人工智能TensorFlow-Fetch和Feed

import tensorflow as tf 

Fetch的概念

Fetch指同时运行，意思是在Session中可以同时执行多个OP，得到其运行的结果

input1 = tf.constant(3.0)
input2 = tf.constant(2.0)
input3 = tf.constant(5.0)

add = tf.add(input2, input3)
mul = tf.multiply(input1, add)

with tf.Session() as sess:
    result = sess.run([mul, add])
    print(result)

[21.0, 7.0]

从上面可以看出，运行了两个OP，也得到了两个值

Feed的概念

# 创建两个占位符
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.]}))

[14.]

Feed允许在运行的时候再传入值

sess.run(output, feed_dict={input1:[7.0], input2:[2.0]})指定了要运行的OP，传入的参数。传入的参数要用字典来表示