Gitiles
Code Review Sign In
review.mlplatform.org / ml / armnn / refs/heads/experimental/pyarmnn
  1. 245d64c Work in progress of python bindings for Arm NN by Matthew Bentham · 4 years, 6 months ago experimental/pyarmnn
  2. 88d5f9f MLCE-143 Fixed driver crash during CTS tests by Mike Kelly · 4 years, 6 months ago
  3. df31cfe IVGCVSW-4070 Implement "send post-optimized network structure" by Narumol Prangnawarat · 4 years, 6 months ago
  4. a68d853 IVGCVSW-3860 Per-channel QSymm8 support of DepthwiseConvolution2d in Cl by Teresa Charlin · 4 years, 6 months ago
  5. 2ba48d2 IVGCVSW-4118 Fix long unit test execution by Colm Donelan · 4 years, 6 months ago
  6. e011d20 IVGCVSW-4209 Create a public API for the ArmNN Utils by Matteo Martincigh · 4 years, 6 months ago
  7. 2e25927 Github #306 Treat data_format attribute as optional in TfParser::ParseFusedBatchNorm() by Aron Virginas-Tar · 4 years, 6 months ago
  8. 2445744 IVGCVSW-3864 Add support for per-channel QSymm8 DepthwiseConvolution2d to Neon backend by Aron Virginas-Tar · 4 years, 6 months ago
  9. 1571700 Make the profiling GUID test independent from random events by Matteo Martincigh · 4 years, 6 months ago
  10. 76c50d8 Remove const type qualifiers with no effect by Matteo Martincigh · 4 years, 6 months ago
  11. 9820d30 MLCE-115 Remove redundant error checking in CL backend by Matthew Bentham · 4 years, 6 months ago
  12. 6d3d205 Github #274 Use non-deprecated path to boost header by Matthew Bentham · 4 years, 6 months ago
  13. dd6804b IVGCVSW-4170 Also convert constants to FP16 when model converted by Derek Lamberti · 4 years, 6 months ago
  14. 710f664 IVGCVSW-4148 Extend reporting of quant multiplier > 1 as unsupported on ACL to per-axis case by Aron Virginas-Tar · 4 years, 6 months ago
  15. 899f64f IVGCVSW-3859 Per-channel QSymm8 support of Convolution2d in Cl by Keith Davis · 4 years, 6 months ago
  16. e9323ec Add IsQuantizeType(DataType) for use in validation functions by Aron Virginas-Tar · 4 years, 6 months ago
  17. 94c4fef IVGCVSW-3728 Add CL workload for Slice by Aron Virginas-Tar · 4 years, 6 months ago
  18. 21fc28b IVGCVSW-3866 Add support for per-channel QSymm8 Convolution2d to Neon backend by Aron Virginas-Tar · 4 years, 6 months ago
  19. 9b6d424 IVGCVSW-4174 Update adb version in the BuildGuideAndroidNDK.md by Nikhil Raj · 4 years, 6 months ago
  20. e131a0b IVGCVSW-4158 FP16 Mobilenet V1 and V2 30% regression on ArmNN on Mate20 by Sadik Armagan · 4 years, 6 months ago
  21. 3a93dfa Github #251 Surround local structs with anonymous namespace by Matthew Bentham · 4 years, 6 months ago
  22. b86a382 IVGCVSW-4148 Report quant multiplier > 1 as unsupported for ACL by James Conroy · 4 years, 7 months ago
  23. 4cace32 IVGCVSW-4124 Replacing the "sleep_for" loop from FileOnlyProfilingConnection by Colm Donelan · 4 years, 7 months ago
  24. cf7c1c6 IVGCVSW-4151 HAL 1_2 Dequantize FP32 Per Channel Tests on CpuAcc Failing by Sadik Armagan · 4 years, 7 months ago
  25. 234d525 IVGCVSW-4070 Add CreatedNamedTypeEntity and CreateNamedTypedChildEntity by Narumol Prangnawarat · 4 years, 7 months ago
  26. 434de54 Revert "Only enable mixed precision FP16 pooling for Android Q" by Kevin May · 4 years, 7 months ago
  27. ba424d2 IVGCVSW-1530 Add TfLite slice parser and fix transpose perm vector creation by josh minor · 4 years, 7 months ago
  28. 52ec346 IVGCVSW-3697 Add check for ArgMinMax QAsymm8 to ClLayerSupport by Francis Murtagh · 4 years, 7 months ago
  29. 47e863d IVGCVSW-4077 Fix issue when NEON import disabled by James Conroy · 4 years, 7 months ago
  30. 85ad78c IVGCVSW-4068 Add Guid to Workload by Narumol Prangnawarat · 4 years, 7 months ago
  31. 036f02d IVGCVSW-3729 Added neon slice workload and supporting neon layer tests by josh minor · 4 years, 7 months ago
  32. 49d0f12 MLCE-144 Cts NNAPI test cases failed by Mike Kelly · 4 years, 7 months ago
