|
; "Train using 16-bit floats instead of 32bit floats")
#FLAGS = flags.FLAGS
#def data_type():
# return tf.float16 if FLAGS.use_fp16 else tf.float32
class PTBInput(object):
"""The input data."""
def __init__(self, config, data, name=None):
self.batch_size = batch_size = config.batch_size
self.num_steps = num_steps = config.num_steps
self.epoch_size = ((len(data) // batch_size) - 1) // num_steps
self.input_data, self.targets = reader.ptb_producer(
data, batch_size, num_steps, name=name)
class PTBModel(object):
"""The PTB model."""
def __init__(self, is_training, config, input_):
self._input = input_
batch_size = input_.batch_size
num_steps = input_.num_steps
size = config.hidden_size
vocab_size = config.vocab_size
# Slightly better results can be obtained with forget gate biases
# initialized to 1 but the hyperparameters of the model would need to be
# different than reported in the paper.
def lstm_cell():
return tf.contrib.rnn.BasicLSTMCell(
size, forget_bias=0.0, state_is_tuple=True)
attn_cell = lstm_cell
if is_training and config.keep_prob < 1:
def attn_cell():
return tf.contrib.rnn.DropoutWrapper(
lstm_cell(), output_keep_prob=config.keep_prob)
cell = tf.contrib.rnn.MultiRNNCell(
[attn_cell() for _ in range(config.num_layers)], state_is_tuple=True)
self._initial_state = cell.zero_state(batch_size, tf.float32)
with tf.device("/cpu:0"):
embedding = tf.get_variable(
"embedding", [vocab_size, size], dtype=tf.float32)
inputs = tf.nn.embedding_lookup(embedding, input_.input_data)
if is_training and config.keep_prob < 1:
inputs = tf.nn.dropout(inputs, config.keep_prob)
# Simplified version of models/tutorials/rnn/rnn.py's rnn().
# This builds an unrolled LSTM for tutorial purposes only.
# In general, use the rnn() or state_saving_rnn() from rnn.py.
#
# The alternative version of the code below is:
#
# inputs = tf.unstack(inputs, num=num_steps, axis=1)
# outputs, state = tf.nn.rnn(cell, inputs,
# initial_state=self._initial_state)
outputs = []
state = self._initial_state
with tf.variable_scope("RNN"):
for time_step in range(num_steps):
if time_step > 0: tf.get_variable_scope().reuse_variables()
(cell_output, state) = cell(inputs[:, time_step, :], state)
outputs.append(cell_output)
|