def __init__(self, params):
super(MTEncoderV1, self).__init__(params)
p = self.params
assert p.packed_input is False, (
'Packed inputs are not yet supported for '
'MTEncoderV1.')
with tf.variable_scope(p.name):
if p.cc_schedule is not None:
self.CreateChild('cc_schedule', p.cc_schedule)
self.CreateChild('emb', p.emb)
rnn_layers_params = []
# L0 is a bi-directional lstm.
# L0's forward lstm cell
params = (p.lstm_tpl.Copy()
if p.lstm_tpl_bidi is None else p.lstm_tpl_bidi.Copy())
params.name = 'L0_rnn_fwd'
params.num_input_nodes = p.emb.embedding_dim
params.num_output_nodes = p.lstm_cell_size
forward_lstm = params
# L0's backward lstm cell
params = params.Copy()
params.name = 'L0_rnn_bak'
backward_lstm = params
# L0 layer.
params = model_helper.CreateBidirectionalRNNParams(
self.params, forward_lstm, backward_lstm)
params.name = 'L0'
rnn_layers_params.append(params)
# The latter layers are all uni-directional lstm.
input_size = 2 * p.lstm_cell_size
for i in range(1, p.num_lstm_layers):
# Forward lstm cell.
cell = (p.lstm_tpl.Copy()
if p.lstm_tpl_uni is None else p.lstm_tpl_uni.Copy())
cell.name = 'L%d_rnn' % i
cell.num_input_nodes = input_size
cell.num_output_nodes = p.lstm_cell_size
# Forward lstm layer.
params = model_helper.CreateUnidirectionalRNNParams(
self.params, cell)
params.name = 'L%d' % i
rnn_layers_params.append(params)
input_size = p.lstm_cell_size
self.CreateChildren('rnn', rnn_layers_params)
dropout_p = layers.DropoutLayer.Params().Set(
name='dropout_layer',
keep_prob=1.0 - p.dropout_prob,
random_seed=p.random_seed +
84828474 if p.random_seed else None)
self.CreateChild('dropout', dropout_p)
def __init__(self, params):
super(MTEncoderBiRNN, self).__init__(params)
p = self.params
with tf.variable_scope(p.name):
if p.cc_schedule is None:
self.cc_schedule = None
else:
self.CreateChild('cc_schedule', p.cc_schedule)
self.CreateChild('emb', p.emb)
rnn_layers_params = []
for i in range(p.num_lstm_layers):
params = p.lstm_tpl.Copy()
params.name = 'L%d_rnn_fwd' % i
if i == 0:
params.num_input_nodes = p.emb.embedding_dim
else:
params.num_input_nodes = 2 * p.lstm_cell_size
params.num_output_nodes = p.lstm_cell_size
params.reset_cell_state = p.packed_input
forward_lstm = params
params = params.Copy()
params.name = 'L%d_rnn_bak' % i
params.reset_cell_state = p.packed_input
backward_lstm = params
params = model_helper.CreateBidirectionalRNNParams(
self.params, forward_lstm, backward_lstm)
params.packed_input = p.packed_input
params.name = 'L%d' % i
rnn_layers_params.append(params)
self.CreateChildren('rnn', rnn_layers_params)
if p.lstm_cell_size * 2 != p.encoder_out_dim:
# Project the encoder output to the desired dim.
proj_p = p.proj_tpl.Copy().Set(name='proj',
batch_norm=False,
input_dim=p.lstm_cell_size * 2,
output_dim=p.encoder_out_dim)
if p.cc_schedule is not None:
proj_p.has_bias = False
proj_p.activation = 'TANH'
else:
proj_p.has_bias = True
proj_p.activation = 'NONE'
self.CreateChild('final_proj', proj_p)
dropout_p = layers.DropoutLayer.Params().Set(
name='dropout_layer',
keep_prob=1.0 - p.dropout_prob,
random_seed=p.random_seed +
827366448 if p.random_seed else None)
self.CreateChild('dropout', dropout_p)
if p.is_transparent:
transparent_params = p.transparent_merger_tpl.Copy()
transparent_params.name = 'transparent'
transparent_params.num_sources = p.num_lstm_layers
self.CreateChild('transparent_merger', transparent_params)
def CreateBidirectionalRNNParams(self, forward_p, backward_p):
return model_helper.CreateBidirectionalRNNParams(
self.params, forward_p, backward_p)
