tensorflow 部分函数笔记

• tf.identity(input, name=None)
  返回一个一模一样的新tensor
  示例：

import tensorflow as tf
a = tf.constant(1.0 , tf.float32)
init = tf.global_variables_initializer()
b = tf.identity(a)
with tf.Session() as sess:
    sess.run(init)
    print(sess.run(a))
    print(sess.run(b))

输出：

1.0
1.0

---

• tf.assign_add(ref, value, use_locking=None, name=None)
  通过增加一个值更新张量
  示例：

import tensorflow as tf
w = tf.Variable(1.0)
update = tf.assign_add(w , 1.0)
init = tf.global_variables_initializer()
with tf.Session() as sess:
    sess.run(init)
    print(sess.run(update))

输出：

2.0

---