- e011d20 IVGCVSW-4209 Create a public API for the ArmNN Utils by Matteo Martincigh · 4 years, 9 months ago
- 2e25927 Github #306 Treat data_format attribute as optional in TfParser::ParseFusedBatchNorm() by Aron Virginas-Tar · 4 years, 9 months ago
- 2445744 IVGCVSW-3864 Add support for per-channel QSymm8 DepthwiseConvolution2d to Neon backend by Aron Virginas-Tar · 4 years, 9 months ago
- 1571700 Make the profiling GUID test independent from random events by Matteo Martincigh · 4 years, 9 months ago
- 76c50d8 Remove const type qualifiers with no effect by Matteo Martincigh · 4 years, 9 months ago
- 9820d30 MLCE-115 Remove redundant error checking in CL backend by Matthew Bentham · 4 years, 9 months ago
- 6d3d205 Github #274 Use non-deprecated path to boost header by Matthew Bentham · 4 years, 9 months ago
- dd6804b IVGCVSW-4170 Also convert constants to FP16 when model converted by Derek Lamberti · 4 years, 9 months ago
- 710f664 IVGCVSW-4148 Extend reporting of quant multiplier > 1 as unsupported on ACL to per-axis case by Aron Virginas-Tar · 4 years, 9 months ago
- 899f64f IVGCVSW-3859 Per-channel QSymm8 support of Convolution2d in Cl by Keith Davis · 4 years, 9 months ago
- e9323ec Add IsQuantizeType(DataType) for use in validation functions by Aron Virginas-Tar · 4 years, 9 months ago
- 94c4fef IVGCVSW-3728 Add CL workload for Slice by Aron Virginas-Tar · 4 years, 9 months ago
- 21fc28b IVGCVSW-3866 Add support for per-channel QSymm8 Convolution2d to Neon backend by Aron Virginas-Tar · 4 years, 9 months ago
- e131a0b IVGCVSW-4158 FP16 Mobilenet V1 and V2 30% regression on ArmNN on Mate20 by Sadik Armagan · 4 years, 9 months ago
- 3a93dfa Github #251 Surround local structs with anonymous namespace by Matthew Bentham · 4 years, 9 months ago
- b86a382 IVGCVSW-4148 Report quant multiplier > 1 as unsupported for ACL by James Conroy · 4 years, 9 months ago
- 4cace32 IVGCVSW-4124 Replacing the "sleep_for" loop from FileOnlyProfilingConnection by Colm Donelan · 4 years, 9 months ago
- cf7c1c6 IVGCVSW-4151 HAL 1_2 Dequantize FP32 Per Channel Tests on CpuAcc Failing by Sadik Armagan · 4 years, 9 months ago
- 234d525 IVGCVSW-4070 Add CreatedNamedTypeEntity and CreateNamedTypedChildEntity by Narumol Prangnawarat · 4 years, 9 months ago
- 434de54 Revert "Only enable mixed precision FP16 pooling for Android Q" by Kevin May · 4 years, 9 months ago
- ba424d2 IVGCVSW-1530 Add TfLite slice parser and fix transpose perm vector creation by josh minor · 4 years, 9 months ago
- 52ec346 IVGCVSW-3697 Add check for ArgMinMax QAsymm8 to ClLayerSupport by Francis Murtagh · 4 years, 9 months ago
- 47e863d IVGCVSW-4077 Fix issue when NEON import disabled by James Conroy · 4 years, 9 months ago
- 85ad78c IVGCVSW-4068 Add Guid to Workload by Narumol Prangnawarat · 4 years, 9 months ago
- 036f02d IVGCVSW-3729 Added neon slice workload and supporting neon layer tests by josh minor · 4 years, 9 months ago
- 49d0f12 MLCE-144 Cts NNAPI test cases failed by Mike Kelly · 4 years, 9 months ago
- dbdd1b4 IVGCVSW-3980 Implementation of Guid generator by Narumol Prangnawarat · 4 years, 9 months ago
- aad2fe4 Fix quantizer crash by zero tensor by Tee Jung · 4 years, 9 months ago
- caf2bdd Fix possible crash in case of zero dimension tensor in the ONNX parser by Tee Jung · 4 years, 9 months ago
- 17d8d85 IVGCVSW-3486 Add clipping parameter validation in LstmQueueDescriptor by janeil01 · 4 years, 9 months ago
- 0270524 IVGCVSW-4129 Fix thread starvation due to low capture periods by Colm Donelan · 4 years, 9 months ago
- 9723d02 IVGCVSW-4074 Send Timeline message in RequestCounterDirectoryCommandHandler by Matteo Martincigh · 4 years, 9 months ago
