aboutsummaryrefslogtreecommitdiff
AgeCommit message (Collapse)Author
2021-03-03IVGCVSW-5612 Fix tiny_wav2letter_relu_fixed_int8 delegate outputexperimental/abi-testsFinn Williams
* fix delegate perchannel quantization * change delegate to check reshape options before inputs * Add int8 "qsymms8" option to ExecuteNetwork * Add option to run ExecuteNetwork on tflite w/o delegate !referencetests:301301 Signed-off-by: Finn Williams <Finn.Williams@arm.com> Change-Id: If3e12599b17aff1199d7ab0a55e1c901e480083d
2021-03-03Point readme files to latest doxygen documentationJan Eilers
* excluding our top level readme Signed-off-by: Jan Eilers <jan.eilers@arm.com> Change-Id: I45b156c248178a141b8497dcc4d09148b67bf406
2021-03-03armnn_tfl_benchmark: Fix crashKeith Mok
The input tensor data pointer was passed incorrectly Signed-off-by: Keith Mok <ek9852@gmail.com> Change-Id: I03f872c57ec588fde0f7d444c80b38823ea4f9b4
2021-03-02Update ACL pin to b1ff7f7baafeba0443bd460793c60b1ce40a405fTeresa Charlin
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: I8e617a6b67cb7188e389146875e41fe15542143b
2021-03-02Update ACL pin to 1055dc14c7812ea322947e5b4a0733fb7b206715Teresa Charlin
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: I79694713bf67bccc61c376d439333c096448e258
2021-03-01Make SubgraphViewSelector give deterministic resultsRob Hughes
The subgraphs produced by SubgraphViewSelector were not deterministic as the order of the input slots, outputs slots and layers within each subgraph were determined by the pointer values of those 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. Change-Id: Ifbcb199733066f99e9f95808a8da22023e5944f1 Signed-off-by: Rob Hughes <robert.hughes@arm.com>
2021-02-25This application allow to benchmark tflite models by providing average ↵Jim Flynn
inference time. Usage: armnn_tfl_benchmark -m <model .tflite> -m --model_file <.tflite file path>: .tflite model to be executed -b --backend <device>: preferred backend device to run layers on by default. Possible choices: CpuAcc, CpuRef -l --loops <int>: provide the number of time the inference will be executed (by default nb_loops=1) Signed-off-by: Vincent ABRIOU <vincent.abriou@st.com> Signed-off-by: Jim Flynn <jim.flynn@arm.com> Change-Id: Ia26fafd4f382f0ad03856436dcae6e71b5abbd26
2021-02-25IVGCVSW-5401 Implement the FILL operatorSadik Armagan
* Added FILL operator to TfLite ArmNN Delegate * Added unit tests Signed-off-by: David Monahan <david.monahan@arm.com> Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: I335ef469ff773fa4305eb87f6e93ae9c03fc6997
2021-02-23MLECO-1253: update ASR example python appNina Drozd
* add link to new wav2letter model from ModelZoo in Readme * update model input size * update to match new model's output Signed-off-by: Nina Drozd <nina.drozd@arm.com> Change-Id: I8e85d025610a458e9ae7be93fd7179c71bac5b18
2021-02-22MLCE-356 'Documentation issue on CrossCompilation guide'Francis Murtagh
* Add updates for Boost, Caffe and TF parsers * Update path Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: Ice9e5393ab47a678b5fe7c1ba4070460ef5b473c Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
2021-02-22Minor doc updatesNikhil Raj
* Updating README * Updating android ndk build guide Change-Id: I09f5e4fe09d590b6b482800730b78cbc84cee9e9 Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
2021-02-22IVGCVSW-5695 Update supported operatorsJan Eilers
* Update supported operators for the delegate, parsers, serializer and deserializer Signed-off-by: Jan Eilers <jan.eilers@arm.com> Change-Id: I33ac99a29d894eec055cd05411014075d78b3168
2021-02-19IVGCVSW-5682 Add Deprecation NotificationJan Eilers
* For Quantizer, Tensorflow Parser and Caffe Parser Signed-off-by: Jan Eilers <jan.eilers@arm.com> Change-Id: If30daa54947c417c0d700f11e630546b1745b72e
2021-02-19Give unique names to debug layersRob Hughes
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>
2021-02-19Fix TransformIterator operator=Rob Hughes
These two operator overloads were giving compile errors as they had misspelled the names of the member variables. Presumably they are not used in any of the code and not tested anywhere, and so the compilers being used on the CI decided to not report this error. I encountered this error using the MSVC compiler, but it may cause problems on others too. Change-Id: I200fc98dbd024d13dbf0e2eca2a0dcd2b0bef261 Signed-off-by: Rob Hughes <robert.hughes@arm.com>
