TensorFlow 入门

1. 第一个TensorFlow程序

import tensorflow as tf

a = tf.constant(2)
b = tf.constant(3)

x = tf.add(a, b)

with tf.Session() as sess:
    print (sess.run(x))

输出：5

2.  使用TensorBoard进行可视化

代码如下：

import tensorflow as tf

a = tf.constant(2)
b = tf.constant(3)

x = tf.add(a, b)

with tf.Session() as sess:
    writer = tf.summary.FileWriter('./graphs', sess.graph)
    print (sess.run(x))

writer.close()

代码保存为：visual.py，在terminal下运行：

$python  visual.py

$tensorboard --logdir="./graphs" --port 6006

在浏览器中打开http://127.0.1.1:6006， 如下界面

从上图中可以看出使用Const和Const_1作为输入名，可以按照如下方式进行修改，代码修改如下

import tensorflow as tf

a = tf.constant(2, name="a")
b = tf.constant(3, name="b")

x = tf.add(a, b, name="add")

with tf.Session() as sess:
    writer = tf.summary.FileWriter('./graphs', sess.graph)
    print (sess.run(x))

writer.close()

得到如下的可视化图形

3. tensorflow操作

a = tf.constant([3, 6])
b = tf.constant([2, 2])

tf.add(a, b)        #>> [5, 8]
tf.add_n([a, b, b]) #>> [7,10]. 等价与 a+b+b
tf.mul(a, b)        #>> [6, 12], mul是各个元素相乘
tf.matmul(a, b)     #>> 值错误
tf.matmul(tf.reshape(a, [1, 2]), tf.reshape(b, [2, 1])) #>> [[18]]
tf.div(a, b)        #>> [1,3]
tf.mod(a, b)        #>> [1,0]

4.tensorflow数据类型

Tensorflow使用python内置的类型：boolean, numeric(int, float), strings


0-d tensorflow或‘标量(scalar)’

t_0 = 19
tf.zeros_like(t_0)      # ==> 0
tf.ones_like(t_0)       # ==> 1

1-d tensorflow或“矢量(vector)”

t_1 = ['apple', 'peach', 'banana']
tf.zeros_like(t_1)	# ==>  ????

2-d tensorflow,或“矩阵(matrix)”

t_2 = [[True, False, False],
 [False, False, True],
 [False, True, False]]
tf.zeros_like(t_2) # ==> 2x2 tensor, all elements are False
tf.ones_like(t_2) # ==> 2x2 tensor, all elements are True