Gitiles
Code Review Sign In
review.mlplatform.org / ml / ComputeLibrary / e9146ed3b4ad8501cb17dfe5953ef0259f106c2e / tests
  1. b9d38ee APPBROWSER-312 Fully connected performance optimization by Frank Lei · 7 years ago
  2. 397d58a COMPMID-617: Add validate support for NEON ArithmeticLayer by Ioan-Cristian Szabo · 7 years ago
  3. c7f9b89 COMPMID-722 - Support for vector-matrix in GEMMLowp (NEON) by Gian Marco · 7 years ago
  4. 923241e APPBROWSER-314: Performance optimazation for BatchNormalizationLayer by zhenglin · 7 years ago
  5. 0a878ae COMPMID-556: Added a rounding policy to the quantize function by Jaroslaw Rzepecki · 7 years ago
  6. 8795ffb COMPMID-700: Adds CPPPermute function by Georgios Pinitas · 7 years ago
  7. 8108d2e COMPMID-718: Added winograd benchmarking tests. by Pablo Tello · 7 years ago
  8. b40879e COMPMID-556: Preserve case-sensitivity of positional arguments by Georgios Pinitas · 7 years ago
  9. 5b73ce1 APPBROWSER-313: medium value and relative standard deviation by Joel Liang · 7 years ago
  10. 5a7e776 COMPMID-556: Rename CPP folder to reference by Georgios Pinitas · 7 years ago
  11. 2ecbada IVGCVSW-656 : added support (and unit tests) for asymmetric padding in by Jaroslaw Rzepecki · 7 years ago
  12. 04a8f8c COMPMID-692 Consistent names for the interfaces by Giorgio Arena · 7 years ago
  13. 58c5794 COMPMID-706 - Add GEMMLowp output stage for scaling by a fixed point number by Gian Marco · 7 years ago
  14. 754e952 COMPMID-617: Add validate support for NEON PixelWiseMultiplication by Ioan-Cristian Szabo · 7 years ago
  15. 8951933 COMPMID-687: Winograd layer. by Pablo Tello · 7 years ago
  16. 2995f5b COMPMID-617 Add validation window to CLActivationLayer by Giorgio Arena · 7 years ago
  17. 0162436 COMPMID-684: 2D In-Map normalization support for CL by Georgios Pinitas · 7 years ago
  18. 45bcc3a COMPMID-661: QASYMM8 support for fully connected layer. by Georgios Pinitas · 7 years ago
  19. 303be90 COMPMID-617: Add validate support for NEON BatchNormalizationLayer. by Ioan-Cristian Szabo · 7 years ago
  20. 236bfe7 COMPIMID-553: MobileNet use case. by Georgios Pinitas · 7 years ago
  21. 9c450cc COMPMID-695: Update Phase and Validation Wrapping by John Richardson · 7 years ago
  22. 5420b28 COMPMID-710 - Fix CLTranspose and NETranspose when the input shape is a vector by Gian Marco · 7 years ago
  23. 6fdfaa8 COMPMID-713: Address failures in OCLGrind for CLDirectConvolution by Georgios Pinitas · 7 years ago
  24. 7062382 COMPMID-617 Add validation window to BatchNormalization, PixelwiseMultiplication, ArithmeticOps by Giorgio Arena · 7 years ago
  25. d912fd8 COMPMID-617: Add validation to NEON functions. by Georgios Pinitas · 7 years ago
  26. b6f182d3 COMPMID-556: Fix CLDepthwiseConvolution3x3 Kernel. by Georgios Pinitas · 7 years ago
  27. 2fdc409 COMPMID-592: Ported GEMMInterleave4x4 tests. by Pablo Tello · 7 years ago
  28. c23b633 COMPMID-617 Add validation window to CLNormalizationLayer by Giorgio Arena · 7 years ago
  29. 9f26b3e COMPMID-617 Add validation window to CLPoolingLayer by Giorgio Arena · 7 years ago
  30. 05288a2 COMPMID-697 - Rework GEMMLowp interface on OpenCL by Gian Marco · 7 years ago
  31. e8895f8 COMPMID-694: merge opencl_timer flag with the opencl flag by Anthony Barbier · 7 years ago
  32. 53d8c5c COMPMID-464 Implement Depthwise separable convolution on NEON by Michalis Spyrou · 7 years ago
  33. f3dfa27 COMPMID-632 Assembly: Integrate gemmlowp assembly version by Michalis Spyrou · 7 years ago
