Gitiles
Code Review Sign In
review.mlplatform.org / ml / ComputeLibrary / a7a5b7b2ee6adcfe86339a402f287c4d0d368659 / tests / validation
  1. a7a5b7b COMPMID-508: Port TableLookup to new validation by Sanghoon Lee · 7 years ago
  2. 99d4f4a COMPMID-417: Fix absolute error template parameter. by Georgios Pinitas · 7 years ago
  3. bf17955 COMPMID-522 - Added support for GlobalPooling in CLPoolingLayer and CLFlattening for 3D tensor by Gian Marco Iodice · 7 years ago
  4. 583137c COMPMID-417: Add support for floats in scale. by Georgios Pinitas · 7 years ago
  5. 8b3b5fa COMPMID-417: Match tolerance for CL and NEON in Normalization layer. by Georgios Pinitas · 7 years ago
  6. 067518c COMPMID-417 - Added large shapes for CLFloor and NEFloor tests by Gian Marco Iodice · 7 years ago
  7. 6f4d49f COMPMID-504: Move NonLinearFilter to new validation by John Richardson · 7 years ago
  8. 2fe7d1c COMPMID-417 Update FIXME / INTERNAL_ONLY comments in files which need removing before releasing by Anthony Barbier · 7 years ago
  9. 24486d6 COMPMID-496: Port DepthConvert to new validation by Sanghoon Lee · 7 years ago
  10. 5ee66ea COMPMID-462: Implement TensorReshape for NEON and CL. by Georgios Pinitas · 7 years ago
  11. ce54b56 COMPMID-532: NEON ConvolutionLayer Quantised valgrind errors by Georgios Pinitas · 7 years ago
  12. 56dd726 COMPMID-448: Implement CL Quantization/Dequantization Layer. by Michele Di Giorgio · 7 years ago
  13. 1cd0d52 COMPMID-532: Disable NEON/ConvLayer/QS8 by Moritz Pflanzer · 7 years ago
  14. 898a806 COMPMID-417: Fix NEDirectConvolutionLayer by Georgios Pinitas · 7 years ago
  15. 5b61fd3 COMPMID-417: Fix validation by Moritz Pflanzer · 7 years ago
  16. f31cac1 COMPMID-417: Reduce DepthConcatenate sizes for NEON by Moritz Pflanzer · 7 years ago
  17. b2833b8 COMPMID-415 - Fixed bad_alloc in DepthConcatenate reducing the size of input tensor for the NIGHTLY tests by Gian Marco Iodice · 7 years ago
  18. 6a45048 COMPMID-526: Disable DirectConvolution tests by Moritz Pflanzer · 7 years ago
  19. fb20568 COMPMID-417: Fix DepthConcatenate validation fixture by Moritz Pflanzer · 7 years ago
  20. 72898fe COMPMID-493: Port ArithmeticSubtraction to new validation by Sanghoon Lee · 7 years ago
  21. 06b184a COMPMID-439 - Refactored NEQuantizationLayer and NEQuantizationLayer in order to support 3D input tensors by Gian Marco Iodice · 7 years ago
  22. cde1e8a COMPMID-415: Add tests for ConvolutionLayer reshaped weights by Moritz Pflanzer · 7 years ago
  23. 86b5333 COMPMID-514 (3RDPARTY_UPDATE)(DATA_UPDATE) Add support to load .npy data by SiCong Li · 7 years ago
  24. 3e05e4e COMPMID-516 Change the CL CNN validation functions to use relative by steniu01 · 7 years ago
  25. 3f0ab6e COMPMID-495: Port Box 3x3 to new validation by Abe Mbise · 7 years ago
  26. 70f8291 COMPMID-492: Port ArithmeticAddition to new validation by Sanghoon Lee · 7 years ago
  27. 732f368 COMPMID-417 - BugFix Scale - Added tolerance(1) by Isabella Gottardi · 7 years ago
  28. 172c58d COMPMID-345 Fix the failure counter wrongly logging issue by steniu01 · 7 years ago
  29. 64ebe5b COMPMID-519: Add support for Lower and Upper Bounded RELU for CL/NEON by Georgios Pinitas · 7 years ago
  30. a09de0c COMPMID-415: Rename and move tests by Moritz Pflanzer · 7 years ago
  31. 632925a COMPMID-417: Set tolerance of 1 for CL HarrisCorners by Moritz Pflanzer · 7 years ago
  32. 338b195 COMPMID-502: Move MeanStdDev to new validation by John Richardson · 7 years ago
