aboutsummaryrefslogtreecommitdiff
AgeCommit message (Collapse)Author
2022-08-18IVGCVSW-6779 Add build-tool Docs and update docsv22.08branches/armnn_22_08James Conroy
* Added Arm NN Build Tool README.md and license. * Added Dockerfile diagram image and license. * Updated existing guides: added note to the cross compile guide to use build-tool, removed content from the Delegate BuildGuideNative.md. * Added Arm NN logo image to homepage README.md and added license. Signed-off-by: James Conroy <james.conroy@arm.com> Change-Id: I9306ad24165cf3b0203c2a1852ec3afd718e9eab
2022-08-12IVGCVSW-6954 'Arm NN SL Improvements'Sadik Armagan
* 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
2022-08-12IVGCVSW-7140 Produce map file for AndroidNN build for debug and release.Cathal Corbett
Signed-off-by: Cathal Corbett <cathal.corbett@arm.com> Change-Id: Ib4433767ba8bd3282a9b19c2a85ff1a6e7e83df5
2022-08-12Fixing documents for 22.08Nikhil Raj
* Fixed broken links * Updated link to bazel guide * Fixed versioning issues in packaging doc * Updated paths to binary files Signed-off-by: Nikhil Raj <nikhil.raj@arm.com> Change-Id: I6120bb2dd56d55a994cd12d99bed054ce4d7c058
2022-08-09Bug Fix for refactor of the ExecuteNetwork for strategy in Precompiled layer.Teresa Charlin
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: Ib91b734d4add47e23ad00f76e53f1873ff617831
2022-08-09IVGCVSW-7154 'Constant Tensors As Inputs'Sadik Armagan
* Fixed the issues about converting Conv2D and DepthwiseConv2d input issues * Read 1D input tensors that do not have shape specified Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: I12f3d1c57a2afedac42c6e7b31e4b1fc689abeca
2022-08-05IVGCVSW-7179 Segfault running ssd_mobilenet_v2_int8 with ExNet and delegate.Teresa Charlin
* model was declared in the TfLiteExecutor constructor, instead of intializing m_Model * Working with this model that has 4 output we saw the the output names were not correct, this got fixed too Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: I48f194ad4ba6af43d43e6eea336eb87ffee02dcc
2022-08-05IVGCVSW-7103 ExecuteNetwork failed while doing Yolov4 executionNikhil Raj
* 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
2022-08-05IVGCVSW-6777 Add Arm NN build-tool DockerfileJames Conroy
* Adds Dockerfile associated with Arm NN build-tool scripts. * The Dockerfile encapsulates the installation of system-wide packages (install-packages.sh), download/install of Arm NN dependencies (setup-armnn.sh) and the building of Arm NN and ACL (build-armnn.sh). * A helper script for copying build contents from the built Docker image is provided for by docker-copy-to-host.sh. * Modified existing scripts: moved the cloning of Arm NN and ACL from setup-armnn.sh to build-armnn.sh and decoupled setup-armnn.sh from scripts outside of build-tool directory e.g. armnn/scripts/get_tensorflow.sh. * The build-armnn.sh script clones the latest release branches of Arm NN and ACL by default. Custom repos can be placed in the build-tool directory prior to 'docker build' and they will be used instead (advanced usage). * Support added for Linux targets only, Android to be added in future work. Signed-off-by: James Conroy <james.conroy@arm.com> Change-Id: I336013cf93821d2cd3e5d9fe2ca4e955ffdd2386
2022-08-05IVGCVSW-6777 Replace old Dockerfile with build-toolJames Conroy
* Removed old Dockerfile and associated docs. * Keeping README as it currently ranks highly on web searches for "armnn docker" and providing a link to new alternative Arm NN Build Tool. Change-Id: I0ce79cedffa035728e394c116912f36481804931 Signed-off-by: James Conroy <james.conroy@arm.com>
2022-08-05IVGCVSW-7157 ExNet. interpreter chooses a different input type.Cathal Corbett
Signed-off-by: Cathal Corbett <cathal.corbett@arm.com> Change-Id: If00d8dab2846c484a1969fb152cb9f8bd16e1b3e
2022-08-04Update ACL pin to 22.08 release branchNikhil Raj
Signed-off-by: Nikhil Raj <nikraj01@e126673.cambridge.arm.com> Change-Id: Ica451b6e4b2f8dd474f1e216d0cb38163a7d2953
2022-08-04Update PROJECT_NUMBER in Doxyfile for 22.08Nikhil Raj
Signed-off-by: Nikhil Raj <nikraj01@e126673.cambridge.arm.com> Change-Id: I2446013092221f3016f8d2d57256ea0f384d0cec
2022-08-04IVGCVSW-7062 'Gpu Tuning does not work with TfLite Benchmark tool'Sadik Armagan
