output = tf.reshape(tf.concat(outputs, 1), [-1, size])
softmax_w = tf.get_variable(
"softmax_w", [size, vocab_size], dtype=tf.float32)
softmax_b = tf.get_variable("softmax_b", [vocab_size], dtype=tf.float32)
logits = tf.matmul(output, softmax_w) + softmax_b
loss = tf.contrib.legacy_seq2seq.sequence_loss_by_example(
[logits],
[tf.reshape(input_.targets, [-1])],
[tf.ones([batch_size * num_steps], dtype=tf.float32)])
self._cost = cost = tf.reduce_sum(loss) / batch_size
self._final_state = state
if not is_training:
return
self._lr = tf.Variable(0.0, trainable=False)
tvars = tf.trainable_variables()
grads, _ = tf.clip_by_global_norm(tf.gradients(cost, tvars),
config.max_grad_norm)
optimizer = tf.train.GradientDescentOptimizer(self._lr)
self._train_op = optimizer.apply_gradients(
zip(grads, tvars),
global_step=tf.contrib.framework.get_or_create_global_step())
self._new_lr = tf.placeholder(
tf.float32, shape=[], name="new_learning_rate")
self._lr_update = tf.assign(self._lr, self._new_lr)
def assign_lr(self, session, lr_value):
session.run(self._lr_update, feed_dict={self._new_lr: lr_value})
@property
def input(self):
return self._input
@property
def initial_state(self):
return self._initial_state
@property
def cost(self):
return self._cost
@property
def final_state(self):
return self._final_state
@property
def lr(self):
return self._lr
@property
def train_op(self):
return self._train_op
class SmallConfig(object):
"""Small config."""
init_scale = 0.1
learning_rate = 1.0
max_grad_norm = 5
num_layers = 2
num_steps = 20
hidden_size = 200
max_epoch = 4
max_max_epoch = 13
keep_prob = 1.0
lr_decay = 0.5
batch_size = 20
vocab_size = 10000
class MediumConfig(object):
"""Medium config."""
init_scale = 0.05
learning_rate = 1.0
max_grad_norm = 5
num_layers = 2
num_steps = 35
hidden_size = 650
max_epoch = 6
max_max_epoch = 39
keep_prob = 0.5
lr_decay = 0.8
batch_size = 20
vocab_size = 10000
class LargeConfig(object):
"""Large config."""
init_scale = 0.04
learning_rate = 1.0
max_grad_norm = 10
num_layers = 2
num_steps = 35
hidden_size = 1500
max_epoch = 14
max_max_epoch = 55
keep_prob = 0.35
lr_decay = 1 / 1.15
batch_size = 20
vocab_size = 10000
class |