2021-02-18Remove unnecessary friend functionRob Hughes
IOptimizedNetwork declares a friend function (CreatePreCompiledWorkloadTest) that is not necessary as that function does not use any of the non-public members of the class. I suspect this is leftover after a refactor, as the function in question uses GetGraphForTesting() to access the internals instead. This friend declaration was causing me a compilation error as the namespace of the declared friend function did not match the namespace of the definition. Removing it solves the compilation error and tidies up the code. Change-Id: I4aa893cb5108cd3b72ca355f725fe7a0cd053a7e Signed-off-by: Rob Hughes <robert.hughes@arm.com>
2021-02-18IVGCVSW-5394 TfLiteDelegate: Implement the Lstm operatorMike Kelly
* Add LSTM operator Signed-off-by: Mike Kelly <mike.kelly@arm.com> Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: If8c667685fa1176738ffe2e6d08b1c684e7ee6b2
2021-02-17IVGCVSW-5654 Fix failing float 16 delegate tests on androidFinn Williams
* add template specialization declaration to header to resolve clang issue Signed-off-by: Finn Williams <Finn.Williams@arm.com> Change-Id: Id8104d6feda19ed3f5f0cb018d719b1677772d9b
2021-02-17IVGCVSW-5734 Building armnn failed in our Backends CI jobFrancis Murtagh
* CreateTestNetwork() and CreateTransposeTestNetwork should only be defined if Ref enabled; the same as the test its called in otherwise it's defined but not called. Signed-off-by: Francis Murtagh <francis.murtagh@arm.com> Change-Id: I7bc522a7884d216d1a8e51afd7cec7a66e4e2947
2021-02-17IVGCVSW-5581 ExecuteNetwork: Fix pass backends as comma separated listJan Eilers
* Allow passing multiple preferred backends as comma separated list e.g. "-c CpuAcc,CpuRef" or by repeating the option "-c CpuAcc -c CpuRef" Signed-off-by: Jan Eilers <jan.eilers@arm.com> Change-Id: I8e304d26c2890b99d5ec4c1af6c372458fa70051
2021-02-16IVGCVSW-5665 'Basic NN Driver support for next OS Version'Sadik Armagan
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: If69dbc230e2136def8a697ab25b9c4cb5cb8c731
2021-02-15IVGCVSW-4873 Implement Pimpl Idiom for INetwork and IOptimizedNetworkFrancis Murtagh
!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>
2021-02-15Remove the undefined behaviour warning from InstallationViaAptRepository.mdNikhil Raj
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com> Change-Id: Ia85dea61a6c63cf6d2ec8c63d4ce7494e66fa1cb
2021-02-15Update pinned version of ACL to 21.02 release branchNikhil Raj
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com> Change-Id: I1671a68b97815a224c89c3abe2f3944d97446c09
2021-02-15IVGCVSW-5694 Update Major, Minor release versionsNikhil Raj
* Update Arm NN version in Version.hpp and all guides * Change Project Version in Doxyfile Signed-off-by: Nikhil Raj <nikhil.raj@arm.com> Change-Id: I05ab20a1ae5d0376a641df68a5877f97e7609052
2021-02-15IVGCVSW-5675 Implement Pimpl Idiom for IProfiler (lower priority)Francis Murtagh
Signed-off-by: Francis Murtagh <francis.murtagh@arm.com> Change-Id: If716f5f4e9b5433586b8a939d326830482da2f74
2021-02-15IVGCVSW-5686 Add GpuAcc MLGO tuning file configuration argumentFinn Williams
Signed-off-by: Finn Williams <Finn.Williams@arm.com> Change-Id: I3f320499c379162f9d1b00cc8816bd144cd7eee4
2021-02-15IVGCVSW-5679 Failure to run the build instructions to build ArmNN using ↵Nikhil Raj
android ndk * Provide FLATBUFFERS_INCLUDE_PATH in GlobalConfig.cmake if ARMCOMPUTECL is enabled Signed-off-by: Nikhil Raj <nikhil.raj@arm.com> Change-Id: Iabd5bb9b8a63970df9b7f485d07f8c1ee1a78560
2021-02-15IVGCVSW-5386 TfLiteDelegate: Add Strided Slice operatorJan Eilers
Signed-off-by: Jan Eilers <jan.eilers@arm.com> Change-Id: Icd87b1c54e1a5de84893882da30840a9097f6d84
2021-02-15IVGCVSW-5648 Adding serializer support for m_DimensionsSpecificityColm Donelan
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
2021-02-12IVGCVSW-5685 Add CpuAcc specific configuration option numberOfThreadsMatthew Sloyan
* Added ability to set number of threads used in CpuAcc backend * Enabled number-of-threads option in ExecuteNetwork * Added TfLiteDelegate ModelOptions test * Added unsigned int type to BackendOptions.hpp Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com> Change-Id: Ia576d4f45cbe5df3654bc730bb5ebd5181d82b5a
