Huan Gui d3fcd0d798 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		2019-02-28 23:21:29 -08:00
..
__init__.py
adaptive_weight.py
add_bias.py
arc_cosine_feature_map.py
batch_distill_lr_loss.py
batch_lr_loss.py
batch_mse_loss.py
batch_normalization.py
batch_sigmoid_cross_entropy_loss.py
batch_softmax_loss.py
blob_weighted_sum.py
bucket_weighted.py
build_index.py
concat.py
constant_weight.py
conv.py
dropout.py	add dropout during eval (#17549)	2019-02-28 23:21:29 -08:00
fc.py
fc_without_bias.py
feature_sparse_to_dense.py	Revert D13551909: [fbcode] logdevice for generic feature type	2019-01-25 00:33:06 -08:00
functional.py
gather_record.py
homotopy_weight.py
label_smooth.py
last_n_window_collector.py
layer_normalization.py
layers.py
margin_rank_loss.py
merge_id_lists.py
pairwise_similarity.py
position_weighted.py
random_fourier_features.py
reservoir_sampling.py
sampling_train.py
sampling_trainable_mixin.py
select_record_by_context.py
semi_random_features.py
sparse_feature_hash.py
sparse_lookup.py	Resubmit: Set the correct engine name for position weighted pooling when fp16 is used for training	2018-11-27 14:51:56 -08:00
split.py
tags.py
uniform_sampling.py