1. 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
  2. 05 Apr, 2021 1 commit
    • Jeremiah Liu's avatar
      Adds `call()` method to `GaussianProcessClassificationHead`. · a35d7aaa
      Jeremiah Liu authored
      This change allows `GaussianProcessClassificationHead` to output only the predictive logits during training and evaluation (instead of outputting a tuple  `(logits, covmat)`). The goal is to make the layer more compatible with `SentencePredictionTask` and Keras' `model.fit()` API.
      
      PiperOrigin-RevId: 366891298
      a35d7aaa
  3. 01 Apr, 2021 3 commits
  4. 24 Mar, 2021 1 commit
  5. 22 Mar, 2021 3 commits
  6. 20 Mar, 2021 1 commit
  7. 17 Mar, 2021 2 commits
  8. 16 Mar, 2021 2 commits
  9. 12 Mar, 2021 4 commits
  10. 10 Mar, 2021 2 commits
  11. 09 Mar, 2021 2 commits
  12. 08 Mar, 2021 2 commits
  13. 04 Mar, 2021 2 commits
  14. 02 Mar, 2021 2 commits
  15. 26 Feb, 2021 2 commits
  16. 23 Feb, 2021 2 commits
  17. 16 Feb, 2021 4 commits
  18. 28 Jan, 2021 2 commits
  19. 19 Jan, 2021 2 commits