Gitiles
Code Review Sign In
review.mlplatform.org / ml / ComputeLibrary / 933fe86bdc0603c5350fa131df72549933632233 / tests
  1. 933fe86 COMPMID-927: Adding support for FP16 in CLDepthwiseConvolutionLayer3x3 by Michele Di Giorgio · 6 years ago
  2. 898d399 COMPMID-945: Fix GEMM CL FP32 mismatch by Michele Di Giorgio · 6 years ago
  3. 9414f64 COMPMID-582: Add validation to channel_extract kernels. by Ioan-Cristian Szabo · 7 years ago
  4. 6acc6ad COMPMID-846: Create a ConvolutionLayer for NEON by Isabella Gottardi · 6 years ago
  5. 51b074a COMPMID-764 Removed reciprocal QS tests by Anthony Barbier · 6 years ago
  6. cac4a2e COMPMID-765 - Fix get_convolution_method in order to return the correct method. by Isabella Gottardi · 6 years ago
  7. 287b570 COMPMID-853 Use tile 2 for CL depthwise convolution QASYM8 by Giorgio Arena · 6 years ago
  8. d267b05 COMPMID-784: Fixed SAME paddding in WinogradLayer by Pablo Tello · 6 years ago
  9. 1fbb812 Revert "COMPMID-582: Add validation to channel_extract kernels." by Anthony Barbier · 6 years ago
  10. 562fe0f COMPMID-578: Faster common keypoint validation routine for FAST and Harris corners by Abe Mbise · 6 years ago
  11. f07d28d COMPMID-845: Create a ConvolutionLayer for CL by Isabella Gottardi · 6 years ago
  12. 7567f5f COMPMID-828 - Add support for pool widths 4, 5 & 6 and for non square data sizes - Part 2 (NEON) by Isabella Gottardi · 6 years ago
  13. f6c572c COMPMID-784: Productise Winograd. by Pablo Tello · 6 years ago
  14. 91d20d9 COMPMID-582: Add validation to channel_extract kernels. by Ioan-Cristian Szabo · 7 years ago
  15. 4402cb9 COMPMID-905 Optimize CLSoftmaxLayer for QASYMM8 by Giorgio Arena · 6 years ago
  16. de5a1cc COMPMID-856: CL Depthwise Convolution QASYMM8 support by Georgios Pinitas · 6 years ago
  17. 57c033b COMPMID-906: Use fused activation in NEON Batch normalization by Georgios Pinitas · 6 years ago
  18. 02ee429 COMPMID-765: Fix CPPPermute error when permuting the strides. by Georgios Pinitas · 6 years ago
  19. ba8fcb0 COMPMID-765: Remove wrong shape in LargeShapesBroadcast by Michele Di Giorgio · 6 years ago
  20. 69af6cf COMPMID-765: Sanitize permutation vector for Permute. by Georgios Pinitas · 6 years ago
  21. 77e4a2d COMPMID-850: Increase tolerance while issue is being investigated by Anthony Barbier · 6 years ago
  22. 36e0075 COMPMID-589: Refactor HOGDescriptor validation test by John Richardson · 6 years ago
  23. 284cfe2 COMPMID-903: Implements NEPermute for NHWC conversions by Georgios Pinitas · 6 years ago
  24. ced7a8d COMPMID-875: Deconvolution 4x4 not working by Georgios Pinitas · 6 years ago
  25. a527e8c COMPMID-828 - Add support for pool widths 4, 5 & 6 and for non square data sizes - Part 2 (CL) by Isabella Gottardi · 6 years ago
  26. 1aede36 COMPMID-765 - Extended GEMM benchmark by Gian Marco · 6 years ago
  27. 1167487 COMPMID-897 Merge batch normalization with bounded relu by Giorgio Arena · 6 years ago
  28. 4e1e7dc COMPMID-892: OCLGrind failures on both validation and benchmark by Georgios Pinitas · 6 years ago
  29. 4074c99 COMPMID-873: Integrate RSH NEON Depthwise Convolution routine by Georgios Pinitas · 6 years ago
  30. c5694af COMPMID-879: Invalid convolution data type in validation. by Georgios Pinitas · 6 years ago
  31. 25a340f COMPMID-578: Implement FAST corners for CL/NEON by Abe Mbise · 7 years ago
  32. 40df1e9 COMPMID-887 Valgrind invalid read in print_measurements by Michalis Spyrou · 6 years ago
  33. 5ae9b69 COMPMID-885 Valgrind NEConvolutionSquare::configure relies on uninitialised values by Michalis Spyrou · 6 years ago
