tf.placeholder(dtype, shape=None, name=None)
placeholder,占位符,在tensorflow中类似于函数参数,运行时必须传入值。
- dtype:数据类型。常用的是tf.float32,tf.float64等数值类型。
- shape:数据形状。默认是None,就是一维值,也可以是多维,比如[2,3], [None, 3]表示列是3,行不定。
- name:名称。
tf.placeholder:用于得到传递进来的真实的训练样本:
- 不必指定初始值,可在运行时,通过 Session.run 的函数的 feed_dict 参数指定;
- 这也是其命名的原因所在,仅仅作为一种占位符;
代码片段-1(计算3*4=12)
#!/usr/bin/env python
# _*_ coding: utf-8 _*_
import tensorflow as tf
import numpy as np
input1 = tf.placeholder(tf.float32)
input2 = tf.placeholder(tf.float32)
output = tf.multiply(input1, input2)
with tf.Session() as sess:
print sess.run(output, feed_dict = {input1:[3.], input2: [4.]})
代码片段-2(计算矩阵相乘,x*x)
#!/usr/bin/env python
# _*_ coding: utf-8 _*_
import tensorflow as tf
import numpy as np
x = tf.placeholder(tf.float32, shape=(4, 4))
y = tf.matmul(x, x)
with tf.Session() as sess:
# print(sess.run(y)) # ERROR: x is none now
rand_array = np.random.rand(4, 4)
print(sess.run(y, feed_dict={x: rand_array}))
https://blog.csdn.net/zj360202/article/details/70243127
https://blog.csdn.net/zj360202/article/details/70243127