Skip to content

Instantly share code, notes, and snippets.

Last active November 23, 2022 08:00
  • Star 7 You must be signed in to star a gist
  • Fork 2 You must be signed in to fork a gist
Star You must be signed in to star a gist
What would you like to do?
An implementation for MGU based on TensorFlow.
# -*- coding: utf-8 -*-
# Copyright (C) 2016 by Akira TAMAMORI
# This program is free software; you can redistribute it and/or modify it under
# the terms of the GNU General Public License as published by the Free Software
# Foundation, either version 3 of the License, or (at your option) any later
# version.
# This program is distributed in the hope that it will be useful, but WITHOUT
# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS
# FOR A PARTICULAR PURPOSE. See the GNU General Public License for more
# details.
# You should have received a copy of the GNU General Public License along with
# this program. If not, see <>.
# Copyright 2015 The TensorFlow Authors. All Rights Reserved.
# Licensed under the Apache License, Version 2.0 (the "License");
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# See the License for the specific language governing permissions and
# limitations under the License.
import tensorflow as tf
# この命令がないとDropoutなどでエラー
from tensorflow.python.ops.rnn_cell import RNNCell
class MGUCell(RNNCell):
"""Minimal Gated Unit (MGU) for recurrent neural networks.
This implementation is based on:
def __init__(self, num_units, input_size=None):
self._num_units = num_units
self._input_size = num_units if input_size is None else input_size
def input_size(self):
return self._input_size
def output_size(self):
return self._num_units
def state_size(self):
return self._num_units
def __call__(self, inputs, state, scope=None):
"""MGU with nunits cells."""
with tf.variable_scope(scope or type(self).__name__): # "MGUCell"
with tf.variable_scope("Gates"):
f = linear([inputs, state], self._num_units, True, 1.0)
f = tf.sigmoid(f)
with tf.variable_scope("Candidate"):
h_tilde = tf.tanh(linear([inputs, f * state], self._num_units,
h = (1 - f) * state + f * h_tilde
return h, h
def linear(args, output_size, bias, bias_start=0.0, scope=None):
"""Linear map: sum_i(args[i] * W[i]), where W[i] is a variable.
args: a 2D Tensor or a list of 2D, batch x n, Tensors.
output_size: int, second dimension of W[i].
bias: boolean, whether to add a bias term or not.
bias_start: starting value to initialize the bias; 0 by default.
scope: VariableScope for the created subgraph; defaults to "Linear".
A 2D Tensor with shape [batch x output_size] equal to
sum_i(args[i] * W[i]), where W[i]s are newly created matrices.
ValueError: if some of the arguments has unspecified or wrong shape.
if args is None or (isinstance(args, (list, tuple)) and not args):
raise ValueError("`args` must be specified")
if not isinstance(args, (list, tuple)):
args = [args]
# Calculate the total size of arguments on dimension 1.
total_arg_size = 0
shapes = [a.get_shape().as_list() for a in args]
for shape in shapes:
if len(shape) != 2:
raise ValueError(
"Linear is expecting 2D arguments: %s" % str(shapes))
if not shape[1]:
raise ValueError(
"Linear expects shape[1] of arguments: %s" % str(shapes))
total_arg_size += shape[1]
# Now the computation.
with tf.variable_scope(scope or "Linear"):
matrix = tf.get_variable("Matrix", [total_arg_size, output_size])
if len(args) == 1:
res = tf.matmul(args[0], matrix)
res = tf.matmul(tf.concat(1, args), matrix)
if not bias:
return res
bias_term = tf.get_variable(
"Bias", [output_size],
return res + bias_term
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment