- a0f8b15 Revert "IVGCVSW-6873 Import inputs but don't export outputs fails." by James Conroy · 2 years ago
- 03bf98a IVGCVSW-6873 Import inputs but don't export outputs fails. by Colm Donelan · 2 years ago
- 721e629 IVGCVSW-6123 ConstTensorsAsInputs: Conv2d by Keith Davis · 2 years, 1 month ago
- 541880f IVGCVSW-6147 ConstTensorsAsInput: Optimizer - FusePermuteIntoConstLayer by Cathal Corbett · 2 years, 1 month ago
- 07307f3 IVGCVSW-6455 Support Const + Dequantize layer and optimize it. by Teresa Charlin · 2 years, 1 month ago
- 80512b0 IVGCVSW-6929 Support for models with implicit expanded dimensions by Mike Kelly · 2 years, 1 month ago
- 8bd5360 IVGCVSW-6126 ConstTensorsAsInput: Conv2d - Backends by Cathal Corbett · 2 years, 1 month ago
- b4dd5cc IVGCVSW-6124 ConstTensorsAsInput: Conv2d - FrontEnd by Keith Davis · 2 years, 2 months ago
- 4b19d22 IVGCVSW-6940 ConstTensorsAsInput: DepthwiseConvolution2d - Complete ACL by Cathal Corbett · 2 years, 1 month ago
- 727c2b5 Wrong variable 'm_ProjectionWeights' is used to check if the pointer is valid from IVGCVSW-4449 by Cathal Corbett · 2 years, 1 month ago
- 0690265 IVGCVSW-6127 ConstTensorsAsInput: DepthwiseConvolution2d by Cathal Corbett · 2 years, 2 months ago
- b2d3ec5 IVGCVSW-6856 Add GATHERNd FrontEnd and Ref Implementation by Teresa Charlin · 2 years, 2 months ago
- a3f4fba IVGCVSW-6732 Tests surrounded in '#if defined(ARMNNREF_ENABLED)' in android-nn-driver do not execute. by Cathal Corbett · 2 years, 2 months ago
- 2776183 IVGCVSW-6706 Move headers to profiling/client/include by Jim Flynn · 2 years, 2 months ago
- af94772 IVGCVSW-6811 replace ProfilingService includes with IProfilingService by Jim Flynn · 2 years, 3 months ago
- 5aa9fd7 IVGCVSW-6704 Change the namespace from armnn::profiling to arm::pipe by Cathal Corbett · 2 years, 3 months ago
- bb6c649 IVGCVSW-6399 Remove deprecated code 22.02 (FullyConnected) by Francis Murtagh · 2 years, 4 months ago
- 9d74ba6 IVGCVSW-6634 SubgraphView: Add method of returning a GetSubgraphWorkingCopy by Francis Murtagh · 2 years, 4 months ago
- 56ccf68 IVGCVSW-6633 SubgraphView uses IConnectableLayer rather than Layer in its m_Layers by Francis Murtagh · 2 years, 6 months ago
- 3ea0107 Fix INetwork::AddPrecompiledLayer to take the CompiledBlobPtr by value rather than reference. by Cathal Corbett · 2 years, 5 months ago
- cbfd718 IVGCVSW-6632 OptimizationViews: has INetwork rather than Graph for holding layers by Cathal Corbett · 2 years, 6 months ago
- 0c47974 IVGCVSW-6626 Promote backend headers in backendCommon to armnn/backends by Colm Donelan · 2 years, 6 months ago
- 18655b8 IVGCVSW-6630 Add new method AddPrecompiledLayer() to INetwork by Cathal Corbett · 2 years, 6 months ago
- 17d34da Add addition timing logging output by Jan Eilers · 2 years, 6 months ago
- 6a71bb5 Add ModelOptions logging output by Jan Eilers · 2 years, 7 months ago
- 7b885b3 IVGCVSW-6509 Front End + Reference Workload implementation by Tamás Nyíri · 2 years, 7 months ago
- b1aad42 IVGCVSW-6527 Support the new memory API in loaded network by Finn Williams · 2 years, 7 months ago
- b7851f9 IVGCVSW-5636 'Implement NNAPI caching functions' by Sadik Armagan · 2 years, 8 months ago
- 5d7b0a3 Add ConstTensorsAsInput support for Conv3d by Matthew Sloyan · 2 years, 8 months ago
- e155bbf Refactor: Profiler moved to Graph by Derek Lamberti · 2 years, 8 months ago
- f1e0ad3 Profiling instrumentation throughout the Optimizer by Derek Lamberti · 2 years, 8 months ago
