本文整理汇总了Python中model.ckpt方法的典型用法代码示例。如果您正苦于以下问题：Python model.ckpt方法的具体用法？Python model.ckpt怎么用？Python model.ckpt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model的用法示例。
在下文中一共展示了model.ckpt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: get_checkpoint_num
# 需要导入模块: import model [as 别名]
# 或者: from model import ckpt [as 别名]
def get_checkpoint_num(checkpoint_path):
m = re.match('^/.+model.ckpt-([0-9]+)$', checkpoint_path)
return int(m.group(1)) 示例2: eval_once
# 需要导入模块: import model [as 别名]
# 或者: from model import ckpt [as 别名]
def eval_once(saver, top_k_op):
"""Run Eval once.
Args:
saver: Saver.
summary_writer: Summary writer.
top_k_op: Top K op.
"""
with tf.Session() as sess:
ckpt = tf.train.get_checkpoint_state(FLAGS.checkpoint_dir)
if ckpt and ckpt.model_checkpoint_path:
# Restores from checkpoint
saver.restore(sess, ckpt.model_checkpoint_path)
# Assuming model_checkpoint_path looks something like:
# /my-favorite-path/MNIST_train/model.ckpt-0,
# extract global_step from it.
global_step = ckpt.model_checkpoint_path.split('/')[-1].split('-')[
-1]
else:
print('No checkpoint file found')
return
predictions = np.sum(sess.run([top_k_op]))
# Compute precision.
print('%s: precision = %.3f' % (datetime.now(), predictions))