  33. 1fab09f COMPMID-424 Implemented reference implementation, new output valid region and validation tests (NEON and CL) for Scale by Isabella Gottardi · 7 years ago
  34. 3e36369 COMPMID-358 Implement OpenCL ROI Pooling by SiCong Li · 7 years ago
  35. dc460f1 COMPMID-417: Port PoolingLayer to new validation. by Georgios Pinitas · 7 years ago
  36. 0c7614f COMPMID-431 Port OpenCL pooling layer to use fixed point by steniu01 · 7 years ago
  37. 69d3341 COMPMID-415: Move FullyConnectedLayer to new validation by Moritz Pflanzer · 7 years ago
  38. 82e70a1 COMPMID-415: Improve SimpleTensor and RawTensor by Moritz Pflanzer · 7 years ago
  39. adfccb8 COMPMID-415: Move BitwiseNot to new validation by Moritz Pflanzer · 7 years ago
  40. 0eafa68 COMPMID-415: Move BitwiseXor to new validation by Moritz Pflanzer · 7 years ago
  41. ffc1255 COMPMID-417 - BugFix Validate with valid_mask by Isabella Gottardi · 7 years ago
  42. fc2817d COMPMID-424 NEON/CL Harris Corners validation tests. by Giorgio Arena · 7 years ago
  43. bbd9fb9 COMPMID-412: Port PoolingLayer to use fixed point 16. by Michalis Spyrou · 7 years ago
  44. 6203153 COMPMID-424 Implemented reference implementation and validation tests (NEON and CL) for Warp Perspective by Isabella Gottardi · 7 years ago
  45. 4a74979 COMPMID-415: Move BitwiseOr to new validation by Moritz Pflanzer · 7 years ago
  46. 62eada2 COMPMID-415: Move BitwiseAnd to new validation by Moritz Pflanzer · 7 years ago
  47. 4dfc235 COMPMID-415: Move GEMM to new validation by Moritz Pflanzer · 7 years ago
  48. b3d2579 COMPMID-415: Move ConvolutionLayer to new validation by Moritz Pflanzer · 7 years ago
  49. 8594b11 COMPMID-424 CLMeanStdDev test completed. by Giorgio Arena · 7 years ago
  50. e3bc5c9 COMPMID-417: Fix (old) validation Tensor by Moritz Pflanzer · 7 years ago
  51. 3ce3ff4 COMPMID-415: Move DepthConcatenateLayer to new validation by Moritz Pflanzer · 7 years ago
  52. a261181 COMPMID-417 NEON/CL MeanStdDev bugfix using FillBorderKernel by Giorgio Arena · 7 years ago
  53. c51b72f COMPMID-355 Implement CL DirectConvolution1x1 by SiCong Li · 7 years ago
  54. 572ade7 COMPMID-415: Move ActivationLayer to new validation by Moritz Pflanzer · 7 years ago
  55. ef4b4ae COMPMID-438: Add support for floating point Min-Max Location layer. by Michele Di Giorgio · 7 years ago
  56. f87cc7f COMPMID-417: Port NEDirectConvolution 1x1 to QS16. by Pablo Tello · 7 years ago
  57. 02dfb2c COMPMID-457 Fix F16 NormalizationLayer CL kernel by SiCong Li · 7 years ago
  58. 8fda1cb COMPMID-421: Added FP16 support in BatchNormalizationLayer. by Pablo Tello · 7 years ago
  59. 6db73ce COMPMID-415: Move NormalizationLayer to new validation by Moritz Pflanzer · 7 years ago
  60. afde732 COMPMID-421: Added FP16 support in the Neon Locally Connected Layer. by Pablo Tello · 7 years ago
  61. f6ad98a COMPMID-415: Move SoftmaxLayer to new validation by Moritz Pflanzer · 7 years ago
  62. f856c74 COMPMID-417: Change rounding mode of half reference by Moritz Pflanzer · 7 years ago
  63. 637540a COMPMID-417: Increase F16 tolerance for CL/ConvolutionLayer by Moritz Pflanzer · 7 years ago
  64. e49e266 COMPMID-415: Use half_float library for F16 by Moritz Pflanzer · 7 years ago
  65. 27b386c COMPMID-355 Implement 3x3 CL direct convolution by steniu01 · 7 years ago
  66. 1b80b6c COMPMID-447: Support scaling factors different than 1 for QS8/QS16 NEPixelWiseMultiplication. by Michele Di Giorgio · 7 years ago
  67. 935deee COMPMID-378 CLMinMaxLocation testing completed. by Giorgio Arena · 7 years ago
