Gitiles
Code Review Sign In
review.mlplatform.org / ml / ComputeLibrary / 218cc52ce6f0ebf052346650d1b2004e7201f348 / tests
  1. 6f49330 COMPMID-475 Enable more data format in the benchmark test by steniu01 · 7 years ago
  2. 6106a4d COMPMID-415: Use absolute and relative tolerance by Moritz Pflanzer · 7 years ago
  3. d8e765b COMPMID-472 : Implement Floor for CL and NEON. by Georgios Pinitas · 7 years ago
  4. e33eb64 COMPMID-415: Fix new validation by Moritz Pflanzer · 7 years ago
  5. b3d2579 COMPMID-415: Move ConvolutionLayer to new validation by Moritz Pflanzer · 7 years ago
  6. 8594b11 COMPMID-424 CLMeanStdDev test completed. by Giorgio Arena · 7 years ago
  7. e3bc5c9 COMPMID-417: Fix (old) validation Tensor by Moritz Pflanzer · 7 years ago
  8. 3ce3ff4 COMPMID-415: Move DepthConcatenateLayer to new validation by Moritz Pflanzer · 7 years ago
  9. a261181 COMPMID-417 NEON/CL MeanStdDev bugfix using FillBorderKernel by Giorgio Arena · 7 years ago
  10. a629da1 COMPMID-458 add direct convolution to benchmark by steniu01 · 7 years ago
  11. c51b72f COMPMID-355 Implement CL DirectConvolution1x1 by SiCong Li · 7 years ago
  12. 572ade7 COMPMID-415: Move ActivationLayer to new validation by Moritz Pflanzer · 7 years ago
  13. ef4b4ae COMPMID-438: Add support for floating point Min-Max Location layer. by Michele Di Giorgio · 7 years ago
  14. f87cc7f COMPMID-417: Port NEDirectConvolution 1x1 to QS16. by Pablo Tello · 7 years ago
  15. 6c92834 COMPMID-413: Add support for QS8 and QS16 CLNormalizationLayer. by Michele Di Giorgio · 7 years ago
  16. d5e65c7 COMPMID-456: Add support for QS16 NEON Normalization Layer. by Michele Di Giorgio · 7 years ago
  17. 02dfb2c COMPMID-457 Fix F16 NormalizationLayer CL kernel by SiCong Li · 7 years ago
  18. 8fda1cb COMPMID-421: Added FP16 support in BatchNormalizationLayer. by Pablo Tello · 7 years ago
  19. 6db73ce COMPMID-415: Move NormalizationLayer to new validation by Moritz Pflanzer · 7 years ago
  20. afde732 COMPMID-421: Added FP16 support in the Neon Locally Connected Layer. by Pablo Tello · 7 years ago
  21. f6ad98a COMPMID-415: Move SoftmaxLayer to new validation by Moritz Pflanzer · 7 years ago
  22. f5d76f2 COMPMID-415: Set rounding mode for half reference by Moritz Pflanzer · 7 years ago
  23. f856c74 COMPMID-417: Change rounding mode of half reference by Moritz Pflanzer · 7 years ago
  24. ec2de0f COMPMID-415: Allow multiple ids for filter-id by Moritz Pflanzer · 7 years ago
  25. b9e9cff COMPMID-415: Print tolerance on error by Moritz Pflanzer · 7 years ago
  26. fa81165 COMPMID-415: Add --stop-on-error by Moritz Pflanzer · 7 years ago
  27. 637540a COMPMID-417: Increase F16 tolerance for CL/ConvolutionLayer by Moritz Pflanzer · 7 years ago
  28. e49e266 COMPMID-415: Use half_float library for F16 by Moritz Pflanzer · 7 years ago
  29. 27b386c COMPMID-355 Implement 3x3 CL direct convolution by steniu01 · 7 years ago
  30. 1b80b6c COMPMID-447: Support scaling factors different than 1 for QS8/QS16 NEPixelWiseMultiplication. by Michele Di Giorgio · 7 years ago
  31. 2ac5040 COMPMID-415: Add log level by Moritz Pflanzer · 7 years ago
  32. bf234e0 COMPMID-415: Add expected failures and disabled tests by Moritz Pflanzer · 7 years ago
  33. c7d1503 COMPMID-415: Build new validation by Moritz Pflanzer · 7 years ago
  34. 935deee COMPMID-378 CLMinMaxLocation testing completed. by Giorgio Arena · 7 years ago
  35. b49a715 COMPMID-421: Added FP16 support to Softmax. by Pablo Tello · 7 years ago
  36. 0aea890 COMPMID-450 Add SqueezeNetV1.1 benchmark tests by SiCong Li · 7 years ago
  37. 0d17614 COMPMID-421: Added FP16 support to the NEON Direct Convolution function. by Pablo Tello · 7 years ago
  38. 0c34fe2 COMPMID-421: Added FP16 support in Pooling Layer by Pablo Tello · 7 years ago
  39. d58cec0 COMPMID-415: Cleanup accessors by Moritz Pflanzer · 7 years ago
  40. 81527bf COMPMID-415: Don't use regex for filter by test id by Moritz Pflanzer · 7 years ago
  41. fb5aabb COMPMID-415: Rename TensorLibrary to AssetsLibrary by Moritz Pflanzer · 7 years ago
  42. 07a1533 COMPMID-417 NEON MeanStdDev bugfix: added floating point validation tolerance by Giorgio Arena · 7 years ago
  43. ede513c COMPMID-415: Rename system tests by Moritz Pflanzer · 7 years ago
  44. 40b2927 COMPMID-421: Enabled FP16 in the neon ConvolutionLayer benchmark tests. by Pablo Tello · 7 years ago
  45. 91654c4 COMPMID-421: Added FP16 support in ActivationLayer. by Pablo Tello · 7 years ago
  46. ec69f93 COMPMID-415: Add MatrixMultiply benchmark by Moritz Pflanzer · 7 years ago
  47. b6c8d24 COMPMID-415: Use templates for data arguments by Moritz Pflanzer · 7 years ago
  48. c87fbf8 COMPMID-415: Simplify test names by Moritz Pflanzer · 7 years ago
  49. db33d6a COMPMID-415: Remove DEMO directory by Moritz Pflanzer · 7 years ago
  50. aab4354 COMPMID-415: Don't require assets for --list-tests by Moritz Pflanzer · 7 years ago
  51. 15d5ac8 COMPMID-415 Fix issue with OpenCL examples by Anthony Barbier · 7 years ago
  52. 2ca209e COMPMID-424 NEON MinMaxLocation test. by Giorgio Arena · 7 years ago
  53. d03b00a COMPMID-415: Fix dataset modes by Moritz Pflanzer · 7 years ago
  54. ee493ae COMPMID-415: Port benchmark tests and remove google benchmark by Moritz Pflanzer · 7 years ago
  55. d7a5d22 COMPMID-421: Added FP16 support to Arithmetic Subtraction. by Pablo Tello · 7 years ago
  56. 7281834 COMPMID-446: Add support for QS8/QS16 CL Arithmetic Add/Sub by Michele Di Giorgio · 7 years ago
  57. e222941 COMPMID-401: Implement FixedPointPosition conversion for NEON. by Georgios Pinitas · 7 years ago
  58. bbd3d60 COMPMID-410 Port BatchNormalization to use fixed point 16 by Michalis Spyrou · 7 years ago
  59. 172e570 COMPMID-425 Port CLBatchnormalization to support QS8/QS16 by Michalis Spyrou · 7 years ago
  60. 579c049 COMPMID-417: Add Leaky RELU support for both NEON/CL. by Georgios Pinitas · 7 years ago
  61. 81f0d15 COMPMID-444: Add support for QS8/QS16 NEON Arithmetic Add/Sub/Mul. by Michele Di Giorgio · 7 years ago
  62. 00394ae COMPMID-406: Port CLActivationLayer to use QS8/QS16. by Georgios Pinitas · 7 years ago
  63. b797fa2 COMPMID-424 - Implemented reference implementation and tests (NEON and CL) for TableLookup by Isabella Gottardi · 7 years ago
  64. ac4e873 COMPMID-417: Port DepthConcatenate to QS8/QS16 for NEON/CL. by Georgios Pinitas · 7 years ago
  65. df24618 COMPMID-421: Added FP16 suppot to NENormalizationLayer and NEPixelWiseMultiplication. by Pablo Tello · 7 years ago
  66. d1b0ecc COMPMID-421: Added FP16 support to Arithmetic Addition. by Pablo Tello · 7 years ago
  67. da37e2f COMPMID-431 Port CLDepthConvert to use 8-bit and 16-bit fixed point by steniu01 · 7 years ago
  68. 9247c92 COMPMID-428: Port NESoftmaxLayer to 16-bit fixed point. by Georgios Pinitas · 7 years ago
  69. 0979675 COMPMID-429: Port CLSoftmaxLayer to QS16. by Georgios Pinitas · 7 years ago
  70. dcdc85e COMPMID-421: Added F16 support in FC Layer. by Pablo Tello · 7 years ago
  71. fc95ed2 COMPMID-415: New framework - base framework [1/5] by Moritz Pflanzer · 7 years ago
  72. 7d323a6 COMPMID-440, COMPMID-441 - Port CLConvolutionLayer and CLFullyConnectedLayer to support 16 bit fixed point by Gian Marco Iodice · 7 years ago
  73. ab0a77e COMPMID-409: Add support for QS8 and QS16 CLPixelWiseMultiplication. by Michele Di Giorgio · 7 years ago
  74. ccc65d4 COMPMID-427: Port NEActivationLayer in 16bit fixed point. by Georgios Pinitas · 7 years ago
  75. 9502f31 COMPMID-417: Increase NEON QS16 tolerance for reciprocal by Moritz Pflanzer · 7 years ago
  76. 331fc74 COMPMID-421: Fixed compiler error for arm-v8.2-a. by Pablo Tello · 7 years ago
  77. 21efeb4 COMPMID-417: DepthConvert NEON for QS8/QS16. by Georgios Pinitas · 7 years ago
  78. 368da83 COMPMID-420, COMPMID-414 - Port CLConvolutionLayer and CLFullyConnectedLayer to use 8 bit fixed point by Gian Marco Iodice · 7 years ago
  79. 2bbd964 COMPMID-436, COMPMID-437 - Port NEConvolutionLayer & NEFullyConnectedLayer to support 16 bit fixed point by Gian Marco Iodice · 7 years ago
  80. 8a38369 COMPMID-434 - Port CLGEMM to support 16 bit fixed point by Gian Marco Iodice · 7 years ago
  81. bdb6b0b COMPMID-433 - Port NEGEMM to support 16 bit fixed point by Gian Marco Iodice · 7 years ago
  82. ac69aa1 COMPMID-418 Add check and fix comments after preprocessor conditions by Anthony Barbier · 7 years ago
  83. 05da6dd COMPMID-417: Remove val_to_string by Moritz Pflanzer · 7 years ago
  84. 221f381 COMPMID-421: Fixed FP16 support in Neon GEMM. by Pablo Tello · 7 years ago
  85. 6410fb2 COMPMID-417: Revert invsqrt validation implementation. by Georgios Pinitas · 7 years ago
  86. d7e8281 COMPMID-408 Create OpenCL complex math functions for 8 bit fixed point arithmetic. by Michalis Spyrou · 7 years ago
  87. 13edbff COMPMID-432 - Extended Convolution Layer to support rectangular kernels by Gian Marco Iodice · 7 years ago
  88. 238cfc0 COMPMID-417: Fix broken build after rebase gone wrong by Moritz Pflanzer · 7 years ago
  89. 3a3066b COMPMID-411 - Port CLGEMM to support 8 bit fixed point by Gian Marco Iodice · 7 years ago
  90. 94450f1 COMPMID-417: Use a common create_tensor function by Moritz Pflanzer · 7 years ago
  91. d4f8c27 COMPMID-417: Include std::vector where needed. by Georgios Pinitas · 7 years ago
  92. 997aba2 COMPMID-421: Fixed a problem in Convolution Layer reference values for FP16. by Pablo Tello · 7 years ago
  93. 7b7858d COMPMID-359: Implement NEON ROIPoolingLayer by Georgios Pinitas · 7 years ago
  94. d0ae8b8 COMPMID-417: Extract common toolchain support file by Moritz Pflanzer · 7 years ago
  95. 0a8334c COMPMID-400 Add support for 16 bit fixed point arithmetic. by Michalis Spyrou · 7 years ago
  96. e5f8fd6 COMPMID-423: Port CLSoftmaxLayer to QS8 by Georgios Pinitas · 7 years ago
  97. 443c8b9 COMPMID-417: Move ActivationLayer tests to boost by Moritz Pflanzer · 7 years ago
  98. 7a03575 COMPMID-424 Clean up validation tests for 2D spatial filter functions by SiCong Li · 7 years ago
  99. 4e28869 COMPMID-417 - Adding support for rectangular kernels by Gian Marco Iodice · 7 years ago
  100. 3b77e9d COMPMID-378 - Implemented reference implementation and tests (NEON and CL) for Non Linear Filter by Isabella Gottardi · 7 years ago