- 521032f IVGCVSW-6417: Catch AddFullyConnected API error when weights TensorInfo isn't set by Cathal Corbett · 2 years, 8 months ago
- 1b2654f IVGCVSW-5985 Remove deprecated code by Jan Eilers · 2 years, 8 months ago
- b63a311 IVGCVSW-6163 Add Conv3d FrontEnd and Ref Implementation by Matthew Sloyan · 2 years, 9 months ago
- 51f6777 IVGCVSW-3705 Add Channel Shuffle Front end and Ref Implementation by Simon Obute · 2 years, 9 months ago
- 0c0019c IVGCVSW-6294 Detect and remove extraneous fp16 conversion layers by Jan Eilers · 2 years, 10 months ago
- d218d98 IVGCVSW-6289 Separate tensor shape inference and validation calls by Finn Williams · 2 years, 10 months ago
- b20d1d4 IVGCVSW-6119 ConstTensorsAsInput: FullyConnected Bug Fix by Matthew Sloyan · 2 years, 10 months ago
- 84e025a Infer tensor shapes before graph optimization by Finn Williams · 2 years, 10 months ago
- 81beae3 IVGCVSW-6119 ConstTensorsAsInput: FullyConnected by Matthew Sloyan · 2 years, 11 months ago
- 8ed39ae MLCE-530 Add front end support for UnidirectionalSequenceLstm on ArmNN by Narumol Prangnawarat · 2 years, 11 months ago
- 33f8987 IVGCVSW-6161 ConstTensorsAsInput: Optimizer - Redirect ConstTensor layer members by Matthew Sloyan · 3 years ago
- 0d677db IVGCVSW-6114 Create multiple LoadedNetworks from one OptimizedNetwork by Mike Kelly · 3 years ago
- 3ae3f97 MLCE-510 Add CpuRef Shape Operator to ArmNN by Keith Davis · 3 years ago
- 77fe76b IVGCVSW-5835 Move the src/profiling/LabelsAndEventClasses class to profiling/common by Nikhil Raj · 3 years ago
- 5786eb7 IVGCVSW-6069 Fold PAD into Depthwise Convolution by Teresa Charlin · 3 years ago
- e5f0b24 IVGCVSW-5818 Enable import on GPU by Narumol Prangnawarat · 3 years, 1 month ago
- 1f58f03 IVGCVSW-5815 Generalise ConstCpuTensorHandle by James Conroy · 3 years, 1 month ago
- fe95d72 Fold PAD into Pooling2d if possible by Diego Lopez Recas · 3 years, 3 months ago
- b392e98 IVGCVSW-5410 Add front-end support for CAST by mathad01 · 3 years, 2 months ago
- 4422cec Fix graph copy memory spike by Finn Williams · 3 years, 2 months ago
- f0a6dec IVGCVSW-5736 and IVGCVSW-5743 'NonConstWeights: Update front-end and TfLiteDelegate support for FullyConnected Operator' by Sadik Armagan · 3 years, 2 months ago
- 381f502 Revert "Fold PAD into Pooling2d" by Jim Flynn · 3 years, 2 months ago
- 51ce7d4 Fold PAD into Pooling2d by Diego Lopez Recas · 3 years, 3 months ago
- 3d2b4b2 IVGCVSW-4873 Implement Pimpl Idiom for INetwork and IOptimizedNetwork by Francis Murtagh · 3 years, 4 months ago
- b454c5c IVGCVSW-4893 Refactor ILayerVisitor using unified interface strategy. by Finn Williams · 3 years, 4 months ago
- 0c3ea5b backends/reference: Add ReduceSum operation support by Sadik Armagan · 3 years, 4 months ago
- 07810fc IVGCVSW-5328-5329 Fuse Activation by Mike Kelly · 3 years, 7 months ago
- aba90cd IVGCVSW-5091 Add Logical ops frontend and ref impl by James Conroy · 3 years, 7 months ago
- 90231b8 IVGCVSW-5315 Create FuseBatchNorm class by Mike Kelly · 3 years, 7 months ago
- 06e0300 IVGCVSW-5314 Create OptimizeForExclusiveConnection by Teresa Charlin · 3 years, 8 months ago
- f290d88 IVGCVSW-4489 Remove remaining occurrence of boost::format by Matthew Sloyan · 3 years, 8 months ago
- 3a613cc Refactored Optimize(...) function to throw exceptions instead of returning null by Mike Kelly · 3 years, 8 months ago
- 0663d66 IVGCVSW-5303 Remove some boost::numeric_cast from rest of ArmNN by Matthew Sloyan · 3 years, 9 months ago
- 16f82f9 IVGCVSW-5305 AddBroadcastReshapeLayer as optimizer by Narumol Prangnawarat · 3 years, 9 months ago
