1. 04 Mar, 2022 1 commit
  2. 03 Mar, 2022 1 commit
  3. 25 Jan, 2022 1 commit
  4. 19 Jan, 2022 1 commit
  5. 18 Jan, 2022 1 commit
  6. 04 Jan, 2022 1 commit
  7. 29 Dec, 2021 1 commit
    • Xin Wang's avatar
      Added block diagonal feedforward layer. · a7e60974
      Xin Wang authored
      This layer replaces the weight matrix of the output_dense layer with a block diagonal matrix to save layer parameters and FLOPs. A linear mixing layer can be added optionally to improve layer expressibility.
      
      PiperOrigin-RevId: 418828099
      a7e60974
  8. 21 Dec, 2021 1 commit
  9. 16 Dec, 2021 1 commit
  10. 03 Dec, 2021 1 commit
  11. 30 Nov, 2021 1 commit
  12. 25 Nov, 2021 1 commit
  13. 10 Nov, 2021 2 commits
  14. 04 Nov, 2021 1 commit
  15. 09 Oct, 2021 1 commit
  16. 08 Oct, 2021 1 commit
  17. 07 Oct, 2021 1 commit
  18. 24 Sep, 2021 1 commit
  19. 10 Sep, 2021 2 commits
  20. 25 Aug, 2021 1 commit
  21. 09 Aug, 2021 1 commit
  22. 28 Jul, 2021 2 commits
  23. 13 Jul, 2021 1 commit
  24. 10 Jul, 2021 1 commit
  25. 03 Jul, 2021 1 commit
  26. 06 Jun, 2021 2 commits
  27. 19 May, 2021 1 commit
  28. 18 May, 2021 1 commit
  29. 17 May, 2021 1 commit
  30. 14 May, 2021 1 commit
  31. 13 May, 2021 1 commit
  32. 20 Apr, 2021 1 commit
  33. 17 Apr, 2021 1 commit
    • Chen Chen's avatar
      Catch tf.text NotFoundError: · ffaa4035
      Chen Chen authored
      tensorflow.python.framework.errors_impl.NotFoundError: /usr/local/lib/python3.6/dist-packages/tensorflow_text/python/metrics/_text_similarity_metric_ops.so: undefined symbol: _ZN10tensorflow6StatusC1ENS_5error4CodeEN4absl12lts_2021032411string_viewEOSt6vectorINS_10StackFrameESaIS7_EE
      
      PiperOrigin-RevId: 368978629
      ffaa4035
  34. 15 Apr, 2021 1 commit
  35. 13 Apr, 2021 2 commits
    • A. Unique TensorFlower's avatar
      Internal change · b1aa44d9
      A. Unique TensorFlower authored
      PiperOrigin-RevId: 368260712
      b1aa44d9
    • Reed Wanderman-Milne's avatar
      Use nonexperimental mixed precision API. · 4334a892
      Reed Wanderman-Milne authored
      This replaces symbols in tf.keras.mixed_precision.experimental with the corresponding nonexperimental symbols. In some cases, passing a Policy is replaced with passing a policy name for conciseness.
      
      Additionally, for the Shakespeare model, the loss_scale flag is removed, since supporting it with the nonexperimental API is slightly more verbose and it is recommended users use the default loss scale.
      
      PiperOrigin-RevId: 368123944
      4334a892