Skip to content

GitLab

Switch branch/tag
  1. 25 Aug, 2021 2 commits
  3. 06 Apr, 2021 2 commits
    • Jeremiah Liu's avatar
      Disable temperature scaling during training. · fab47e9e
      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
      fab47e9e
    • 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
  5. 05 Apr, 2021 2 commits
    • Jeremiah Liu's avatar
      Adds `call()` method to `GaussianProcessClassificationHead`. · 2ae06c8a
      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
      2ae06c8a
    • 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
  7. 24 Mar, 2021 2 commits
  9. 22 Mar, 2021 2 commits
  11. 10 Mar, 2021 2 commits
  13. 09 Mar, 2021 2 commits
  15. 01 Dec, 2020 2 commits
  17. 19 Aug, 2020 2 commits
  19. 30 May, 2020 1 commit