1. 13 Apr, 2021 1 commit
    • Reed Wanderman-Milne's avatar
      Use nonexperimental mixed precision API. · 9a4d14a9
      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
      9a4d14a9
  2. 06 Apr, 2021 1 commit
    • Jeremiah Liu's avatar
      Disable temperature scaling during training. · ff3ed4cc
      Jeremiah Liu authored
      For the `GaussianProcessClassificationHead`, the temperature scaling needs to be disabled during training to avoid unexpected modification to the learning rate, which harms model quality. (Unfortunately, this seems to require adding `training` to the `call` method).
      
      Also set the default of `gp_cov_ridge_penalty` in `RandomFeatureGaussianProcess` to 1 to be consistent with that in the `GaussianProcessClassificationHead`.
      
      PiperOrigin-RevId: 366917075
      ff3ed4cc
  3. 05 Apr, 2021 2 commits
  4. 01 Apr, 2021 3 commits
  5. 25 Mar, 2021 1 commit
  6. 24 Mar, 2021 1 commit
  7. 22 Mar, 2021 4 commits
  8. 20 Mar, 2021 1 commit
  9. 17 Mar, 2021 2 commits
  10. 16 Mar, 2021 4 commits
  11. 12 Mar, 2021 6 commits
  12. 10 Mar, 2021 2 commits
  13. 09 Mar, 2021 2 commits
  14. 08 Mar, 2021 2 commits
  15. 04 Mar, 2021 4 commits
  16. 02 Mar, 2021 2 commits
  17. 26 Feb, 2021 2 commits