- 87972be IVGCVSW-4119 Fix FP16 to FP32 fallback mechanism in optimizer to work with Dequantize by Aron Virginas-Tar · 4 years, 9 months ago
- 5716de2 IVGCVSW-4140 Report per-axis quantization as unsupported for DepthwiseConvolution on ACL backends by Aron Virginas-Tar · 4 years, 9 months ago
- cdfb941 IVGCVSW-4073 Send stream info in the ConnectionAcknowledgedCommandHandler by Matteo Martincigh · 4 years, 10 months ago
- 34a407d IVGCVSW-4072 Add stream header to Timeline Message Directory packet by Matteo Martincigh · 4 years, 10 months ago
- 30db8ad NNXSW-1853 Change SubgraphViewSelector algorithm by Rob Hughes · 4 years, 10 months ago
- 721b82f Print CMake messages on stdout rather than stderr by Rob Hughes · 4 years, 9 months ago
- db1a283 Add FP16 support to DebugWorkload by Aron Virginas-Tar · 4 years, 9 months ago
- 60538ad Only enable mixed precision FP16 pooling for Android Q by Derek Lamberti · 4 years, 9 months ago
- f4c502f Fix redundancy in call to configure() in ACL DepthwiseConvolution workloads by Aron Virginas-Tar · 4 years, 9 months ago
- 9313895 Add SpaceToDepth to GetLayerTypeAsCString() by Aron Virginas-Tar · 4 years, 9 months ago
- e3803ea CL & Neon workload factories inherit from WorkloadFactoryBase by Derek Lamberti · 4 years, 9 months ago
- 270233f Fix a few compile errors: by Rob Hughes · 4 years, 9 months ago
- 68a4dbc IVGCVSW-4053 Enable ArgMinMax EndToEndTest for NEON/CL by James Conroy · 4 years, 9 months ago
- 1939df5 IVGCVSW-4128 Add Signed32 to supported input types for Ref ArgMinMax by Francis Murtagh · 4 years, 9 months ago
- 2dc0572 IVGCVSW-3695 Add CL ArgMinMax workload by James Conroy · 5 years ago
- 663c184 IVGCVSW-4051 Update ACL pin to 94e0cf960ea6116eb57fa88d9b951f859b52c602 by James Conroy · 4 years, 10 months ago
- d8df026 IVGCVSW-4079 Add support of per-axis quantization to DepthwiseConvolution2d by Teresa Charlin · 4 years, 10 months ago
- 99d9d4a IVGCVSW-4069 Add ProfilingGuid to Network by Jan Eilers · 4 years, 10 months ago
- 94d3b93 IVGCVSW-3839 Add support of per-axis quantization to reference TransposeConvolution2d by Aron Virginas-Tar · 4 years, 10 months ago
- 62cdb08 IVGCVSW-4064 ArmNN Master fails due to an error in RefArgMaxAxis2Uint8Test by Francis Murtagh · 4 years, 10 months ago
- 07f25e0 IVGCVSW-4104 Report Conv2d per-axis quantization unsupported on ACL backends by Aron Virginas-Tar · 4 years, 10 months ago
- 3fec1ea IVGCVSW-4067 Change LayerGuid to use ProfilingGuid by janeil01 · 4 years, 10 months ago
- ffab16f IVGCVSW-4077 Disable NEON memory import by James Conroy · 4 years, 10 months ago
- 130ec60 IVGCVSW-4108 Fixed invalid data type exception by Mike Kelly · 4 years, 10 months ago
- 70f609b MLCE-144 Fix cts MAX_POOL_2D_V1_0 tests by Finn Williams · 4 years, 10 months ago
- 8bf442e IVGCVSW-4107 Fix bug in ProfilingConnectionDumpToFileDecoratorTests by Aron Virginas-Tar · 4 years, 10 months ago
- c4946c7 IVGCVSW-4102 Move ProfilingGuid to public interface by janeil01 · 4 years, 10 months ago
- e63a026 IVGCVSW-3951 Create the timeline decoder by Finn Williams · 4 years, 10 months ago
- 362e032 Escape angle brackets in dot file labels by Rob Hughes · 4 years, 10 months ago
- 5dc816e IVGCVSW-4065 Add a RecordEvent function by Matteo Martincigh · 4 years, 10 months ago
- 5edc881 IVGCVSW-3837 Add support for per-axis quantization to reference Convolution2d workload by Aron Virginas-Tar · 4 years, 10 months ago
- ec33a91 IVGCVSW-4038 Convert Strided_Slice Shrink_Axis_Mask Parameter to ACL format by Francis Murtagh · 4 years, 10 months ago
- 3201eea IVGCVSW-3444 File Only Profiling Connection by Keith Davis · 4 years, 10 months ago
- 2321443 Rename Optimize's errMessages to messages by Rob Hughes · 4 years, 10 months ago
