本文整理汇总了Python中data_utils.namignizer_iterator方法的典型用法代码示例。如果您正苦于以下问题：Python data_utils.namignizer_iterator方法的具体用法？Python data_utils.namignizer_iterator怎么用？Python data_utils.namignizer_iterator使用的例子？那么恭喜您, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类data_utils的用法示例。
在下文中一共展示了data_utils.namignizer_iterator方法的2个代码示例，这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞，您的评价将有助于系统推荐出更棒的Python代码示例。
示例1: run_epoch
# 需要导入模块: import data_utils [as 别名]
# 或者: from data_utils import namignizer_iterator [as 别名]
def run_epoch(session, m, names, counts, epoch_size, eval_op, verbose=False):
"""Runs the model on the given data for one epoch
Args:
session: the tf session holding the model graph
m: an instance of the NamignizerModel
names: a set of lowercase names of 26 characters
counts: a list of the frequency of the above names
epoch_size: the number of batches to run
eval_op: whether to change the params or not, and how to do it
Kwargs:
verbose: whether to print out state of training during the epoch
Returns:
cost: the average cost during the last stage of the epoch
"""
start_time = time.time()
costs = 0.0
iters = 0
for step, (x, y) in enumerate(data_utils.namignizer_iterator(names, counts,
m.batch_size, m.num_steps, epoch_size)):
cost, _ = session.run([m.cost, eval_op],
{m.input_data: x,
m.targets: y,
m.weights: np.ones(m.batch_size * m.num_steps)})
costs += cost
iters += m.num_steps
if verbose and step % (epoch_size // 10) == 9:
print("%.3f perplexity: %.3f speed: %.0f lps" %
(step * 1.0 / epoch_size, np.exp(costs / iters),
iters * m.batch_size / (time.time() - start_time)))
if step >= epoch_size:
break
return np.exp(costs / iters) 示例2: run_epoch
# 需要导入模块: import data_utils [as 别名]
# 或者: from data_utils import namignizer_iterator [as 别名]
def run_epoch(session, m, names, counts, epoch_size, eval_op, verbose=False):
"""Runs the model on the given data for one epoch
Args:
session: the tf session holding the model graph
m: an instance of the NamignizerModel
names: a set of lowercase names of 26 characters
counts: a list of the frequency of the above names
epoch_size: the number of batches to run
eval_op: whether to change the params or not, and how to do it
Kwargs:
verbose: whether to print out state of training during the epoch
Returns:
cost: the average cost during the last stage of the epoch
"""
start_time = time.time()
costs = 0.0
iters = 0
for step, (x, y) in enumerate(data_utils.namignizer_iterator(names, counts,
m.batch_size, m.num_steps, epoch_size)):
cost, _ = session.run([m.cost, eval_op],
{m.input_data: x,
m.targets: y,
m.initial_state: m.initial_state.eval(),
m.weights: np.ones(m.batch_size * m.num_steps)})
costs += cost
iters += m.num_steps
if verbose and step % (epoch_size // 10) == 9:
print("%.3f perplexity: %.3f speed: %.0f lps" %
(step * 1.0 / epoch_size, np.exp(costs / iters),
iters * m.batch_size / (time.time() - start_time)))
if step >= epoch_size:
break
return np.exp(costs / iters)