaRefLayerSupport::IsLayerSupported to work with any
operator.
* Changed TosaCommon.hpp utils to inline functions.
* Added source files for TosaMappings.hpp and AdditionOperator.hpp.
* Fixed multiple defines issue with HALF_ROUND_STYLE and
HALF_ROUND_TIES_TO_EVEN.
Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com>
Change-Id: Ib2576ec3fb97faa3a2256b2fb93ec16ac8745760
|
|
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: I6a541db9a602609282cc6f33af930ca141b83c41
|
|
* In TF what ArmNN calls quantized data types can be non-quantized as well.
* This patch creates 2 models:
* ArmNN: model where int8 and uint8 will always be quantized, but scale can be 1 and offset 0
* TFLite: model where int8 and uint8 can be quantized and non-quantized
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: Id960f2f30988f2bbec88cb4e0c52c189ac957bae
|
|
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: I2def6995f81d33e68f1ea45d8d19a1e6294049b1
|
|
* half.hpp is now required as an include for numpy_utils.h
* DType_FLOAT was changed to DType_FP32.
* DType_FP16 support has been added to ArmNNToDType utility function.
Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com>
Change-Id: Ib25be9a5abfbd9db2a90b3e42d592259a6df0e01
|
|
Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com>
Change-Id: Ie9aa1aa20a5bc837e005a7a36d4d07b4cd8d021b
|
|
* Modify get_tensorflow.sh to point to the 2.10 Tensorflow tag.
* Modify FindTfLite.cmake to handle the break up of libruy.a
* Modify armnn_delegate.cpp to add registration_external field.
* Prevent the serializer/deserializer from using a system installed
version of flatc.
Signed-off-by: Colm Donelan <colm.donelan@arm.com>
Change-Id: I688f33f387924ba29bf400f60e56f73b2329fdc1
|
|
* Bug fix where files were being overwritten at each debug layer
Signed-off-by: Keith Davis <keith.davis@arm.com>
Change-Id: I609fdc82afcee925824efb02183c7dbc942fced0
|
|
* Add functionality to print output tensors to file in tempdir
* UnitTests
Signed-off-by: Keith Davis <keith.davis@arm.com>
Change-Id: Idfb4c186544187db1fecdfca11c662540f645439
|
|
Signed-off-by: Jim Flynn <jim.flynn@arm.com>
Change-Id: I3573078206272c3a72a2b3acf8781ab458ea6c90
|
|
* Some CL kernels are not run after the first inference and this breaks
the profiler which is expecting a measurement for every kernel each run
* Add a function HasKernelMeasurements() to ascertain if the Event is
returning kernel measurements and if so insert 0.0 values for any missing
kernel measurements.
* Fix ExecuteNetwork to only print a json object after all inferences
have completed
Signed-off-by: Kevin May <kevin.may@arm.com>
Change-Id: I99f2bb0db847f5a52ab4c5705b072155c6b6f333
|
|
* Asserts are removed during a release build, which causes build
failures due to unused variables.
Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com>
Change-Id: Ie36f2bd22f5b2916b03ba7e64c1895fdf21f11f0
|
|
* Fix for Debug mode in ExNet does not work with ConstTensorsAsInputs
* Remove unnecessary assertion with ambiguous message in LoadedNetwork
Signed-off-by: Keith Davis <keith.davis@arm.com>
Change-Id: I9cd5d1f811dbbc89072d1190c510bf1b22e3069c
|
|
* This affects only to the layers (not workloads) Conv, DWConv and FC
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: I66a91ed1a78bc0464e00423c7fc7c28c91d199ce
|
|
param contains a value of -1.
Signed-off-by: Cathal Corbett <cathal.corbett@arm.com>
Change-Id: I538347083e9f22b3f3b6c048aebc2cf5cf4dc786
|
|
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: I1bc3d50b8fa6e216d8b6b7e3421d2ff37a21712c
|
|
* Add a breakdown of the runtime options to the documentation.
* Exclude test classes from Doxygen generation.
* Limit the file extension selection for Doxygen generation.
* Add the support library to be generated.
* Fix some broken markups.
Signed-off-by: Colm Donelan <colm.donelan@arm.com>
Change-Id: I81896f2d7fff503a1d51d6d4ac3876aa8b84118e
|
|
buffer data for Slice operator.
