当你需要一个可以修改的tensor的时候,就不能使用tf.paaceholder()和tf.constant()了,这时候需要tf.Variable()函数。
tf.Variable(initializer, name):initializer是初始化参数,可以有tf.random_normal,tf.constant,tf.constant等,name就是变量的名字,用法如下:
import tensorflow as tf; import numpy as np; import matplotlib.pyplot as plt; a1 = tf.Variable(tf.random_normal(shape=[2,3], mean=0, stddev=1), name='a1') a2 = tf.Variable(tf.constant(1), name='a2') a3 = tf.Variable(tf.ones(shape=[2,3]), name='a3') with tf.Session() as sess: sess.run(tf.initialize_all_variables()) print sess.run(a1) print sess.run(a2) print sess.run(a3)输出:
[[ 0.76599932 0.99722123 -0.89361787]
[ 0.19991693 -0.16539733 2.16605783]]
1
[[ 1. 1. 1.]
[ 1. 1. 1.]]