Spaces:
Running
Running
File size: 2,443 Bytes
0b8359d |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 |
# Copyright 2017 The TensorFlow Authors All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
# ==============================================================================
"""Zoneout Wrapper"""
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import tensorflow as tf
class ZoneoutWrapper(tf.contrib.rnn.RNNCell):
"""Add Zoneout to a RNN cell."""
def __init__(self, cell, zoneout_drop_prob, is_training=True):
self._cell = cell
self._zoneout_prob = zoneout_drop_prob
self._is_training = is_training
@property
def state_size(self):
return self._cell.state_size
@property
def output_size(self):
return self._cell.output_size
def __call__(self, inputs, state, scope=None):
output, new_state = self._cell(inputs, state, scope)
if not isinstance(self._cell.state_size, tuple):
new_state = tf.split(value=new_state, num_or_size_splits=2, axis=1)
state = tf.split(value=state, num_or_size_splits=2, axis=1)
final_new_state = [new_state[0], new_state[1]]
if self._is_training:
for i, state_element in enumerate(state):
random_tensor = 1 - self._zoneout_prob # keep probability
random_tensor += tf.random_uniform(tf.shape(state_element))
# 0. if [zoneout_prob, 1.0) and 1. if [1.0, 1.0 + zoneout_prob)
binary_tensor = tf.floor(random_tensor)
final_new_state[
i] = (new_state[i] - state_element) * binary_tensor + state_element
else:
for i, state_element in enumerate(state):
final_new_state[
i] = state_element * self._zoneout_prob + new_state[i] * (
1 - self._zoneout_prob)
if isinstance(self._cell.state_size, tuple):
return output, tf.contrib.rnn.LSTMStateTuple(
final_new_state[0], final_new_state[1])
return output, tf.concat([final_new_state[0], final_new_state[1]], 1)
|