tensorflow學習之tf.assign

tf.assign(ref, value, validate_shape=None, use_locking=None, name=None)，

函數功能是將value賦值給ref

ref必須是tf.Variable創建的tensor，如果ref=tf.constant()就會報錯，而且默認情況下ref的shape和value的shape是相同的

 

import tensorflow as tf
state = tf.Variable(0,name='counter')
print(state.name)
one = tf.constant(1)
new_value = tf.add(state,one)
update = tf.assign(state,new_value)
init = tf.global_variables_initializer()

with tf.Session() as sess:
    sess.run(init)
    for __ in range(3):
        sess.run(update)
        print(sess.run(state))


#counter:0
1
2
3