Signed-off-by: Cathal Corbett <cathal.corbett@arm.com>
Change-Id: I86735faf8d57168a63ca6657f281ec03b90f7235
|
|
The subgraphs produced by SubgraphViewSelector were not produced in a
deterministic order, as the order was determined by the pointer values
of some objects, which are not guaranteed to be the same for each
execution.
This patch adds a post-processing sorting step based on the GUIDs of the
layers and the slot indices so that the results will be the same for
each execution.
This makes debugging the optimised graph much easier as subsequent
stages can also be deterministic. It also simplifies some unit tests.
Change-Id: I64f552706b7fb1bf82c19d85a448e054277917bc
Signed-off-by: Rob Hughes <robert.hughes@arm.com>
|
|
* Added files based on RefBackend
* Added PreCompiled Workload skeleton
* Increment ABI version of armnnTestUtils for CreateInput which had
been left as pure virtual, added base implementation for it.
* Add IsTosaLayerSupported() for Addition
Change-Id: I4c963adf3f50593d17ecdf21554502a64ad3bd76
|
|
* Files deleted when Stabilizing the API
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: I0ae73ee36968fa880761c10358bfa827be5fe054
|
|
overridden
Signed-off-by: Cathal Corbett <cathal.corbett@arm.com>
Change-Id: If594e291951a5f9ed1957a19a971c498f6e7843f
|
|
* AddConv and AddDWConv with weights and bias
* ResizeBilinearDescriptor
* b,blacklist option in accuracy tool
!android-nn-driver:8172
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: Ibbc04fd18be7f938b11590bf67cd7af103cb4d99
|
|
* Added armnnTfLiteParser for BatchMatMul
* Added unit testing for parser
* Updated CMakeLists
Signed-off-by: Samuel Yap <samuel.yap@arm.com>
Change-Id: If6842aaf7cf08f688093b714e2ecea6e8cd87161
|
|
* Updated FlatBuffers schema for BatchMatMul layer type
* Added Serializer and Deserializer implementations for BatchMatMul
* Added unit tests for BatchMatMul serialization and deserialization
* Updated CMakeLists and docs
Signed-off-by: Samuel Yap <samuel.yap@arm.com>
Change-Id: Iad63afbd036a3eb648683eb7416a475561aa20cb
|
|
* Added transpose parameters to pre-transpose each input tensor's slices
* Added adjoint parameters to pre-adjoint each input tensor's slices
* Small refactoring (BatchMatMulDescriptor static helpers and BatchMatMulImpl constructor)
* Updated input validation and output shape inference for parameters
* Additional layer unit tests for parameters added
* Versionings incremented
Signed-off-by: Samuel Yap <samuel.yap@arm.com>
Change-Id: Ibe5242a8a5bf604c13de0dc65844fd6c421cc667
|
|
TosaMappings operator.
Signed-off-by: Cathal Corbett <cathal.corbett@arm.com>
Change-Id: Ibea0cf625b3af4ab38e8b985f7a129c983ca9659
|
|
* The previous fix for IVGCVSW-7106 introduced a problem around
operators with multiple inputs and outputs: addSeparator was being
applied to all tensors in the list not just the last one.
Signed-off-by: Colm Donelan <colm.donelan@arm.com>
Change-Id: I0325d9abcb7fb512f834c61686c698bbfc29a3be
|
|
* Move the Conv2D and DepthwiseConv2D validation to Optimization level
when the weights and tensors are as constant inputs
* Take into account offset and scales values when doing INT8 to FP32 dequantization
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: I1f81f15640395ac041923b10dbe9151159715117
|
|
* ProfilingDetails assumed that every workload description included
both tensors and parameters. This is not always the case.
* Modify ProfilingDetails::AddDetailsToString to check the next
element to be printed before deciding to add a separator and new line.