* Load the tuning file when GpuAcc is selected as a backend. Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: I1d6b0237a87301f07681293a2c6dbc37e352dd28
2022-08-04Update ACL pin to f67903b8ab8205b47f0ee2c27aeca8bed405c58eNikhil Raj
Signed-off-by: Nikhil Raj <nikraj01@e126673.cambridge.arm.com> Change-Id: I849476ac201c151a9c2087bab03af1fc67732bce
2022-08-03IVGCVSW-7089 Add LICENSE.spdx for Arm NNJim Flynn
Signed-off-by: Jim Flynn <jim.flynn@arm.com> Change-Id: I6e5f41a7a4432f448156755389c108692b7213e2
2022-08-03IVGCVSW-7111 change backend deprecation from 22.11 to 23.08Jim Flynn
Signed-off-by: Jim Flynn <jim.flynn@arm.com> Change-Id: I3a3aab7b5042349cb2df8517678306665e037610
2022-08-03Bug Fixes for refactor of the ExecuteNetwork.Teresa Charlin
* dot file to be generated when -v is given. It was only being generated when using the delegate as executor * output name read from m_Params.m_OutputNames instead of m_TfLiteInterpreter * typo: "delage" instead of "delegate" * QAsymmS8 templated as int8, instead of uint8 Change-Id: Ie13ae0f7e6395c0ebcb5ecda32e72082dee8aa6c Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: Iac97a23927ba42290ebeb3446bbd36da15045e07
2022-08-03Update ACL pin to 3c4d085da54c3d9727cb31718c5b407c18ff646aNikhil Raj
Signed-off-by: Nikhil Raj <nikraj01@e126673.cambridge.arm.com> Change-Id: Ibd6f971f275c115f97a0d8338f6e7770790f2e67
2022-08-03Fix '#if defined(ARMNN_POST_TFLITE_2_3)' in TfLiteParser Conv3D test.Cathal Corbett
Signed-off-by: Cathal Corbett <cathal.corbett@arm.com> Change-Id: I5c68b81a67fc2b5a33cf62753351440564bb868e
2022-08-03IVGCVSW-6992 Update Major, Minor release versions for 22.08Cathal Corbett
Signed-off-by: Cathal Corbett <cathal.corbett@arm.com> Change-Id: Ic134f73f217fff420fec089cd817e48ef62641c6
2022-08-03IVGCVSW-7145: BatchMatMul Fix for Raspi Cross Compile FailingSamuel Yap
* Changed long variable declaration to int Signed-off-by: Samuel Yap <samuel.yap@arm.com> Change-Id: I2df6f8f6df8780e48e09f7e68c04626a8a8a207d
2022-08-02IVGCVSW-6889 Seg fault running ExeNet with --bf16-turbo-mode on fpgaFrancis Murtagh
* 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
2022-08-02IVGCVSW-7063 'Support Library NNAPI Caching'Sadik Armagan
* Fixed caching issue. Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: Ic7b3e0bd4438b2fd1b3dbfa86b6c89d625bbf9dd
2022-08-02Update ACL pin to 9b921be1ff7283050eb39d9ce1b10b5c8bfc1300Nikhil Raj
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com> Change-Id: Iecfb4ef0f821f71aaf16c6f3c80f26a4c39f2e3a
2022-08-02IVGCVSW-7149 FoldPadIntoQuantizedAvgPoolCpuRefTest test failing while ↵Cathal Corbett
running Arm NN Unittest Signed-off-by: Cathal Corbett <cathal.corbett@arm.com> Change-Id: I567452000287babad345e61ea85ea84f362f48e0
2022-08-02IVGCVSW-7147 Bug Fix for refactor of the ExecuteNetwork for strategy in ↵Teresa Charlin
ConvertLayers. * ConvertBf16ToFp32Layer * ConvertFp16ToFp32Layer * ConvertFp32ToBf16Layer * ConvertFp32ToFp16Layer Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: I5e763519a12f017dc14b09ea191fdb3b7398c0d7
2022-07-29GitHub #667: Neon fold padding into average pool 2D quantization bug fix.Cathal Corbett
* 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
2022-07-28Bug Fix for refactor of the ExecuteNetwork for Strategy in MemCopyLayerTeresa Charlin
* Correcting some typos Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: Icb21dc4828e51afa38816bd454926fc41e9e82cb
2022-07-28IVGCVSW-7049 Inform Arm NN external users about switching branch to mainNikhil Raj
* Adding an announcement in the main Readme file with the date we are freezing master and moving to main branch Change-Id: I87a0e99d83cc872ef6ac3ba1f0fd445665885059 Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
2022-07-28Update ACL pin to aa52b7d45dc82323aafb09a9002b76a0000925bcNikhil Raj
* Fix compilation error rasied in Nightly_NEW Signed-off-by: Nikhil Raj <nikhil.raj@arm.com> Change-Id: I2e7ea907dd2d6e99fc56ff8f48f7c2b6c2a4a7c1
2022-07-28Revert "Revert "IVGCVSW-6650 Refactor ExecuteNetwork""Teresa Charlin
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>
2022-07-26GitHub #650: DelegateQuickStartGuide.md errors fix.Cathal Corbett
Signed-off-by: Cathal Corbett <cathal.corbett@arm.com> Change-Id: If24cad1d5d403e195d7adc539afb83cc5df134d1
2022-07-22IVGCVSW-7109: Add Batch MatMul front end support - ReferenceSamuel Yap
