def encode(self, inputs, input_seq_length, is_training):
'''
Create the variables and do the forward computation
Args:
inputs: the inputs to the neural network, this is a dictionary of
[batch_size x time x ...] tensors
input_seq_length: The sequence lengths of the input utterances, this
is a dictionary of [batch_size] vectors
is_training: whether or not the network is in training mode
Returns:
- the outputs of the encoder as a dictionary of
[bath_size x time x ...] tensors
- the sequence lengths of the outputs as a dictionary of
[batch_size] tensors
'''
encoded = {}
encoded_seq_length = {}
for inp in inputs:
with tf.variable_scope(inp):
#add input noise
std_input_noise = float(self.conf['input_noise'])
if is_training and std_input_noise > 0:
noisy_inputs = inputs[inp] + tf.random_normal(
tf.shape(inputs[inp]), stddev=std_input_noise)
else:
noisy_inputs = inputs[inp]
outputs = noisy_inputs
output_seq_lengths = input_seq_length[inp]
for l in range(int(self.conf['num_layers'])):
outputs, output_seq_lengths = layer.pblstm(
inputs=outputs,
sequence_length=output_seq_lengths,
num_units=int(self.conf['num_units']),
num_steps=int(self.conf['pyramid_steps']),
scope='layer%d' % l)
if float(self.conf['dropout']) < 1 and is_training:
outputs = tf.nn.dropout(outputs,
float(self.conf['dropout']))
outputs = layer.blstm(inputs=outputs,
sequence_length=output_seq_lengths,
num_units=int(self.conf['num_units']),
scope='layer%d' %
int(self.conf['num_layers']))
if float(self.conf['dropout']) < 1 and is_training:
outputs = tf.nn.dropout(outputs,
float(self.conf['dropout']))
encoded[inp] = outputs
encoded_seq_length[inp] = output_seq_lengths
return encoded, encoded_seq_length
def encode(self, inputs, input_seq_length, is_training):
'''
Create the variables and do the forward computation
Args:
inputs: the inputs to the neural network, this is a dictionary of
[batch_size x time x ...] tensors
input_seq_length: The sequence lengths of the input utterances, this
is a dictionary of [batch_size] vectors
is_training: whether or not the network is in training mode
Returns:
- the outputs of the encoder as a dictionary of
[bath_size x time x ...] tensors
- the sequence lengths of the outputs as a dictionary of
[batch_size] tensors
'''
#do the forward computation
encoded = {}
encoded_seq_length = {}
for inp in inputs:
with tf.variable_scope(inp):
#add gaussian noise to the inputs
if is_training and float(self.conf['input_noise']) > 0:
logits = inputs[inp] + tf.random_normal(
tf.shape(inputs[inp]),
stddev=float(self.conf['input_noise']))
else:
logits = inputs[inp]
for l in range(int(self.conf['num_layers'])):
logits = layer.blstm(inputs=logits,
sequence_length=input_seq_length[inp],
num_units=int(self.conf['num_units']),
scope='layer' + str(l))
if is_training and float(self.conf['dropout']) < 1:
logits = tf.nn.dropout(logits,
float(self.conf['dropout']))
encoded[inp] = logits
encoded_seq_length[inp] = input_seq_length[inp]
return encoded, encoded_seq_length
def encode(self, features, len_feas):
'''
Create the variables and do the forward computation
Args:
inputs: [batch_size x time x ...] tensor
input_seq_length: [batch_size] vector
is_train: whether or not the network is in training mode
Returns:
- [bath_size x time x ...] tensor
- [batch_size] tensor
'''
num_pblayers = self.args.model.encoder.num_pblayers
num_blayers = self.args.model.encoder.num_blayers
num_cell_units = self.args.model.encoder.num_cell_units
dropout = self.args.model.encoder.dropout
outputs = features
output_seq_lengths = len_feas
for l in range(num_pblayers):
outputs, output_seq_lengths = layer.pblstm(
inputs=outputs,
sequence_length=output_seq_lengths,
num_units=num_cell_units,
num_steps=2,
layer_norm=True,
scope='en_pblstm_%d' % l)
if dropout > 0 and self.is_train:
outputs = tf.nn.dropout(outputs, keep_prob=1.0 - dropout)
for l in range(num_blayers):
outputs = layer.blstm(inputs=outputs,
sequence_length=output_seq_lengths,
num_units=num_cell_units,
scope='en_blstm_%d' % (l + num_pblayers))
if dropout > 0 and self.is_train:
outputs = tf.nn.dropout(outputs, keep_prob=1.0 - dropout)
return outputs, output_seq_lengths
def encode(self, features, len_feas):
'''
Create the variables and do the forward computation
Args:
inputs: [batch_size x time x ...] tensor
input_seq_length: [batch_size] vector
is_train: whether or not the network is in training mode
Returns:
- [bath_size x time x ...] tensor
- [batch_size] tensor
'''
num_pblayers = self.args.model.encoder.num_pblayers
num_blayers = self.args.model.encoder.num_blayers
num_cell_units = self.args.model.encoder.num_cell_units
dropout = self.args.model.encoder.dropout
size_feat = self.args.data.dim_input
# the first cnn layer
size_batch = tf.shape(features)[0]
size_length = tf.shape(features)[1]
x = tf.reshape(features,
[size_batch, size_length,
int(size_feat / 3), 3])
x = normal_conv(inputs=x,
filter_num=64,
kernel=(3, 3),
stride=(2, 2),
padding='SAME',
use_relu=True,
name="conv",
w_initializer=None,
norm_type='layer')
# conv_output = tf.expand_dims(features, -1)
# len_sequence = len_feas
# conv_output, len_sequence, size_feat = conv_layer(
# inputs=conv_output,
# len_sequence=len_sequence,
# size_feat=size_feat,
# num_filter=64,
# kernel=(3,3),
# stride=(2,2),
# scope='en_conv_0')
# the second pblstm layer
size_feat = int(np.ceil(40 / 2)) * 64
size_length = tf.cast(tf.ceil(tf.cast(size_length, tf.float32) / 2),
tf.int32)
output_seq_lengths = tf.cast(
tf.ceil(tf.cast(len_feas, tf.float32) / 2), tf.int32)
outputs = tf.reshape(x, [size_batch, size_length, size_feat])
for l in range(num_pblayers):
outputs, output_seq_lengths = layer.pblstm(
inputs=outputs,
sequence_length=output_seq_lengths,
num_units=num_cell_units,
num_steps=2,
layer_norm=True,
scope='en_pblstm_%d' % l)
if dropout > 0 and self.is_train:
outputs = tf.nn.dropout(outputs, keep_prob=1.0 - dropout)
# the third blstm layer
for l in range(num_blayers):
outputs = layer.blstm(inputs=outputs,
sequence_length=output_seq_lengths,
num_units=num_cell_units,
scope='en_blstm_%d' % (l + num_pblayers))
if dropout > 0 and self.is_train:
outputs = tf.nn.dropout(outputs, keep_prob=1.0 - dropout)
return outputs, output_seq_lengths