  34. e9146ed COMPMID-879: Investigate CL mismatches in Convolution S16 by Georgios Pinitas · 6 years ago
  35. 6e464c3 COMPMID-828 - Add support for non square pool size - Part1 by Isabella Gottardi · 6 years ago
  36. 3364c4c COMPMID-893: Fix segfault in graph_squeezenet_v1_1 by Georgios Pinitas · 6 years ago
  37. 101de50 COMPMID-896: Replace legacy 4x4 u8 GEMM kernel with safe version. by David Mansell · 6 years ago
  38. 679463a COMPMID-784: Added support for PADDING = SAME in Winograd layer. by Pablo Tello · 6 years ago
  39. b7e3028 COMPMID-890: Valgrind: NEON Convolution Layer validation fails by Isabella Gottardi · 6 years ago
  40. 6259e5f COMPMID-787: Add CL support for broadcast multiply by Michele Di Giorgio · 6 years ago
  41. 054a714 COMPMID-765 Small fixes to MobileNet dwc dataset by Giorgio Arena · 6 years ago
  42. 33ff9ef APPBROWSER-400: Implement the tensorshift kernel for fixing DC's alignment issue on OpenGL ES by Xinghang Zhou · 6 years ago
  43. 1c0d0ff COMPMID-832: Decrease validation coverage of QS8/QS16 by Anthony Barbier · 6 years ago
  44. 18d352a COMPMID-765: Added tolerance of 1 for CL Convolution S16 while the issue is investigated by Anthony Barbier · 6 years ago
  45. 0021d75 IVGCVSW-863 Broadcast support in CL/NEON Arithmetic Add by Diego Lopez Recas · 7 years ago
  46. 2219dea APPBROWSER-390,397,398: bugfix and fully connected validation issue on specific dataset by zhenglin · 6 years ago
  47. d466c2d COMPMID-833 Direct convolution, Normalization and by Michalis Spyrou · 6 years ago
  48. c0079e9 COMPMID-564: CustomConvolution Test Name updated by Sanghoon Lee · 6 years ago
  49. 0434d75 COMPMID-588: Port Equalize Histogram to new validation by John Richardson · 7 years ago
  50. fc1ffe6 COMPMID-837: Fixed remap tests failures in Valgrind. by Pablo Tello · 6 years ago
  51. 35ceeb2 IVGCVSW-798 Add Softmax NEON support for QASYMM8 by Diego Lopez Recas · 7 years ago
  52. 97cf249 COMPMID-564: CustomConvolution issue fixed by Sanghoon Lee · 6 years ago
  53. d6ca478 COMPMID-784: Added support for biases in WinogradLayer. by Pablo Tello · 6 years ago
  54. d05dce4 COMPMID-791: Generic Depthwise Convolution Layer NEON QASYMM8 by Georgios Pinitas · 6 years ago
  55. 5d9d019 COMPMID-863: Only output (end-start) for OpenCL timers by Anthony Barbier · 6 years ago
  56. e6630e4 COMPMID-790 - NEON: Add QASYMM8 support to Convolution by Isabella Gottardi · 6 years ago
  57. c9afce5 COMPMID-863: Remove some of the post-processing from the JSON backend by Anthony Barbier · 6 years ago
  58. bd0e612 COMPMID-848 NEPoolingLayerKernel incorrectly reports by Michalis Spyrou · 6 years ago
  59. 46edf63 COMPMID-765: Fixed output accessor in LeNet example, and disabled colors when not running in a terminal by Anthony Barbier · 6 years ago
  60. c8d2316 COMPMID-564: Implement reference and CL/NEON validation for CustomConvolution (output S16) by Sanghoon Lee · 6 years ago
  61. 503cec8 COMPMID-765: Added missing <errno.h> include by Anthony Barbier · 6 years ago
  62. e8a4983 COMPMID-798 Add instrumentation to NEON kernels by Anthony Barbier · 6 years ago
  63. dde3ad9 COMPMID-842: Add NEON QASYMM8 RELU Activation by Michele Di Giorgio · 6 years ago
  64. a1f7e33 COMPMID-841: Add CL QASYMM8 RELU Activation by Michele Di Giorgio · 6 years ago
  65. e855c23 APPBROWSER-377: GCConvoutionLayer support for FP16 by Stephen Li · 7 years ago
  66. 5237e01 COMPMID-838 Implement CLPermute by Michalis Spyrou · 6 years ago
