Tensorflow學習教程------Fetch and Feed

Fetch的意思就是在一個會話（session）中可以同時運行多個op。

#coding:utf-8
import tensorflow as tf 
#Fetch
input1 = tf.constant(3.0)
input2 = tf.constant(1.0)
input3 = tf.constant(5.0)
add = tf.add(input1,input2)
mul = tf.multiply(input1,add)
with tf.Session() as sess:
    result = sess.run([mul,add]) #同時運行兩個op
    print (result)
結果

Total memory: 10.91GiB
Free memory: 10.21GiB
I tensorflow/core/common_runtime/gpu/gpu_device.cc:906] DMA: 0 
I tensorflow/core/common_runtime/gpu/gpu_device.cc:916] 0:   Y 
I tensorflow/core/common_runtime/gpu/gpu_device.cc:975] Creating TensorFlow device (/gpu:0) -> (device: 0, name: GeForce GTX 1080 Ti, pci bus id: 0000:03:00.0)
[12.0, 4.0]

 

Feed的字面意思是喂養，流入。在tensorflow里面就是說先聲明一個或者幾個tensor，先用占位符給他們留幾個位置，等到后面run的時候，再以其他形式比如字典的形式把值傳進去，相當於買了兩個存錢罐，先不存錢，等我想存的時候我再把錢一張一張“喂”進去。

#Feed
#創建占位符
input1 = tf.placeholder(tf.float32)
input2 = tf.placeholder(tf.float32)
output = tf.multiply(input1,input2)

with tf.Session() as sess:
    #feed的數據以字典的形式傳入
    print (sess.run(output,feed_dict={input1:[7.], input2:[8.]}))

結果

I tensorflow/core/common_runtime/gpu/gpu_device.cc:975] Creating TensorFlow device (/gpu:0) -> (device: 0, name: GeForce GTX 1080 Ti, pci bus id: 0000:03:00.0)
[ 56.]