tensorflow入门

 

Start

https://tensorflow.google.cn/tutorials/

import tensorflow as tf
a = 3
# Create a variable.
w = tf.Variable([[0.5,1.0]],dtype=tf.float64)
x = tf.Variable([[2.0],[1.0]],dtype=tf.float64)
print(w)

y = tf.matmul(w, x)  


#variables have to be explicitly initialized before you can run Ops
init_op = tf.global_variables_initializer()
with tf.Session() as sess:
    sess.run(init_op)
    print (y.eval())

 

 Functions

with tf.Session() as sess:
    
    print(sess.run(tf.zeros([3, 4], tf.int32))) # ==> [[0, 0, 0, 0], [0, 0, 0, 0], [0, 0, 0, 0]]
      
    tensor = [[1, 2, 3], [4, 5, 6]]
    print(sess.run(tf.zeros_like(tensor))) # ==> [[0, 0, 0], [0, 0, 0]]
    print(sess.run(tf.ones([2, 3], tf.int32))) # ==> [[1, 1, 1], [1, 1, 1]]

    # 'tensor' is [[1, 2, 3], [4, 5, 6]]
    print(sess.run(tf.ones_like(tensor))) # ==> [[1, 1, 1], [1, 1, 1]]

    # Constant 1-D Tensor populated with value list.
    print(sess.run(tf.constant([1, 2, 3, 4, 5, 6, 7]))) # => [1 2 3 4 5 6 7]
          
    # Constant 2-D tensor populated with scalar value -1.
    print(sess.run(tf.constant(-1.0, shape=[2, 3])))  # => [[-1. -1. -1.]
                                                      #     [-1. -1. -1.]]

    print(sess.run(tf.linspace(10.0, 12.0, 3, name="linspace"))) # => [ 10.0  11.0  12.0]

    start = 3
    limit = 18
    delta = 3
    print(sess.run(tf.range(start, limit, delta))) # ==> [3, 6, 9, 12, 15]
norm = tf.random_normal([2, 3], mean=-1, stddev=4)

# Shuffle the first dimension of a tensor
c = tf.constant([[1, 2], [3, 4], [5, 6]])
shuff = tf.random_shuffle(c)

# Each time we run these ops, different results are generated
sess = tf.Session()
print (sess.run(norm))
print (sess.run(shuff))
state = tf.Variable(0)
new_value = tf.add(state, tf.constant(1))
update = tf.assign(state, new_value)

with tf.Session() as sess:
    sess.run(tf.global_variables_initializer())
    print(sess.run(state))    
    for _ in range(3):
        sess.run(update)
        print(sess.run(state))

# 输出
# 0
# 1
# 2
# 3
import numpy as np
a = np.zeros((3,3))
ta = tf.convert_to_tensor(a)
with tf.Session() as sess:
     print(sess.run(ta))

输出
[[0. 0. 0.]
[0. 0. 0.]
[0. 0. 0.]]
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.]}))

 

Model Save/Restore

注意,如下两段代码,不能再同一文件中执行。

v1 = tf.Variable(tf.random_normal([1,2]), name="v1")
v2 = tf.Variable(tf.random_normal([2,3]), name="v2")

因为v1和v2只能初始化一次,第二次执行时,name会被tensorflow自动分配成v1_1,v2_1

Save:

import tensorflow as tf

v1 = tf.Variable(tf.random_normal([1,2]), name="v1")
v2 = tf.Variable(tf.random_normal([2,3]), name="v2")
print ("V1:", v1)  
print ("V2:", v2)
init_op = tf.global_variables_initializer()
saver = tf.train.Saver()
with tf.Session() as sess:
    sess.run(init_op)
    print ("V1:",sess.run(v1))  
    print ("V2:",sess.run(v2))
    saver_path = saver.save(sess, "save/model.ckpt")
    print ("Model saved in file: ", saver_path)

Restore:

import tensorflow as tf
v1 = tf.Variable(tf.random_normal([1,2]), name="v1")
v2 = tf.Variable(tf.random_normal([2,3]), name="v2")
print ("v1 =", v1)
print ("v2 =", v2)
saver = tf.train.Saver()
with tf.Session() as sess:
    saver.restore(sess, "save/model.ckpt")
    print ("Model restored")
    print ("V1:", sess.run(v1), ", V2:", sess.run(v2))
    print ("V1:", sess.run(v1), ", V2:", sess.run(v2))

 

posted @ 2018-08-30 16:08  xbit  阅读(188)  评论(0编辑  收藏  举报