  67. f72f936 COMPMID-791: Adds support of QASYMM8 in NEDepthwiseConvolution3x3 by Georgios Pinitas · 6 years ago
  68. 61ef5bf IVGCVSW-847 Fix {NEON/CL}PoolingLayerKernel config by Diego Lopez Recas · 7 years ago
  69. 9c42de9 COMPMID-753 Add benchmarks for ActivationLayers used in MobileNet by Giorgio Arena · 6 years ago
  70. 51a6730 COMPMID-832: Clean up tests. by Georgios Pinitas · 6 years ago
  71. 20d7848 COMPMID-816 - Enabled CLConvolutionLayer to use CLGEMM function instead by Gian Marco · 6 years ago
  72. 84f3ae8 COMPMID-830 Fix hang in arm_compute_benchmark NEON by Michalis Spyrou · 6 years ago
  73. 7c10f48 COMPMID-765 - Reduced to 4 the batch size for AlexNet by Gian Marco · 6 years ago
  74. 5518671 COMPMID-785: Add QASYMM8 support for pooling layer by Georgios Pinitas · 6 years ago
  75. 72856ab COMPMID-786: Remove all the fill() calls in benchmarks by Anthony Barbier · 6 years ago
  76. 571b18a COMPMID-565 - Implement reference and CL/NEON validation for CustomConvolutionSeparable by Sanghoon Lee · 7 years ago
  77. 4b9c58a COMPMID-800: Display build_information() at the beginning of the runs by Anthony Barbier · 6 years ago
  78. 093adbc COMPMID-753 Add benchmarks for GEMM/GEMMLowp used in AlexNet by Giorgio Arena · 6 years ago
  79. bcbc970 IVGCVSW-863 calculate_max_window..() family takes ValidRegion by Diego Lopez Recas · 7 years ago
  80. 345ab18 COMPMID-742: Add image input support for Harris Corners tests by Alex Gilday · 6 years ago
  81. 780db4e COMPMID-471 Implement Deconvolution on OpenCL by Michalis Spyrou · 7 years ago
  82. d7ba539 COMPMID-727 - Implement reference and CL/NEON validation for CustomConvolutionRectangle by Sanghoon Lee · 7 years ago
  83. 6db0ff5 COMPMID-771 Allow examples to be profiled by Anthony Barbier · 7 years ago
  84. a302d69 COMPMID-753 Add benchmarks for QASYMM8 depthwise convolution layers used in MobileNet by Giorgio Arena · 6 years ago
  85. e671d6a COMPMID-765: Fix HarrisCorners data type in benchmarks by Georgios Pinitas · 6 years ago
  86. 088cc7f COMPMID: GEMMTranspose1xW tests. by Pablo Tello · 7 years ago
  87. 25f2368 COMPMID-589: Port HOGDescriptor to new validation by John Richardson · 7 years ago
  88. 6485691 COMPMID-773: Add CL/NEON Harris Corners benchmark tests by Alex Gilday · 7 years ago
  89. 384a43e COMPMID-579: Port Derivative to new validation by John Richardson · 7 years ago
  90. 8cdfdb8 APPBROWSER-366: Add DepthwiseConvolutionLayer(fp16 only) support. by Frank Lei · 7 years ago
  91. d064389 APPBROWSER-357: Fix Transpose performance issue by tuning lws by steli01 · 7 years ago
  92. 2c35018 COMPMID-761: Add CL/NEON Magnitude benchmark tests by Ioan-Cristian Szabo · 7 years ago
  93. 926d5e1 APPBROWSER-356: Implement GCArithmeticAddition Operator by zhenglin · 7 years ago
  94. 358ca20 COMPMID-617: Adds CLFullyConnectionLayer validation support by Georgios Pinitas · 7 years ago
  95. 1c5ffd6 APPBROWSER-359: Sync tensor in GC benchmark tests by Joel Liang · 7 years ago
  96. 57a150a APPBROWSER-341: Add ResizeNearest operator support by Frank Lei · 7 years ago
  97. 88b8d8c COMPMID-556 Run format_code.py on HWC headers by Anthony Barbier · 7 years ago
  98. 490b3d8 IVGCVSW-863 Move clamp, for_each, foldl to misc/utility.h by Diego Lopez Recas · 7 years ago
  99. 53a6ec5 APPBROWSER-304,342: Add exclude padding support for OpenGL ES implementation and implement MaxPool operators by Xinghang Zhou · 7 years ago
  100. 6e993b5 COMPMID-761 Add CL/NEON QuantizationLayer benchmark tests by Michalis Spyrou · 7 years ago