入门--tensorflow

最新推荐文章于 2025-12-21 09:00:14 发布

原创最新推荐文章于 2025-12-21 09:00:14 发布 · 136 阅读

0 ·

CC 4.0 BY-SA版权

文章标签：

#tensorflow

本文详细介绍如何使用Anaconda环境搭建TensorFlow开发平台，并演示了基本的数据类型操作、算术运算、矩阵运算，以及创建常用张量的方法。通过实例，读者可以快速掌握TensorFlow的基本用法。

部署运行你感兴趣的模型镜像

搭建：anaconda + tensorflow
begin：

import tensorflow as tf
data1 = tf.constant(2, dtype=tf.int32)
data2 = tf.Variable(10, name='var')
print(data1, data2)
sess = tf.Session()
'''
print(sess.run(data1))
init = tf.global_variables_initializer()
sess.run(init)
print(sess.run(data2))
sess.close()
'''
init = tf.global_variables_initializer()
with sess:
    sess.run(init)
    print(sess.run(data2))

tf.Session() 会话
init = tf.global_variables_initializer()
init = tf.initialize_all_variables()
{WARNING:tensorflow:From C:\Users\cd\Anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\util\tf_should_use.py:193: initialize_all_variables (from tensorflow.python.ops.variables) is deprecated and will be removed after 2017-03-02.
Instructions for updating:
Use tf.global_variables_initializer instead.}
输出：

Tensor("Const:0", shape=(), dtype=int32) <tf.Variable 'var:0' shape=() dtype=int32_ref>
10

基础运算：

import tensorflow as tf
data1 = tf.constant(6)
data2 = tf.constant(2)
dataAdd = tf.add(data1, data2)
dataMul = tf.multiply(data1, data2)
dataSub = tf.subtract(data1, data2)
dataDiv = tf.divide(data1, data2)
with tf.Session() as sess:
    print(sess.run(dataAdd))
    print(sess.run(dataMul))
    print(sess.run(dataSub), sess.run(dataDiv))

输出：

8
12
4 3.0

矩阵运算：

import tensorflow as tf
data1 = tf.constant([6,6])
data2 = tf.constant([[2],
                     [2]])
data3 = tf.constant([[1,2],
                    [3,4],
                    [5,6]])
print(data3.shape)
with tf.Session() as sess:
    print(sess.run(data3))
    print(sess.run(data3[0]))
    print(sess.run(data3[:,0]))

输出：

(3, 2)
[[1 2]
 [3 4]
 [5 6]]
[1 2]
[1 3 5]

其它：

import tensorflow as tf
mat1 = tf.constant([[0,0,0],[0,0,0]])
mat2 = tf.zeros([2,3])
mat3 = tf.fill([2,3],14)
mat4 = tf.zeros_like(mat1)
mat5 = tf.linspace(0.0,2.0,11)
mat6 = tf.random_uniform([2,3],-1,2)
with tf.Session() as sess:
    print(sess.run(mat1))
    print(sess.run([[mat2],[mat3]]))
    print(sess.run(mat4))
    print(sess.run(mat5))
    print(sess.run(mat6))

输出：

[[0 0 0]
 [0 0 0]]
[[array([[ 0.,  0.,  0.],
       [ 0.,  0.,  0.]], dtype=float32)], [array([[14, 14, 14],
       [14, 14, 14]])]]
[[0 0 0]
 [0 0 0]]
[ 0.          0.2         0.40000001  0.60000002  0.80000001  1.
  1.20000005  1.39999998  1.60000002  1.80000007  2.        ]
[[ 0.44188511  1.27390599  1.53598404]
 [ 0.39836574  1.29693556  0.00948727]]

您可能感兴趣的与本文相关的镜像