* 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
2022-07-22IVGCVSW-6776 Add Arm NN build-tool scriptsJames Conroy
* Initial scripts which download and build Arm NN dependencies (setup-armnn.sh) and build both Arm NN and ACL (build-armnn.sh). * Also added common.sh for handling common variables between scripts and validation.sh for common command line arg validation. Signed-off-by: James Conroy <james.conroy@arm.com> Change-Id: I6a61149d048f618b4cc9770cc9dd6ec2e5f64ea5
2022-07-22IVGCVSW-6978: RedirectMembersToConstantInputs does not work with ↵Francis Murtagh
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>
2022-07-21IVGCVSW-6954 'Arm NN Support Library Implementation'Sadik Armagan
* Fixed model converting issue * Fixed import memory issue Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: Ied61810b308e0c5d5754f122a6ea2bac1d0725f1
2022-07-20IVGCVSW-7113 Fix building nn driver failed in our Android OOBTKevin May
* Android.bp file gets picked up by older Android versions so rename it to "switch it off" and update guide on how to enable it Signed-off-by: Kevin May <kevin.may@arm.com> Change-Id: I1fc59a0d0dc2e6ce9cdc19f94b0b34d08d414351
2022-07-20IVGCVSW-7061: Use same sentence for Aynch execution in ExNetTeresa Charlin
* "Asynchronous Execution with std::launch:async..." * "Asynchronous Execution with Arm NN thread pool..." Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: I93f6ae92fd5599d1042f0dfced7e90ef85e20463
2022-07-19Update ACL pin to 99c46475daf277aa53e6747f9e41209f418fed33Nikhil Raj
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com> Change-Id: Ia09aba7d8a358f27db7773d360604a2570fdf657
2022-07-18IVGCVSW-7036 Remove reference to Android 32 from Arm NN README.Colm Donelan
Signed-off-by: Colm Donelan <colm.donelan@arm.com> Change-Id: I01000533c3023271f81e9f7f53504ba185a62778
2022-07-15IVGCVSW-6896 Fix pre-import when using sync execute.Colm Donelan
* 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
2022-07-15IVGCVSW-7107 'Error while running Arm NN Sl with -d option'Sadik Armagan
* Templated the DumpTensor() function based on tensor type Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: I08775e480f89010be61daf0a09a2ab0274e05978
2022-07-15IVGCVSW-7096 Harmonise macro ARMNN_TFLITE_DELEGATETeresa Charlin
* Remove ARMNN_TF_LITE_DELEGATE and DARMNN_TF_LITE_DELEGATE Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: I3fc08da3fa0b733e6791c42f6bc59494f2bc26a6
2022-07-15Update ACL pin to a1f7851e2f776610019db8725c2963c36b0c85ebNikhil Raj
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com> Change-Id: Id2cf6cda8f83466f76959ca90b03b56864d3ac8a
2022-07-14Update ACL pin to 4bfc70e31766587c951204c93a127a486e007d0cNikhil Raj
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com> Change-Id: I8129fcd6b20ad6ec3b43f7d3b2bfcb1de45d28e6
2022-07-13Update ACL pin to 2186aef84fe1206545f6d5bc321752044fdd1b3dNikhil Raj
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com> Change-Id: I654a9e0cb2e9458e0a1ccdab55bc32c3d80ee3a9
2022-07-13Documentation refactor and updates.Cathal Corbett
* Includes updating ContributorGuide.md with information section 'Contributing code to Arm NN'. * Renaming of ContributorGuide.md to CONTRIBUTING.md. Also renamed associated licence file and links in other pages that call the md file. Signed-off-by: Cathal Corbett <cathal.corbett@arm.com> Change-Id: Ic3336d78b64ae41af07ea9fd03631bb161613c4b
2022-07-13IVGCVSW-7094 Add LOG and SIN support to tflite delegateTeresa Charlin
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: I355298f365b82cad1e3f46cfebf1c1375716cf92
2022-07-13IVGCVSW-6620 Update the async api to use ExecutionDataMatthew Sloyan
* ExecutionData holds a void* which can be assigned to data required for execution in a backend. WorkingMemDescriptors are used in the Ref backend which hold TensorHandles for inputs and outputs. * Updated ExecuteAsync functions to take ExecutionData. * Added CreateExecutionData and UpdateExectutionData to IBackendInternal. * Streamlined experimental IWorkingMemHandle API by removing map related function and unused m_workingMemDescriptorMap from WorkingMemHandle. Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com> Change-Id: I54b0aab12872011743a141eb42dae200227769af
generated by cgit v1.2.1 (git 2.23.0) at 2024-05-17 08:46:58 +0000