def __init__(self, units, output_dim,
activation='tanh',
return_probabilities=False,
name='AttentionDecoder',
kernel_initializer='glorot_uniform',
recurrent_initializer='orthogonal',
bias_initializer='zeros',
kernel_regularizer=None,
bias_regularizer=None,
activity_regularizer=None,
kernel_constraint=None,
bias_constraint=None,
**kwargs):
"""
Implements an AttentionDecoder that takes in a sequence encoded by an
encoder and outputs the decoded states
:param units: dimension of the hidden state and the attention matrices
:param output_dim: the number of labels in the output space
references:
Bahdanau, Dzmitry, Kyunghyun Cho, and Yoshua Bengio.
"Neural machine translation by jointly learning to align and translate."
arXiv preprint arXiv:1409.0473 (2014).
"""
self.units = units
self.output_dim = output_dim
self.return_probabilities = return_probabilities
self.activation = activations.get(activation)
self.kernel_initializer = initializers.get(kernel_initializer)
self.recurrent_initializer = initializers.get(recurrent_initializer)
self.bias_initializer = initializers.get(bias_initializer)
self.kernel_regularizer = regularizers.get(kernel_regularizer)
self.recurrent_regularizer = regularizers.get(kernel_regularizer)
self.bias_regularizer = regularizers.get(bias_regularizer)
self.activity_regularizer = regularizers.get(activity_regularizer)
self.kernel_constraint = constraints.get(kernel_constraint)
self.recurrent_constraint = constraints.get(kernel_constraint)
self.bias_constraint = constraints.get(bias_constraint)
super(AttentionDecoder, self).__init__(**kwargs)
self.name = name
self.return_sequences = True # must return sequences
评论列表
文章目录
