tf.placeholder(dtype, shape=None, name=None)
此函数可以理解为形参,用于定义过程,在执行的时候再赋具体的值。
- dtype:数据类型。一般要加上tf.float32,否则报错
- 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。
import tensorflow as tf
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:[7.],input2:[2.]}))
import tensorflow as tf
import numpy as np
x = tf.placeholder(tf.float32, shape=(14, 14))
y = tf.matmul(x, x)
with tf.Session() as sess:
rand_array = np.random.rand(14, 14)
print(sess.run(y, feed_dict={x: rand_array})) # Will succeed.