  34. f202e50 COMPMID-556 Improved indentation and error handling in format_doxygen.py by Anthony Barbier · 7 years ago
  35. dbfb31c COMPMID-556 Print tests list using printers rather than cout by Anthony Barbier · 7 years ago
  36. b7b3153 COMPMID-464 Implement Depthwise separable convolution on NEON by Michalis Spyrou · 7 years ago
  37. 02bf80d COMPMID-661: Fix scale border issue (#38) by Daniil Efremov · 7 years ago
  38. 6194145 COMPMID-694: Fix condition which decides whether or not to profile a run by Anthony Barbier · 7 years ago
  39. b28f29d COMPMID-652 - Graph examples shouldn't need to link against OpenCL by Isabella Gottardi · 7 years ago
  40. a3b1b46 COMPMID-667: Add validation static method to NEON GEMMlowp by Georgios Pinitas · 7 years ago
  41. fc35b51 COMPMID-580 - Implement reference and CL/NEON validation for Remap by Sanghoon Lee · 7 years ago
  42. 37908d9 COMPMID-560 - Validation mismatches Gaussian Pyramid Half Scale by Gian Marco · 7 years ago
  43. 93dcd83 COMPMID-645: MobileNet network and benchmark by Georgios Pinitas · 7 years ago
  44. 6b77e91 COMPMID-665 - NEON: Add QASYMM8 in place Activation layer by Gian Marco · 7 years ago
  45. 30902ed COMPMID-617: Add validation methods to ML CL functions. by Georgios Pinitas · 7 years ago
  46. 77f0f87 COMPMID-621: Disable colours when printing to file by Anthony Barbier · 7 years ago
  47. d7295b7 COMPMID-661: Add QASYMM8 support (and basic tests) to CLDepthwiseConvolution3x3 kernel (#28) by Dmitry Savenko · 7 years ago
  48. 540d008 COMPMID-556: Fixes bias in CLDirectConvolutionLayer to be int32. by Georgios Pinitas · 7 years ago
  49. 43ce898 COMPMID-670 - Extend Sobel tests by Isabella Gottardi · 7 years ago
  50. c1294fa COMPMID-494: Fixing values to const by Sanghoon Lee · 7 years ago
  51. 41caa62 COMPMID-683: Normalization layer API clarification. by Georgios Pinitas · 7 years ago
  52. 181e651 COMPMID-675: NEGEMMLowp Assembly Integration by Pablo Tello · 7 years ago
  53. bc8fb06 COMPMID-556 Pretty-printing is enabled twice by default by Anthony Barbier · 7 years ago
  54. 7a49c79 COMPMID-661: issue# 23 Scale border fix (#26) by Daniil Efremov · 7 years ago
  55. 283c179 COMPMID-676: Rework TensorInfo building by Georgios Pinitas · 7 years ago
  56. ce58a9f COMPMID-622 Let the user choose the units for the instruments by Giorgio Arena · 7 years ago
  57. 82afedf COMPMID-678 Align Convolution Interfaces by Giorgio Arena · 7 years ago
  58. 02aabcc COMPMID-583 - Implemented reference implementation and validation tests (NEON and CL) for Histogram by Isabella Gottardi · 7 years ago
  59. 2f8e077 COMPMID-556: Don't measure performance for the first run by Anthony Barbier · 7 years ago
  60. 4c2dd54 COMPMID-671: Add global pooling layer support. by Georgios Pinitas · 7 years ago
  61. fa33043 COMPMID-556: Fix double pretty printer registration. by Georgios Pinitas · 7 years ago
  62. e75a02b COMPMID-675 - Reworked NEGEMMLowp interface/function by Gian Marco · 7 years ago
  63. 87f21cd COMPMID-556 Updated libnpy.hpp by Anthony Barbier · 7 years ago
  64. 5edbd1c COMPMID-556: Add support to build arm64-v8.2-a for Android platform (clang compiler) by Ioan-Cristian Szabo · 7 years ago
  65. 84b51ad COMPMID-666: Adds the ability to import backing memory in a Tensor(CPU). by Georgios Pinitas · 7 years ago
  66. c5d5439 COMPMID-621 Add output options for json and pretty files by Giorgio Arena · 7 years ago
