《深度学习之Tensorflow》学习笔记三

最新推荐文章于 2024-10-01 20:17:55 发布

COST_97

最新推荐文章于 2024-10-01 20:17:55 发布

阅读量178

点赞数

分类专栏：本三上学期学习笔记文章标签：深度学习

本三上学期学习笔记专栏收录该内容

11 篇文章 0 订阅

订阅专栏

计算图的相关操作

import tensorflow as tf
import numpy as np

#建立图
# c = tf.constant(0.)
#
# g = tf.Graph()
# with g.as_default():
#     c1 = tf.constant(0.)
#     # print(c1.graph)
#     # print(g)
#     # print(c.graph)
#     print(c1.name)
#     t = g.get_tensor_by_name(name='Const:0')
#     print(t)
# g2 = tf.get_default_graph()
# print(g2)
#
# tf.reset_default_graph()
# g3 = tf.get_default_graph()
# print(g3)
a = tf.constant([[1.,2.]])
b = tf.constant([[1.],[3.]])

tensor1 = tf.matmul(a, b, name='example_op')
# print(tensor1.name,tensor1)

g3 = tf.get_default_graph()
test = g3.get_tensor_by_name('example_op:0')
# print(test)

# print(tensor1.op.name)
testop = g3.get_operation_by_name('example_op')
# print(testop)

with tf.Session() as sess:
    test = sess.run(test)
    print(test)
    test = tf.get_default_graph().get_tensor_by_name("example_op:0")
    print(test)