  68. b49a715 COMPMID-421: Added FP16 support to Softmax. by Pablo Tello · 7 years ago
  69. 0d17614 COMPMID-421: Added FP16 support to the NEON Direct Convolution function. by Pablo Tello · 7 years ago
  70. 0c34fe2 COMPMID-421: Added FP16 support in Pooling Layer by Pablo Tello · 7 years ago
  71. d58cec0 COMPMID-415: Cleanup accessors by Moritz Pflanzer · 7 years ago
  72. fb5aabb COMPMID-415: Rename TensorLibrary to AssetsLibrary by Moritz Pflanzer · 7 years ago
  73. 07a1533 COMPMID-417 NEON MeanStdDev bugfix: added floating point validation tolerance by Giorgio Arena · 7 years ago
  74. 91654c4 COMPMID-421: Added FP16 support in ActivationLayer. by Pablo Tello · 7 years ago
  75. 2ca209e COMPMID-424 NEON MinMaxLocation test. by Giorgio Arena · 7 years ago
  76. d7a5d22 COMPMID-421: Added FP16 support to Arithmetic Subtraction. by Pablo Tello · 7 years ago
  77. 7281834 COMPMID-446: Add support for QS8/QS16 CL Arithmetic Add/Sub by Michele Di Giorgio · 7 years ago
  78. e222941 COMPMID-401: Implement FixedPointPosition conversion for NEON. by Georgios Pinitas · 7 years ago
  79. bbd3d60 COMPMID-410 Port BatchNormalization to use fixed point 16 by Michalis Spyrou · 7 years ago
  80. 172e570 COMPMID-425 Port CLBatchnormalization to support QS8/QS16 by Michalis Spyrou · 7 years ago
  81. 579c049 COMPMID-417: Add Leaky RELU support for both NEON/CL. by Georgios Pinitas · 7 years ago
  82. 81f0d15 COMPMID-444: Add support for QS8/QS16 NEON Arithmetic Add/Sub/Mul. by Michele Di Giorgio · 7 years ago
  83. 00394ae COMPMID-406: Port CLActivationLayer to use QS8/QS16. by Georgios Pinitas · 7 years ago
  84. b797fa2 COMPMID-424 - Implemented reference implementation and tests (NEON and CL) for TableLookup by Isabella Gottardi · 7 years ago
  85. ac4e873 COMPMID-417: Port DepthConcatenate to QS8/QS16 for NEON/CL. by Georgios Pinitas · 7 years ago
  86. df24618 COMPMID-421: Added FP16 suppot to NENormalizationLayer and NEPixelWiseMultiplication. by Pablo Tello · 7 years ago
  87. d1b0ecc COMPMID-421: Added FP16 support to Arithmetic Addition. by Pablo Tello · 7 years ago
  88. da37e2f COMPMID-431 Port CLDepthConvert to use 8-bit and 16-bit fixed point by steniu01 · 7 years ago
  89. 9247c92 COMPMID-428: Port NESoftmaxLayer to 16-bit fixed point. by Georgios Pinitas · 7 years ago
  90. 0979675 COMPMID-429: Port CLSoftmaxLayer to QS16. by Georgios Pinitas · 7 years ago
  91. dcdc85e COMPMID-421: Added F16 support in FC Layer. by Pablo Tello · 7 years ago
  92. fc95ed2 COMPMID-415: New framework - base framework [1/5] by Moritz Pflanzer · 7 years ago
  93. 7d323a6 COMPMID-440, COMPMID-441 - Port CLConvolutionLayer and CLFullyConnectedLayer to support 16 bit fixed point by Gian Marco Iodice · 7 years ago
  94. ab0a77e COMPMID-409: Add support for QS8 and QS16 CLPixelWiseMultiplication. by Michele Di Giorgio · 7 years ago
  95. ccc65d4 COMPMID-427: Port NEActivationLayer in 16bit fixed point. by Georgios Pinitas · 7 years ago
  96. 9502f31 COMPMID-417: Increase NEON QS16 tolerance for reciprocal by Moritz Pflanzer · 7 years ago
  97. 331fc74 COMPMID-421: Fixed compiler error for arm-v8.2-a. by Pablo Tello · 7 years ago
  98. 21efeb4 COMPMID-417: DepthConvert NEON for QS8/QS16. by Georgios Pinitas · 7 years ago
  99. 368da83 COMPMID-420, COMPMID-414 - Port CLConvolutionLayer and CLFullyConnectedLayer to use 8 bit fixed point by Gian Marco Iodice · 7 years ago
  100. 2bbd964 COMPMID-436, COMPMID-437 - Port NEConvolutionLayer & NEFullyConnectedLayer to support 16 bit fixed point by Gian Marco Iodice · 7 years ago