  33. f83b114 IVGCVSW-4116 Update ACL pin to the 19.11 release branch by Kevin May · 4 years, 7 months ago
  34. b0dc601 IVGCVSW-4062 Update Readme for 19.11 by Nikhil Raj · 4 years, 7 months ago
  35. dbdd1b4 IVGCVSW-3980 Implementation of Guid generator by Narumol Prangnawarat · 4 years, 7 months ago
  36. aad2fe4 Fix quantizer crash by zero tensor by Tee Jung · 4 years, 7 months ago
  37. d9d6371 IVGCVSW-4117 Update version number to 19.11 by Aron Virginas-Tar · 4 years, 7 months ago
  38. caf2bdd Fix possible crash in case of zero dimension tensor in the ONNX parser by Tee Jung · 4 years, 7 months ago
  39. 17d8d85 IVGCVSW-3486 Add clipping parameter validation in LstmQueueDescriptor by janeil01 · 4 years, 7 months ago
  40. 0270524 IVGCVSW-4129 Fix thread starvation due to low capture periods by Colm Donelan · 4 years, 7 months ago
  41. 9723d02 IVGCVSW-4074 Send Timeline message in RequestCounterDirectoryCommandHandler by Matteo Martincigh · 4 years, 7 months ago
  42. 87972be IVGCVSW-4119 Fix FP16 to FP32 fallback mechanism in optimizer to work with Dequantize by Aron Virginas-Tar · 4 years, 7 months ago
  43. 5716de2 IVGCVSW-4140 Report per-axis quantization as unsupported for DepthwiseConvolution on ACL backends by Aron Virginas-Tar · 4 years, 7 months ago
  44. cdfb941 IVGCVSW-4073 Send stream info in the ConnectionAcknowledgedCommandHandler by Matteo Martincigh · 4 years, 7 months ago
  45. 34a407d IVGCVSW-4072 Add stream header to Timeline Message Directory packet by Matteo Martincigh · 4 years, 7 months ago
  46. 30db8ad NNXSW-1853 Change SubgraphViewSelector algorithm by Rob Hughes · 4 years, 7 months ago
  47. 721b82f Print CMake messages on stdout rather than stderr by Rob Hughes · 4 years, 7 months ago
  48. db1a283 Add FP16 support to DebugWorkload by Aron Virginas-Tar · 4 years, 7 months ago
  49. 60538ad Only enable mixed precision FP16 pooling for Android Q by Derek Lamberti · 4 years, 7 months ago
  50. f4c502f Fix redundancy in call to configure() in ACL DepthwiseConvolution workloads by Aron Virginas-Tar · 4 years, 7 months ago
  51. 9313895 Add SpaceToDepth to GetLayerTypeAsCString() by Aron Virginas-Tar · 4 years, 7 months ago
  52. e3803ea CL & Neon workload factories inherit from WorkloadFactoryBase by Derek Lamberti · 4 years, 7 months ago
  53. 199c98e Fix link error due to pthread being linked in the wrong order by Rob Hughes · 4 years, 7 months ago
  54. 270233f Fix a few compile errors: by Rob Hughes · 4 years, 7 months ago
  55. b5b3b35 IVGCVSW-3697 Add utility function to get ArgMinMaxFunction as string by Francis Murtagh · 4 years, 7 months ago
  56. 68a4dbc IVGCVSW-4053 Enable ArgMinMax EndToEndTest for NEON/CL by James Conroy · 4 years, 7 months ago
  57. 1939df5 IVGCVSW-4128 Add Signed32 to supported input types for Ref ArgMinMax by Francis Murtagh · 4 years, 7 months ago
  58. 2dc0572 IVGCVSW-3695 Add CL ArgMinMax workload by James Conroy · 4 years, 9 months ago
  59. 663c184 IVGCVSW-4051 Update ACL pin to 94e0cf960ea6116eb57fa88d9b951f859b52c602 by James Conroy · 4 years, 7 months ago
  60. d8df026 IVGCVSW-4079 Add support of per-axis quantization to DepthwiseConvolution2d by Teresa Charlin · 4 years, 7 months ago
  61. 99d9d4a IVGCVSW-4069 Add ProfilingGuid to Network by Jan Eilers · 4 years, 7 months ago
  62. 94d3b93 IVGCVSW-3839 Add support of per-axis quantization to reference TransposeConvolution2d by Aron Virginas-Tar · 4 years, 7 months ago
  63. 62cdb08 IVGCVSW-4064 ArmNN Master fails due to an error in RefArgMaxAxis2Uint8Test by Francis Murtagh · 4 years, 7 months ago
  64. 07f25e0 IVGCVSW-4104 Report Conv2d per-axis quantization unsupported on ACL backends by Aron Virginas-Tar · 4 years, 7 months ago
  65. 3fec1ea IVGCVSW-4067 Change LayerGuid to use ProfilingGuid by janeil01 · 4 years, 7 months ago
