diff options
| author | Huan Gui <huangui@fb.com> | 2019-02-28 23:17:35 -0800 |
|---|---|---|
| committer | Facebook Github Bot <facebook-github-bot@users.noreply.github.com> | 2019-02-28 23:21:29 -0800 |
| commit | d3fcd0d798a0188ae4fffafe13d7c71f4186f4ce (patch) | |
| tree | 083198a520b491513c2f16d241b5da734925f84f /c10/cuda/CUDAException.h | |
| parent | 3ed44b6714cadf41409f42132a1581c33cf7b458 (diff) | |
| download | pytorch-d3fcd0d798a0188ae4fffafe13d7c71f4186f4ce.tar.gz pytorch-d3fcd0d798a0188ae4fffafe13d7c71f4186f4ce.tar.bz2 pytorch-d3fcd0d798a0188ae4fffafe13d7c71f4186f4ce.zip | |
add dropout during eval (#17549)
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/17549
Currently Dropout is only enabled in training, we enable the option of having dropout in Eval.
This is to follow [1]. This functionality would be used for uncertainty estimation in exploration project.
[1] Gal, Yarin, and Zoubin Ghahramani. "Dropout as a bayesian approximation: Representing model uncertainty in deep learning." international conference on machine learning. 2016.
Reviewed By: Wakeupbuddy
Differential Revision: D14216216
fbshipit-source-id: 87c8c9cc522a82df467b685805f0775c86923d8b
Diffstat (limited to 'c10/cuda/CUDAException.h')
0 files changed, 0 insertions, 0 deletions