zoukankan      html  css  js  c++  java
  • TensorFlow简单介绍和在centos上的安装

     
    ##tensorflow简单介绍:

    TensorFlow™ is an open source software library for numerical computation using data flow graphs.https://www.tensorflow.org/
    TensorFlow是谷歌基于DistBelief进行研发的第二代人工智能学习系统,其命名来源于本身的运行原理。Tensor(张量)意味着N维数组,Flow(流)意味着基于数据流图的计算,TensorFlow为张量从图象的一端流动到另一端计算过程。
    选择virtualenv install的方法;TensorFlow支持CNN、RNN和LSTM算法,这都是目前在Image,Speech和NLP最流行的深度神经网络模型。


    ##tensorflow安装步骤:
     [biostack@localhost.localdomain ylHe_test]$ virtualenv --system-site-packages ~/tensorflow
    New python executable in /home/biostack/tensorflow/bin/python
    Installing Setuptools..............................................................................................................................................................................................................................done.
    Installing Pip.....................................................................................................................................................................................................................................................................................................................................done.

    [biostack@localhost.localdomain ylHe_test]$ source ~/tensorflow/bin/activate

    (tensorflow)[biostack@localhost.localdomain ylHe_test]$ export TF_BINARY_URL=https://storage.googleapis.com/tensorflow/linux/cpu/tensorflow-0.11.0rc1-cp27-none-linux_x86_64.whl

    (tensorflow)[biostack@localhost.localdomain ylHe_test]$ sudo pip install --upgrade $TF_BINARY_URL --trusted-host pypi.douban.com
    Collecting tensorflow==0.11.0rc1 from https://storage.googleapis.com/tensorflow/linux/cpu/tensorflow-0.11.0rc1-cp27-none-linux_x86_64.whl
      Using cached https://storage.googleapis.com/tensorflow/linux/cpu/tensorflow-0.11.0rc1-cp27-none-linux_x86_64.whl
    Requirement already up-to-date: six>=1.10.0 in /usr/lib/python2.7/site-packages (from tensorflow==0.11.0rc1)
    Collecting wheel (from tensorflow==0.11.0rc1)
      Downloading http://pypi.doubanio.com/packages/8a/e9/8468cd68b582b06ef554be0b96b59f59779627131aad48f8a5bce4b13450/wheel-0.29.0-py2.py3-none-any.whl (66kB)
        100% |████████████████████████████████| 71kB 3.4MB/s
    Collecting mock>=2.0.0 (from tensorflow==0.11.0rc1)
      Downloading http://pypi.doubanio.com/packages/e6/35/f187bdf23be87092bd0f1200d43d23076cee4d0dec109f195173fd3ebc79/mock-2.0.0-py2.py3-none-any.whl (56kB)
        100% |████████████████████████████████| 61kB 2.7MB/s
    Collecting numpy>=1.11.0 (from tensorflow==0.11.0rc1)
      Downloading http://pypi.doubanio.com/packages/5e/d5/3433e015f3e4a1f309dbb110e8557947f68887fe9b8438d50a4b7790a954/numpy-1.11.2-cp27-cp27mu-manylinux1_x86_64.whl (15.3MB)
        100% |████████████████████████████████| 15.3MB 4.3MB/s
    Collecting protobuf==3.0.0 (from tensorflow==0.11.0rc1)
      Downloading http://pypi.doubanio.com/packages/97/e4/b2e4c62394cf1bf69b6b1261a0e8d864672a8b9c975a1bc2803fda2c35b7/protobuf-3.0.0-py2.py3-none-any.whl (342kB)
        100% |████████████████████████████████| 348kB 4.1MB/s
    Collecting funcsigs>=1; python_version < "3.3" (from mock>=2.0.0->tensorflow==0.11.0rc1)
      Downloading http://pypi.doubanio.com/packages/69/cb/f5be453359271714c01b9bd06126eaf2e368f1fddfff30818754b5ac2328/funcsigs-1.0.2-py2.py3-none-any.whl
    Collecting pbr>=0.11 (from mock>=2.0.0->tensorflow==0.11.0rc1)
      Downloading http://pypi.doubanio.com/packages/b8/a1/7abb01fd93d66fc71e24e5df9ca6d7d9acfb4b715937d2a38fd739f266e6/pbr-1.10.0-py2.py3-none-any.whl (96kB)
        100% |████████████████████████████████| 102kB 2.9MB/s
    Collecting setuptools (from protobuf==3.0.0->tensorflow==0.11.0rc1)
      Downloading http://pypi.doubanio.com/packages/74/c5/c78a788e65f9eb241c531839e909df1226534ea2d09d300231766b82b79a/setuptools-28.7.1-py2.py3-none-any.whl (472kB)
        100% |████████████████████████████████| 481kB 4.7MB/s
    Installing collected packages: wheel, funcsigs, pbr, mock, numpy, setuptools, protobuf, tensorflow
      Found existing installation: mock 1.0.1
        Uninstalling mock-1.0.1:
          Successfully uninstalled mock-1.0.1
      Found existing installation: numpy 1.11.1
        Uninstalling numpy-1.11.1:
          Successfully uninstalled numpy-1.11.1
      Found existing installation: setuptools 24.0.3
        Uninstalling setuptools-24.0.3:
          Successfully uninstalled setuptools-24.0.3
    Successfully installed funcsigs-1.0.2 mock-2.0.0 numpy-1.11.2 pbr-1.10.0 protobuf-3.0.0 setuptools-28.7.1 tensorflow-0.11.0rc1 wheel-0.29.0

    ##简单的测试
    (tensorflow)[biostack@localhost.localdomain ylHe_test]$ python
    Python 2.7.5 (default, Sep 15 2016, 22:37:39)
    [GCC 4.8.5 20150623 (Red Hat 4.8.5-4)] on linux2
    Type "help", "copyright", "credits" or "license" for more information.
    >>> import tensorflow as tf
    >>> hello = tf.constant("hello,tensorflow")
    >>> sess = tf.Session()
    >>> print(sess.run(hello))
    hello,tensorflow
    >>> exit()




    学习连接:http://blog.csdn.net/lynnandwei/article/details/51722119

  • 相关阅读:
    透过WebGL 3D看动画Easing函数本质
    vmware虚拟机Windows 2003上网问题
    JAVA多态学习2
    h5播放音乐
    Unity3D:粒子系统Particle System
    文章标题
    【面试加分项】java自己定义注解之申明注解
    osgi实战学习之路:1. ant+bnd+felix搭建osgi之HelloWorld
    Android简单实现Socket通信,client连接server后,server向client发送文字数据
    句子开头
  • 原文地址:https://www.cnblogs.com/ylHe/p/6024682.html
Copyright © 2011-2022 走看看