1. 24 Mar, 2020 1 commit
  2. 12 Mar, 2020 1 commit
  3. 10 Mar, 2020 1 commit
    • Revive the Rust + SGX refactor (#4976) · 41e1d5f9
      * Add Nick's changes's squashed
      
      * Fix frontend compilation
      
      * Re-enable Rust CI
      
      * Add changes with conflicted badly
      
      * Restructure import_module! macro in order to avoid unstable features
      
      * Kill old unstable feature enablement
      
      * Refactor common to use new APIs
      
      * Move the code to stable
      
      * Fix warning
      
      Co-authored-by: Nick Hynes <nhynes@oasislabs.com>
      Jared Roesch committed
  4. 05 Mar, 2020 1 commit
  5. 26 Feb, 2020 1 commit
  6. 18 Feb, 2020 1 commit
  7. 09 Feb, 2020 1 commit
  8. 06 Feb, 2020 1 commit
  9. 25 Jan, 2020 1 commit
  10. 19 Jan, 2020 1 commit
  11. 10 Jan, 2020 3 commits
  12. 06 Jan, 2020 2 commits
  13. 24 Dec, 2019 1 commit
  14. 23 Dec, 2019 1 commit
  15. 13 Dec, 2019 1 commit
  16. 18 Nov, 2019 1 commit
  17. 16 Nov, 2019 1 commit
  18. 14 Nov, 2019 1 commit
  19. 06 Nov, 2019 1 commit
  20. 31 Oct, 2019 2 commits
  21. 30 Oct, 2019 1 commit
  22. 18 Oct, 2019 1 commit
  23. 17 Oct, 2019 1 commit
    • [DOCKER] Pin torchvision==0.4.1 (#4140) · a8a98317
      The existing sequence of pip install commands fetches and installs
      torch==1.0.1.post2 then fetches an unpinned version of torchvision,
      recent torchvision packages hardwire the specific torch version they
      depend on, the overall effect is that we install a pinned torch
      version then replace it with whatever version the torchvision package
      depends on.
      
      The most recent torchvision==0.4.1 package results in some test case
      failures.
      
      This patch pins torchvision back to 0.4.0, the most recent version
      that the test suite worked.  Removing the explicit torch install
      because it is implied and pinned as dependency of torchvision.
      
      Change-Id: Ib30bf6aed79ff130ea15ef5134fefb0508790574
      Marcus Shawcroft committed
  24. 10 Oct, 2019 1 commit
    • [DOCKER] torch install depends on future package (#4098) · 4b8cb3a4
      The torch package depends on the future package but the torch wheel
      does not expose that dependency resulting in an inconsitent install.
      
      Ideally the wheel should declare all of its dependencies, I'm not sure
      why the packagers have choosen not to do this, for now the simple work
      around is to explicitly install the future package.
      
      Change-Id: Ic9f0f4bb4c78ab65706fc1b20c1b4fd287856a9e
      Marcus Shawcroft committed
  25. 27 Sep, 2019 1 commit
  26. 17 Sep, 2019 1 commit
  27. 08 Sep, 2019 1 commit
  28. 23 Aug, 2019 1 commit
  29. 08 Aug, 2019 1 commit
  30. 07 Aug, 2019 2 commits
  31. 02 Aug, 2019 1 commit
  32. 22 Jul, 2019 1 commit
    • Add support for Tflite operator SPLIT (#3520) · 19eb829e
      * [RFC] Initial support for Tflite operator SPLIT
      
      This patch adds initial support for the tflite operator split. However
      I am not yet sure how to handle the axis parameter for the split
      operator and support it in the test infrastructure. Putting this up for
      an initial review and comment.
      
      The split operator in tflite according to
      https://www.tensorflow.org/lite/guide/ops_compatibility
      
      appears to take num_or_size_split as a 0D tensor.
      
      I also note that tflite.split is one of the few operators that returns
      multiple outputs and thus the helper routines in the tests needed some
      massaging to make this work.
      
      @apivarov , could you please review this ?
      
      Thanks,
      Ramana
      
      * Fix the axis parameter
      
      Add more tests
      
      * Address review comments
      
      * Try out frozen_gene's suggestion
      
      * Handle split of 1 element
      
      * int32 is only supported in tflite 1.14, let's check that version here.
      
      * Keep this at python3.5
      
      * Add packaging as a python package to be installed
      Ramana Radhakrishnan committed
  33. 21 Jul, 2019 1 commit
  34. 18 Jul, 2019 1 commit
  35. 10 Jul, 2019 1 commit