转载请注明出处:http://blog.csdn.net/dongdong9223/article/details/78968824 >本文出自【我是干勾鱼的博客】
Python如下代码:
#coding=utf-8
import tensorflow as tf
# NumPy是一个科学计算的工具包,这里通过NumPy工具包生成模拟数据集,
from numpy.random import RandomState
v = tf.constant([[1.0, 2.0, 3.0], [4.0, 5.0, 6.0]])
'''
#这段代码之前如果没有添加session,会报错:Cannot evaluate tensor using `eval()`: No default session is registered
print tf.clip_by_value(v, 2.5, 4.5).eval()
为避免报错应该使用下面的方式:
with tf.Session() as sess:
print tf.clip_by_value(v, 2.5, 4.5).eval()
'''
with tf.Session() as sess:
print tf.clip_by_value(v, 2.5, 4.5).eval()
会报如下错误:
Traceback (most recent call last):
File “constant_eval.py”, line 10, in
print tf.clip_by_value(v, 2.5, 4.5).eval()
File “/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py”, line 575, in eval
return _eval_using_default_session(self, feed_dict, self.graph, session)
File “/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py”, line 3619, in _eval_using_default_session
raise ValueError(“Cannot evaluate tensor usingeval()
: No default ”
ValueError: Cannot evaluate tensor usingeval()
: No default session is registered. Usewith sess.as_default()
or pass an explicit session toeval(session=sess)
如图所示:
可以如代码所示增加session的定义:
with tf.Session() as sess:
让print在其中运行就可以了,如图所示: