From e3ad8b66eac3f9efada045dfaad5cdfbbb5ae6ef Mon Sep 17 00:00:00 2001 From: Moses Marin Date: Tue, 9 Apr 2019 23:41:59 -0700 Subject: [PATCH 1/2] Title of paper as clickable link --- tensorflow/python/ops/rnn_cell_impl.py | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/tensorflow/python/ops/rnn_cell_impl.py b/tensorflow/python/ops/rnn_cell_impl.py index dc545e1d6ab9b7..973b6619942a57 100644 --- a/tensorflow/python/ops/rnn_cell_impl.py +++ b/tensorflow/python/ops/rnn_cell_impl.py @@ -1197,10 +1197,8 @@ def __init__(self, cell, input_keep_prob=1.0, output_keep_prob=1.0, """Create a cell with added input, state, and/or output dropout. If `variational_recurrent` is set to `True` (**NOT** the default behavior), - then the same dropout mask is applied at every step, as described in: - - Y. Gal, Z Ghahramani. "A Theoretically Grounded Application of Dropout in - Recurrent Neural Networks". https://arxiv.org/abs/1512.05287 + then the same dropout mask is applied at every step, as described in: [A Theoretically + Grounded Application of Dropout in Recurrent Neural Networks. Y. Gal, Z. Ghahramani](https://arxiv.org/abs/1512.05287). Otherwise a different dropout mask is applied at every time step. From a1b4a3f1f3e7e81d982f21a60b92308105726d7d Mon Sep 17 00:00:00 2001 From: Moses Marin Date: Fri, 12 Apr 2019 16:22:21 -0700 Subject: [PATCH 2/2] fix ubuntu sanity failure (line-too-long) fix ubuntu sanity failure (line-too-long) --- tensorflow/python/ops/rnn_cell_impl.py | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/tensorflow/python/ops/rnn_cell_impl.py b/tensorflow/python/ops/rnn_cell_impl.py index 973b6619942a57..3f4cf9761b4778 100644 --- a/tensorflow/python/ops/rnn_cell_impl.py +++ b/tensorflow/python/ops/rnn_cell_impl.py @@ -1197,8 +1197,9 @@ def __init__(self, cell, input_keep_prob=1.0, output_keep_prob=1.0, """Create a cell with added input, state, and/or output dropout. If `variational_recurrent` is set to `True` (**NOT** the default behavior), - then the same dropout mask is applied at every step, as described in: [A Theoretically - Grounded Application of Dropout in Recurrent Neural Networks. Y. Gal, Z. Ghahramani](https://arxiv.org/abs/1512.05287). + then the same dropout mask is applied at every step, as described in: + [A Theoretically Grounded Application of Dropout in Recurrent + Neural Networks. Y. Gal, Z. Ghahramani](https://arxiv.org/abs/1512.05287). Otherwise a different dropout mask is applied at every time step.