  66. ffab16f IVGCVSW-4077 Disable NEON memory import by James Conroy · 4 years, 7 months ago
  67. 55e488a Add profiling includes to Android.mk by janeil01 · 4 years, 7 months ago
  68. 130ec60 IVGCVSW-4108 Fixed invalid data type exception by Mike Kelly · 4 years, 7 months ago
  69. 70f609b MLCE-144 Fix cts MAX_POOL_2D_V1_0 tests by Finn Williams · 4 years, 7 months ago
  70. 8bf442e IVGCVSW-4107 Fix bug in ProfilingConnectionDumpToFileDecoratorTests by Aron Virginas-Tar · 4 years, 7 months ago
  71. c4946c7 IVGCVSW-4102 Move ProfilingGuid to public interface by janeil01 · 4 years, 7 months ago
  72. e63a026 IVGCVSW-3951 Create the timeline decoder by Finn Williams · 4 years, 7 months ago
  73. 362e032 Escape angle brackets in dot file labels by Rob Hughes · 4 years, 7 months ago
  74. 5dc816e IVGCVSW-4065 Add a RecordEvent function by Matteo Martincigh · 4 years, 7 months ago
  75. 5edc881 IVGCVSW-3837 Add support for per-axis quantization to reference Convolution2d workload by Aron Virginas-Tar · 4 years, 7 months ago
  76. ec33a91 IVGCVSW-4038 Convert Strided_Slice Shrink_Axis_Mask Parameter to ACL format by Francis Murtagh · 4 years, 7 months ago
  77. 3201eea IVGCVSW-3444 File Only Profiling Connection by Keith Davis · 4 years, 7 months ago
  78. fe2e2cb GitHub #294 Add sample serialized graph by Tee Jung · 4 years, 7 months ago
  79. 2321443 Rename Optimize's errMessages to messages by Rob Hughes · 4 years, 7 months ago
  80. 378bbfc IVGCVSW-4065 Use platform-specific thread id size in Timeline packets by Matteo Martincigh · 4 years, 7 months ago
  81. 2ffcc41 IVGCVSW-4065 Refactor the IPacketBuffer smart pointers by Matteo Martincigh · 4 years, 7 months ago
  82. b67f957 IVGCVSW-3836 Add support for Int32 per-axis scales by Aron Virginas-Tar · 4 years, 7 months ago
  83. 13b653f IVGCVSW-3843 Add support of per-axis quantization to BuildArmComputeTensorInfo by Aron Virginas-Tar · 4 years, 7 months ago
  84. 5236e1d IVGCVSW-3835 Create Encoder and Decoder for QSymm8PerAxis by Keith Davis · 4 years, 7 months ago
  85. f710793 Add fp16 support for dequantize by Jan Eilers · 4 years, 7 months ago
  86. 7ff9a60 Make onnx parser to support TanH / Sigmoid / LeakyRelu layers by Tee Jung · 4 years, 7 months ago
  87. fcf6fd5 Fix crash issue by Tee Jung · 4 years, 7 months ago
  88. d94efa8 Match shape in between initializer and tensor by Tee Jung · 4 years, 7 months ago
  89. 584a2b8 Better error reporting for unconnected layers by Matthew Bentham · 4 years, 7 months ago
  90. fe414cf IVGCVSW-4050 Add backward compatibility deserialization test for ResizeBilinear by Aron Virginas-Tar · 4 years, 7 months ago
  91. d1f5773 IVGCVSW-3698 Add EndToEnd Layer test for ArgMinMax by Narumol Prangnawarat · 4 years, 7 months ago
  92. 3f4d710 Increase tolerance for bias scale quantization calculation for ResNet50v2 by ricbur01 · 4 years, 7 months ago
  93. 9a5f9f2 GitHub #292 Build the ML-examples using only ArmNN's public frontend API by Matteo Martincigh · 4 years, 7 months ago
  94. 3c9b270 Fix bug in deserializitaion of ResizeLayer by Aron Virginas-Tar · 4 years, 7 months ago
  95. 7be12b8 IVGCVSW-4049 Fix potential threading issue with the SendCounterPacket thread by Finn Williams · 4 years, 7 months ago
  96. b4e6720 Github #277 Add option to use shared boost libraries by Matthew Bentham · 4 years, 7 months ago
  97. 27dbd34 Github #220 Mention deprecated Caffe features in the Caffe parser README by Matthew Bentham · 4 years, 8 months ago
  98. c601aa6 GitHub #292 Move BackendRegistry.hpp to the public API by Matteo Martincigh · 4 years, 7 months ago
  99. d905307 IVGCVSW-3842 Add per-axis quantization support to ValidateBiasTensorQuantization() by Aron Virginas-Tar · 4 years, 7 months ago
  100. 9be4916 IVGCVSW-4039 AndroidQ (HAL 1.2) driver support for Fp16 by Sadik Armagan · 4 years, 7 months ago