- 378bbfc IVGCVSW-4065 Use platform-specific thread id size in Timeline packets by Matteo Martincigh · 4 years, 10 months ago
- 2ffcc41 IVGCVSW-4065 Refactor the IPacketBuffer smart pointers by Matteo Martincigh · 4 years, 10 months ago
- b67f957 IVGCVSW-3836 Add support for Int32 per-axis scales by Aron Virginas-Tar · 4 years, 10 months ago
- 13b653f IVGCVSW-3843 Add support of per-axis quantization to BuildArmComputeTensorInfo by Aron Virginas-Tar · 4 years, 10 months ago
- 5236e1d IVGCVSW-3835 Create Encoder and Decoder for QSymm8PerAxis by Keith Davis · 4 years, 10 months ago
- f710793 Add fp16 support for dequantize by Jan Eilers · 4 years, 10 months ago
- 7ff9a60 Make onnx parser to support TanH / Sigmoid / LeakyRelu layers by Tee Jung · 4 years, 10 months ago
- fcf6fd5 Fix crash issue by Tee Jung · 4 years, 10 months ago
- d94efa8 Match shape in between initializer and tensor by Tee Jung · 4 years, 10 months ago
- 584a2b8 Better error reporting for unconnected layers by Matthew Bentham · 4 years, 10 months ago
- fe414cf IVGCVSW-4050 Add backward compatibility deserialization test for ResizeBilinear by Aron Virginas-Tar · 4 years, 10 months ago
- d1f5773 IVGCVSW-3698 Add EndToEnd Layer test for ArgMinMax by Narumol Prangnawarat · 4 years, 10 months ago
- 3f4d710 Increase tolerance for bias scale quantization calculation for ResNet50v2 by ricbur01 · 4 years, 10 months ago
- 9a5f9f2 GitHub #292 Build the ML-examples using only ArmNN's public frontend API by Matteo Martincigh · 4 years, 10 months ago
- 3c9b270 Fix bug in deserializitaion of ResizeLayer by Aron Virginas-Tar · 4 years, 10 months ago
- 7be12b8 IVGCVSW-4049 Fix potential threading issue with the SendCounterPacket thread by Finn Williams · 4 years, 10 months ago
- 27dbd34 Github #220 Mention deprecated Caffe features in the Caffe parser README by Matthew Bentham · 4 years, 10 months ago
- c601aa6 GitHub #292 Move BackendRegistry.hpp to the public API by Matteo Martincigh · 4 years, 10 months ago
- d905307 IVGCVSW-3842 Add per-axis quantization support to ValidateBiasTensorQuantization() by Aron Virginas-Tar · 4 years, 10 months ago
- 9be4916 IVGCVSW-4039 AndroidQ (HAL 1.2) driver support for Fp16 by Sadik Armagan · 4 years, 10 months ago
- 94a3088 IVGCVSW-4037 Add a CreateNamedTypedChildEntity method by Narumol Prangnawarat · 4 years, 10 months ago
- d034e08 IVGCVSW-4036 Add CreateNamedTypedEntity function by Narumol Prangnawarat · 4 years, 10 months ago
- c0a87c1 IVGCVSW-3831 Add support of per-axis quantization to TensorInfo by Aron Virginas-Tar · 4 years, 10 months ago
- c040199 IVGCVSW-4035 Add a CreateTypedLabel function by Matteo Martincigh · 4 years, 10 months ago
- b3670b1 Refactor Resize layer tests by Aron Virginas-Tar · 4 years, 10 months ago
- 102cdbd IVGCVSW-4033 Provide a utility method to send the 'well known' by Matteo Martincigh · 4 years, 10 months ago
- ab84575 IVGCVSW-4031 Provide well known profiling GUIDs by Jim Flynn · 4 years, 10 months ago
- d6f26fc Fix ExecuteNetwork no longer printing out the inference results, by Matteo Martincigh · 4 years, 10 months ago
- 86324fc Refine SerializeDeserializeQuantizedLstm for the validation of by alanhsu5678 · 4 years, 10 months ago
- c34e53b Bug fix on serialization of tensor with qsymm16 type by Tee Jung · 4 years, 10 months ago
- 830101c IVGCVSW-4022 Create a DeclareLabel utility function by Matteo Martincigh · 4 years, 10 months ago
- 48623a0 IVGCVSW-4018 Move QuantizeHelper.hpp to armnnUtils by Aron Virginas-Tar · 4 years, 10 months ago
- 57d10b7 IVGCVSW-3962 Return 0 for Neon GetExportFlags() by James Conroy · 4 years, 10 months ago
- 8b20065 IVGCVSW-4028 Add TimelinePacketWriterFactory to ProfilingService by Jim Flynn · 4 years, 10 months ago