  67. f450caa COMPMID-661: softmax-uint8 implementation (#16) by Chunosov · 7 years ago
  68. 7068f99 COMPMID-631: Merge branches/gles_compute branch by Anthony Barbier · 7 years ago
  69. d607375 COMPMID-663: Fixed JSON writer for raw_data by Anthony Barbier · 7 years ago
  70. 1c52992 COMPMID-562: Port Schaar to new validation by John Richardson · 7 years ago
  71. 7d6bf6a COMPMID-650 Check we have all the DirectConvolution benchmarks by Giorgio Arena · 7 years ago
  72. ea1c950 COMPMID-556: Allow building only specific validation tests using the option variable test_filter. by Pablo Tello · 7 years ago
  73. 4a4a164 COMPMID-556: When an EnumListOption contains some invalid values: still keep the valid ones by Anthony Barbier · 7 years ago
  74. 6e43349 COMPMID-663 Adding instrument to return timestamps of clGetEventProfilingInfo by Anthony Barbier · 7 years ago
  75. 9c45f56 COMPMID-556 - Added 5x5 Direct Convolution benchmark for AlexNet by Gian Marco · 7 years ago
  76. ab14c15 COMPMID-663: Reworked / cleaned up instuments' measurements by Anthony Barbier · 7 years ago
  77. 33da05b COMPMID-556 - Reduced number of batches to 2 for VGG-16 tests by Gian Marco · 7 years ago
  78. 764f39e COMPMID-556 - Fix Warp Perspective validation by Isabella Gottardi · 7 years ago
  79. eed841c COMPMID-661: Add QAsymm8 for Reshape (#29) by Daniil Efremov · 7 years ago
  80. af6204c COMPMID-661: Add avgpool-uint8 support. Optimize avgpool-fp32 for Bifrost. (#13) by Anton Lokhmotov · 7 years ago
  81. 3a873a5 COMPMID-556 - Fixed tests for AlexNet by Gian Marco · 7 years ago
  82. 1a39f6d COMPMID-669 - Add validation for different border modes by Gian Marco · 7 years ago
  83. f9d3a0a COMPMID-617: Add validation functions. by Georgios Pinitas · 7 years ago
  84. d6afedc COMPMID-661: softmax-fp32 optimisation (#14) by Chunosov · 7 years ago
  85. 6ff12a0 COMPMID-662: Integrated the new a64_s8_gemm_12x8 + dot product kernel into ACL. by Pablo Tello · 7 years ago
  86. d621bca COMPMID-661: directconv-uint8 (#20) by Chunosov · 7 years ago
  87. 5a99ddf COMPMID-590: Add transpose_validation to the test framework. by Ioan-Cristian Szabo · 7 years ago
  88. 3faea25 COMPMID-617: Adds validation to CLPoolingLayer by Georgios Pinitas · 7 years ago
  89. b5908c2 COMPMID-653 - Arithmetic Subtraction, add support different datatype by Isabella Gottardi · 7 years ago
  90. ab18212 COMPMID-616 - Optimizing GEMMLowp on NEON intrinsics by Gian Marco Iodice · 7 years ago
  91. adaae7e COMPMID-647: Exclude padding pixels from averaging factor. by Georgios Pinitas · 7 years ago
  92. 7362f0d COMPMID-464 Implement Depthwise convolution 3x3 on NEON by Michalis Spyrou · 7 years ago
  93. 3c5f949 COMPMID-575: Port Magnitude to new validation by John Richardson · 7 years ago
  94. 63e5041 COMPMID-576: Port Phase to new validation by John Richardson · 7 years ago
  95. 2d09993 COMPMID-621 Support several printers for tests by Giorgio Arena · 7 years ago
  96. 5cbd20f COMPMID-556: Autoconfigure support in CLDepthwiseConvolution. by Georgios Pinitas · 7 years ago
  97. 0c1d148 COMPMID-623 Make command line options case insensitive by Giorgio Arena · 7 years ago
  98. 33fd07b COMPMID-634: Enable clang with libc++ to compile for Android (32 and 64 bits) by Ioan-Cristian Szabo · 7 years ago
  99. daaa1fa COMPMID-642: Fixed mismatches in NEDeconvolutionLayer. by Pablo Tello · 7 years ago
  100. 81a26ad COMPMID-643: Add bias to CLDepthwiseConvolution. by Georgios Pinitas · 7 years ago