Signed-off-by: Colm Donelan <colm.donelan@arm.com>
Change-Id: I2577b0e8a149d0a172ee12975e18b78238d8256e
|
|
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: Ib91b734d4add47e23ad00f76e53f1873ff617831
|
|
* Adding the check only if it's not a const layer which is needed to run ai_benchmark_v5_yolo_v4_tiny_quant.tflite model
* We still won't be able to run the model due to IVGCVSW-7158
Signed-off-by: Nikhil Raj <nikraj01@e126673.cambridge.arm.com>
Change-Id: Ib7e77a0b5a64be0c92a8e4eae45729f799770b37
|
|
Signed-off-by: Jim Flynn <jim.flynn@arm.com>
Change-Id: I3a3aab7b5042349cb2df8517678306665e037610
|
|
Signed-off-by: Cathal Corbett <cathal.corbett@arm.com>
Change-Id: I5c68b81a67fc2b5a33cf62753351440564bb868e
|
|
* Changed long variable declaration to int
Signed-off-by: Samuel Yap <samuel.yap@arm.com>
Change-Id: I2df6f8f6df8780e48e09f7e68c04626a8a8a207d
|
|
* Added case for Bf16 to switch and changed Assertion to Exception
so it shows up in Release build.
Signed-off-by: Francis Murtagh <francis.murtagh@arm.com>
Change-Id: I817260dc7b7667386c4aa734bea649383866a785
|
|
* Fixed caching issue.
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: Ic7b3e0bd4438b2fd1b3dbfa86b6c89d625bbf9dd
|
|
running Arm NN Unittest
Signed-off-by: Cathal Corbett <cathal.corbett@arm.com>
Change-Id: I567452000287babad345e61ea85ea84f362f48e0
|
|
ConvertLayers.
* ConvertBf16ToFp32Layer
* ConvertFp16ToFp32Layer
* ConvertFp32ToBf16Layer
* ConvertFp32ToFp16Layer
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: I5e763519a12f017dc14b09ea191fdb3b7398c0d7
|
|
* Originated from a GitHub issue: https://github.com/ARM-software/armnn/issues/667
* Initially, Arm NN supports the pool 2D operation because there is no padding
on the pool2d. Neon failure occurs when padding is followed by average pool 2D
due to folding optimization.
* Here we prevent the folding optimization from happening for the above special case
and add it in as a backend specific optimization.
Signed-off-by: Cathal Corbett <cathal.corbett@arm.com>
Change-Id: Ia0fd90c3a6b4b9d29c81106f154617d2e893e26b
|
|
* Correcting some typos
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: Icb21dc4828e51afa38816bd454926fc41e9e82cb
|
|
This reverts commit 1a7f033768acb27da11503bd29abb468d2e77f9e.
List of fixes to be able to add this code again:
* "emplacing_back" the vector inputTensors into the vector m_InputTensorsVec outside the for loop
* GetIOInfo() uses IOptimizedNetwork instead of INetwork, where the infered shapes are not saved
* Add missing data type Signed32 to SetupInputsAndOutputs()
* PrintOutputTensors() prints the actual output without dequantizing
* Add profilingDetailsMethod as input in networkProperties in ArmNNExecutor constructor
* Fix typos
Change-Id: I91de166f87228282db3efa27431fe91458834442
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: Ic6634d48892d11e5f146cdf285e1e333e93e9937
Signed-off-by: Francis Murtagh <francis.murtagh@arm.com>
|
|
* Descriptors added for BatchMatMul
* Layer definition added
* Input validation added (will likely change when opt. param support comes in)
* Ref workload implementation for BatchMatMul added (will also change with opt. param support)
* Ref layer tests made for BatchMatMul
* CMake and other build files updated
Signed-off-by: Samuel Yap <samuel.yap@arm.com>
Change-Id: Ic885301da543ee0fbe7922b85e7f9658c4efc617
|
|
Fp32NetworkToBf16Converter
* Fuse FP32ToBF16Layers with Constant Layer so Conv2d/FullyConnected
can have their weights redirected.
* If BF16 Unsupported in Conv2d || FullyConnected revert fused
Constant Layer to FP32
Change-Id: If523c708a822659d64597d9ae39cca1c2f84b76f
Signed-off-by: Francis Murtagh <francis.murtagh@arm.com>
|
|
* Refactor backend capability checks in LoadedNetwork.
* ImportInputs should check the number of tensors does not exceed the
number of inputs.
* In EnqueueWorkload the check for for the count of input tensors
was ignoring pre-imported inputs.
* Added checks to verify ImportInputs/ImportOutputs worked as expected
in EndToEndTestImpl.
* Improve documentation on ImportInputs/ImportOutputs in IRuntime.hpp.
* Disabled import tests in CL and Neon EndToEndTests that cannot work.
Signed-off-by: Colm Donelan <colm.donelan@arm.com>
Change-Id: Iae4b2644a1c9f01ee72bce1afb211661cc9ae2e3
|