- 045f6be IVGCVSW-5156 Introduce ModelOptions to OptimizedNetwork by Sadik Armagan · 3 years, 9 months ago
- bbf71a6 IVGCVSW-5244 Load-scope dynamic tensor TfLite tests by Narumol Prangnawarat · 3 years, 9 months ago
- a2493a0 IVGCVSW-5012 Add importEnabled option for OptimizerOptions by Narumol Prangnawarat · 3 years, 10 months ago
- b8d771a IVGCVSW-5012 Enable zero copy for Neon by Narumol Prangnawarat · 3 years, 10 months ago
- f24effa IVGCVSW-5155 Update Arm NN API to allow for call to shape inference by Finn Williams · 4 years ago
- 2605b23 IVGCVSW-4624 Add a RANK Reference Implementation by Finn Williams · 4 years ago
- 5266473 IVGCVSW-4903 Connect axis parameter in Gather from android to ACL. by Teresa Charlin · 4 years ago
- ec6c680 IVGCVSW-4906 Add front-end support for FILL operator by Ryan OShea · 4 years ago
- 749294b remove BOM from files by Laurent Carlier · 4 years ago
- 4a0c9b9 IVGCVSW-4888 Update Resize Front end for new parameters by David Monahan · 4 years ago
- ed32405 IVGCVSW-4449 Add missing QLstm nullptr checks by James Conroy · 4 years, 1 month ago
- bb446e5 IVGCVSW-4483 Remove boost::polymorphic_downcast by Jan Eilers · 4 years, 2 months ago
- ac2770a IVGCVSW-4485 Remove Boost assert by Narumol Prangnawarat · 4 years, 2 months ago
- 250d392 IVGCVSW-4633 Add conversion of BF16 support to Neon by Narumol Prangnawarat · 4 years, 2 months ago
- e2062cd IVGCVSW-4590 Fix Lstm layers CellToInputWeights by Jan Eilers · 4 years, 2 months ago
- 57ef008 IVGCVSW-4597 Modify BF16 optimizer to Convert only inputs and weights of by Narumol Prangnawarat · 4 years, 2 months ago
- bc7ffb5 IVGCVSW-4520 Implement BFloat16 Optimizer by Narumol Prangnawarat · 4 years, 2 months ago
- 586a9aa IVGCVSW-4549 Add front end for new QLSTM layer by James Conroy · 4 years, 2 months ago
- 3184c90 IVGCVSW-4463 Change ProfilingService to a member of runtime from a singleton by Sadik Armagan · 4 years, 3 months ago
- 8eb2560 IVGCVSW-4482 Remove boost::ignore_unused by Jan Eilers · 4 years, 3 months ago
- 490b7be IVGCVSW-4375 Add support for Transpose to optimizations by Mike Kelly · 4 years, 3 months ago
- 4a9e24b IVGCVSW-4314 Per-layer backend hint API by Derek Lamberti · 4 years, 5 months ago
- c9ea45a IVGCVSW-4375 Add support for Transpose by Mike Kelly · 4 years, 3 months ago
- 4a3c610 IVGCVSW-4259 Add frontend and reference workload for UnaryOperationLayer by josh minor · 4 years, 5 months ago
- f48afc6 Remove Logging.hpp from ArmNN.hpp by Matthew Bentham · 4 years, 5 months ago
- f90c56d Rename quantized data types to remove ambiguity for signed/unsigned payloads by Derek Lamberti · 4 years, 5 months ago
- 94a88d2 IVGCVSW-4246 Clean build Layers with -Wextra by Derek Lamberti · 4 years, 6 months ago
- e5b8eb9 IVGCVSW-4210 Create a public API for the common backend files by Matteo Martincigh · 4 years, 6 months ago
- 0844697 Replace boost logging with simple logger by Derek Lamberti · 4 years, 6 months ago
- dd6804b IVGCVSW-4170 Also convert constants to FP16 when model converted by Derek Lamberti · 4 years, 6 months ago
- 47e863d IVGCVSW-4077 Fix issue when NEON import disabled by James Conroy · 4 years, 7 months ago
- 87972be IVGCVSW-4119 Fix FP16 to FP32 fallback mechanism in optimizer to work with Dequantize by Aron Virginas-Tar · 4 years, 7 months ago
- 99d9d4a IVGCVSW-4069 Add ProfilingGuid to Network by Jan Eilers · 4 years, 7 months ago
- ffab16f IVGCVSW-4077 Disable NEON memory import by James Conroy · 4 years, 7 months ago
- 2321443 Rename Optimize's errMessages to messages by Rob Hughes · 4 years, 7 months ago