Tensorflow tf.placeholder

转载：https://blog.csdn.net/cc1949/article/details/78364615

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。

计算3*4=12

1. dtype:类型  常用的是tf.float32,tf.float64等数值类型
2. 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,行不确定
3. name:名称

#!/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.]})

 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=(1024, 1024))
y = tf.matmul(x, x)
 
with tf.Session() as sess:
#  print(sess.run(y))  # ERROR: x is none now
  rand_array = np.random.rand(1024, 1024)
  print(sess.run(y, feed_dict={x: rand_array}))  # Will succeed.