2021-02-12IVGCVSW-4893 Refactor ILayerVisitor using unified interface strategy.Finn Williams
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
2021-02-12IVGCVSW-5717 Update JsonPrinterTestImpl to match latest ACLDavid Monahan
* Updated JsonPrinterTestImpl to use CpuLogitsDLogSoftmaxKernel_# * Update ACL pin to: 8958167c8d609566a40c9e618158ebcbdcd3e3bb Signed-off-by: David Monahan <david.monahan@arm.com> Change-Id: Ic48d6cc321d8f4cc15c488244f0d69508fad2d1c
2021-02-11MLCE-347 Bug fixes in Reduce: QueueDescriptor.validate and init REDUCE_MINTeresa Charlin
* Allow input tensors of any rank in ReduceQueueDescriptor::validate * Fix VTS tests failing for REDUCE_MIN due to initialization Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: Id8fba1662ade4e0a967093fe5a53b275847f2393
2021-02-11MLCE-360 'ReduceLayer InferOutputShape Issue'Sadik Armagan
* 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
2021-02-11IVGCVSW-5392 TfLiteDelegate: Implement the Batch/Space operatorsMatthew Sloyan
* Added support for BATCH_TO_SPACE_ND and SPACE_TO_BATCH_ND Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com> Change-Id: Ib29333f3e2bc1a18bcc63533da4369b63c45ab90
2021-02-10IVGCVSW-5400 'TfLiteDelegate: FLOOR operator support'Sadik Armagan
* Added FLOOR operator support to Arm NN TfLiteDelegate Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: I986ce8c5a825f509e0f8b3d257fd5b60834c322f
2021-02-09IVGCVSW-5679 Fix Android NDK OOB buildMatthew Sloyan
* Specific OOB builds will fail if flatc is not available. * flatc command is now only run if found. Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com> Change-Id: Iab6e082fe35dc3c3dfb78a29e1630c9edbb80be6
2021-02-09Update ACL pin to 7e20e29904c98adae5a91c6492fd78da88b7a9bfNikhil Raj
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com> Change-Id: Ica5d673e9f6a192b0cfd28c9ad5a5143aecefba7
2021-02-09MLCE-347 'REDUCE_MIN, REDUCE_MAX, REDUCE_SUM Support'Sadik Armagan
* 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
2021-02-08IVGCVSW-4901 Add semantic versioning to Parsers and TfLite DelegateMatthew Sloyan
* Added Version.hpp to all Parsers * Added Version.hpp to TfLite Delegate * Updated CMakeLists to use new versions * Added GetVersion method to parsers and TfLite Delegate Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com> Change-Id: If29e1e6d9e615f9095ec1c01ad47acfff40b1dd5
2021-02-08IVGCVSW-4873 Implement Pimpl Idiom for IRuntimeKevin May
Signed-off-by: Kevin May <kevin.may@arm.com> Change-Id: I52448938735b2aa678c47e0f3061c87fa0c693b1
2021-02-08Update ACL pin to dda6914c6e923187c2ca2c3bfd71677e9c9e5c68Nikhil Raj
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com> Change-Id: I0e29496698b5e7934c2b1c18740527cd9eb23ecd
2021-02-08IVGCVSW-5605 Doxygen: Update parser sectionJan Eilers
* 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
2021-02-08IVGCVSW-5605 Doxygen: Add remaining guides to doxygenJan Eilers
* Integrates the debian package installation guide * Integrates the AndroidNDK guide * Integrates the cross compile guide Signed-off-by: Jan Eilers <jan.eilers@arm.com> Change-Id: I2243b15ee3f8e976789494199f12f3cc0fd5f00d
2021-02-06ArmnnConfig.cmake install to correct directoryKeith Mok
Signed-off-by: Keith Mok <ek9852@gmail.com> Change-Id: I9b1037275379bdbf452589357576cfa763b7c128
2021-02-05IVGCVSW-4143 Add semantic versioning to Arm NNNikhil Raj
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com> Change-Id: Ibe1200c6d7be9e04821b4a829c83833d44542ad5
2021-02-05Update ACL pin to cf87f509fc23d02c56569f794a3fb59e1b8be277Nikhil Raj
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com> Change-Id: I20b69cc042ae5828584b2ecfd2f9694021d7693c
2021-02-05MLCE-326 'Support Dilation in Conv2D in ONNX and Tensorflow Parsers'Sadik Armagan
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: I4a0f07b1e8f80aff0d29405def1f33bde7944e31
2021-02-04Remove LFS configurationNarumol Prangnawarat
* Remove LFS configuration * Add mock test models for external delegate Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com> Change-Id: I9f5b427a995aff22391548cd45821cb2afc8a474
generated by cgit v1.2.1 (git 2.23.0) at 2024-05-17 22:21:46 +0000