Gitiles
Code Review Sign In
review.mlplatform.org / ml / ethos-u / ethos-u-vela / cb33704fcd7859b1c334f996445bba2f4efea5f9 / ethosu / vela / graph_optimiser.py
  1. cb33704 MLBEDSW-1693 Convert batched FC to Conv by Patrik Gustavsson · 3 years, 9 months ago
  2. c3862c2 MLBEDSW-3008: Replace Split ops with Identity by Dwight Lidman · 3 years, 10 months ago
  3. 8dbf8cf MLBEDSW-2745 Support relus with differing scales by Michael McGeagh · 3 years, 10 months ago
  4. fa4cb29 MLBEDSW-2994 Remove undesired reshape OPs by Patrik Gustavsson · 3 years, 10 months ago
  5. 11b0bdb vela: Refactor op sets in graph_optimiser by Michael McGeagh · 3 years, 10 months ago
  6. 98a3499 MLBEDSW-2935: LUT fusing with preceding operator by Louis Verhaard · 3 years, 10 months ago
  7. 90033f3 MLBEDSW-2906: Only add padding fields to Npu ops by Jacob Bohlin · 3 years, 10 months ago
  8. d7911c4 MLBEDSW-2688: LUT calculation with different in/out scale by Louis Verhaard · 3 years, 10 months ago
  9. a41cd4d Small fix for Softmax regression by Jacob Bohlin · 3 years, 10 months ago
  10. 58520b9 MLBEDSW-2688: use LeakyRelu for int16 by Louis Verhaard · 3 years, 10 months ago
  11. d47cc27 MLBEDSW-2847: Fix for TransposeConv crash and u8 output diff by Jacob Bohlin · 3 years, 10 months ago
  12. 87c1350 MLBEDSW-2654: Convert Resizebilinear to a number of 2x2 pools by Charles Xu · 3 years, 11 months ago
  13. b9fc33c MLBEDSW-2688: LeakyRelu rewrite to LUT or MUL/MAX by Louis Verhaard · 3 years, 11 months ago
  14. 67e0d8f MLBEDSW-2663: Handle optional tensors by Jacob Bohlin · 3 years, 10 months ago
  15. eebb1c2 MLBEDSW-2779 Avoid NHCWB16 in some SplitSliceRead cases by Patrik Gustavsson · 3 years, 10 months ago
  16. 29d568e MLBEDSW-2779 Consider num dimensions, in check for NHCWB16 by Patrik Gustavsson · 3 years, 10 months ago
  17. 458a208 MLBEDSW-2570 Avoid usage of NHCWB16 for some cases by Patrik Gustavsson · 3 years, 11 months ago
  18. c5b549b MLBEDSW-2637 Utilise new tensor and operator funcs by Michael McGeagh · 3 years, 11 months ago
  19. 36ffaf3 Skip the NOP resizebilinear op by Charles Xu · 3 years, 11 months ago
  20. a0c3624 [MLBEDSW-2335] SoftMax int16 by Fredrik Svedberg · 4 years, 1 month ago
  21. 9a03fdf MLBEDSW-2569:Support 1x1 IFM ResizeBilinear by Charles Xu · 4 years ago
  22. 8d939c0 MLBEDSW-2660 Convert FC-like convs to FC by Michael McGeagh · 4 years ago
  23. 6a8d424 vela: Move common functionality by Michael McGeagh · 4 years ago
  24. 9b64ba0 MLBEDSW-2584: Support cascading of Transpose Convolution by Jacob Bohlin · 4 years ago
  25. e843d33 MLBEDSW-2548: Fix for Double Buffer size estimate by Jacob Bohlin · 4 years ago
  26. c30f495 Code clean-up using black and flake8 by Tim Hall · 4 years ago
  27. e0ef273 MLBEDSW-2379: Fix 1-element tensors that were marked as scalars by Louis Verhaard · 4 years, 1 month ago
  28. cf7da10 MLBEDSW-1716: Transpose Convolution support by Jacob Bohlin · 4 years, 1 month ago
  29. b2fb212 MLBEDSW-2420: Improved support for dilated convolution by Louis Verhaard · 4 years, 1 month ago
  30. 42fed94 MLBEDSW-2372: Failing assert for ResizeBilinear with upscale != 2x by Dwight Lidman · 4 years, 1 month ago
  31. 7db7896 MLBEDSW-2067: added custom exceptions by Louis Verhaard · 4 years, 1 month ago
  32. 7879222 Add elementwise vector scalars support by Charles Xu · 4 years, 1 month ago
  33. 4e12776 Further update for MLBEDSW-1872 by Tim Hall · 4 years, 1 month ago
  34. e8a1045 Add reorder-python-import pre-commit hook by Diego Russo · 4 years, 2 months ago
  35. 3ec04ac MLBEDSW-1498: Add Resize_Bilinear operator support by Dwight Lidman · 4 years, 2 months ago
  36. ea6111a Add pre-commit support for sanity checks by Diego Russo · 4 years, 2 months ago
  37. cf72890 MLBEDSW-1998: Add support for new_axis_mask by Patrik Gustavsson · 4 years, 2 months ago
  38. 79d07d2 Add Vela codebase by Tim Hall · 4 years, 2 months ago 0.1.0