TensorFlow安装

最新推荐文章于 2024-03-05 21:41:05 发布

Cache969

最新推荐文章于 2024-03-05 21:41:05 发布

阅读量377

点赞数

CC 4.0 BY-SA版权

分类专栏： AI TensorFlow

本文链接：https://blog.youkuaiyun.com/dutlxq2014/article/details/56926793

TensorFlow 同时被 2 个专栏收录

1 篇文章

订阅专栏

0 篇文章

订阅专栏

本文详细介绍了在MacOSX系统上使用Virtualenv安装TensorFlow的过程，并验证了安装的成功。此外，还提供了一个运行TensorFlow自带示例的完整过程，该示例通过训练一个简单的卷积神经网络来识别手写数字。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

TensorFlow安装

　　使用TensorFlow前需要先安装TensorFlow的环境，这个官方提供的安装文档： https://www.tensorflow.org/versions/r0.10/get_started/os_setup，有多种安装方式可选：

Pip install
Virtualenv install
Anaconda install
Docker install
Installing from sources

　　我选择了第二种 Virtualenv install 的安装方式，环境是Mac OS X 10.12.2系统，Python 2.7.10。

安装步骤如下：

Install pip and Virtualenv.
Create a Virtualenv environment.
Activate the Virtualenv environment and install TensorFlow in it.
After the install you will activate the Virtualenv environment each time you want to use TensorFlow.
When finish using tensorflow, deactivate the Virtualenv environment.

第一步：安装Python包管理工具 [pip](https://en.wikipedia.org/wiki/Pip_(package_manager) 和虚拟环境 Virtualenv，Virtualenv保证项目依赖的包不会覆盖已有的包：

# Mac OS X
$ sudo easy_install pip
$ sudo easy_install --upgrade six

第二步：在~/tensorflow环境下创建一个虚拟环境

virtualenv --system-site-packages ~/tensorflow

第三步：激活环境

$ source ~/tensorflow/bin/activate  # If using bash
$ source ~/tensorflow/bin/activate.csh  # If using csh
(tensorflow)$  # Your prompt should change

第四步：使用pip安装 TensorFlow 的二进制安装包，简单起见我选择安装了CPU版本：

# Mac OS X, CPU only, Python 2.7:
$ export TF_BINARY_URL=https://storage.googleapis.com/tensorflow/mac/cpu/tensorflow-0.10.0-py2-none-any.whl

执行安装

# Python 2
$ sudo pip install --upgrade $TF_BINARY_URL

# Python 3
$ sudo pip3 install --upgrade $TF_BINARY_URL

　　最后要验证安装是否成功，在命令行下进入Python的REPL环境，执行下面的语句，或者直接新建Python文件进行验证更方便一些：

$ python
...
>>> import tensorflow as tf
>>> hello = tf.constant('Hello, TensorFlow!')
>>> sess = tf.Session()
>>> print(sess.run(hello))
Hello, TensorFlow!
>>> a = tf.constant(10)
>>> b = tf.constant(32)
>>> print(sess.run(a + b))
42
>>>

　　有一点需要注意，使用完后通过 deactivate 命令可以退出Virtualenv环境，下次如果要再次使用TensorFlow，需要再次激活这个环境 source ~/tensorflow/bin/activate

　　最后跑一个简单的 tensorflow 例子，是安装包自带的example，识别手写的数字[0-9]，属于有监督学习的范畴，网上有不少文章分析了这个例子对应的算法，主要是逻辑回归算法的应用。要运行的Demo脚本在这个目录下：~/tensorflow/lib/python2.7/site-packages/tensorflow/models/image/mnist/convolutional.py，直接运行就可以了：

python ~/tensorflow/lib/python2.7/site-packages/tensorflow/models/image/mnist/convolutional.py

Successfully downloaded train-images-idx3-ubyte.gz 9912422 bytes.
Successfully downloaded train-labels-idx1-ubyte.gz 28881 bytes.
Successfully downloaded t10k-images-idx3-ubyte.gz 1648877 bytes.
Successfully downloaded t10k-labels-idx1-ubyte.gz 4542 bytes.
Extracting data/train-images-idx3-ubyte.gz
Extracting data/train-labels-idx1-ubyte.gz
Extracting data/t10k-images-idx3-ubyte.gz
Extracting data/t10k-labels-idx1-ubyte.gz
Initialized!
Step 0 (epoch 0.00), 2.7 ms
Minibatch loss: 12.054, learning rate: 0.010000
Minibatch error: 90.6%
Validation error: 84.6%
Step 100 (epoch 0.12), 160.3 ms
Minibatch loss: 3.280, learning rate: 0.010000
Minibatch error: 6.2%
Validation error: 7.0%
Step 200 (epoch 0.23), 159.7 ms
Minibatch loss: 3.491, learning rate: 0.010000
Minibatch error: 12.5%
Validation error: 3.8%
Step 300 (epoch 0.35), 162.0 ms
Minibatch loss: 3.231, learning rate: 0.010000
Minibatch error: 7.8%
Validation error: 3.3%
Step 400 (epoch 0.47), 163.0 ms
Minibatch loss: 3.229, learning rate: 0.010000
Minibatch error: 10.9%
Validation error: 2.7%
Step 500 (epoch 0.58), 160.9 ms
Minibatch loss: 3.290, learning rate: 0.010000
Minibatch error: 7.8%
Validation error: 2.6%
Step 600 (epoch 0.70), 160.4 ms
Minibatch loss: 3.172, learning rate: 0.010000
Minibatch error: 6.2%
Validation error: 2.5%
Step 700 (epoch 0.81), 159.1 ms
Minibatch loss: 3.023, learning rate: 0.010000
Minibatch error: 3.1%
Validation error: 2.5%
Step 800 (epoch 0.93), 167.9 ms
Minibatch loss: 3.093, learning rate: 0.010000
Minibatch error: 6.2%
Validation error: 2.1%
Step 900 (epoch 1.05), 166.8 ms
Minibatch loss: 2.934, learning rate: 0.009500
Minibatch error: 3.1%
Validation error: 1.6%
Step 1000 (epoch 1.16), 161.6 ms
Minibatch loss: 2.871, learning rate: 0.009500
Minibatch error: 1.6%
Validation error: 1.6%
Step 1100 (epoch 1.28), 162.5 ms
Minibatch loss: 2.831, learning rate: 0.009500
Minibatch error: 1.6%
Validation error: 1.5%
Step 1200 (epoch 1.40), 162.5 ms
Minibatch loss: 2.916, learning rate: 0.009500
Minibatch error: 4.7%
Validation error: 1.5%
Step 1300 (epoch 1.51), 162.6 ms
Minibatch loss: 2.768, learning rate: 0.009500
Minibatch error: 0.0%
Validation error: 1.7%
Step 1400 (epoch 1.63), 159.9 ms
Minibatch loss: 2.772, learning rate: 0.009500
Minibatch error: 1.6%
Validation error: 1.5%
Step 1500 (epoch 1.75), 161.2 ms
Minibatch loss: 2.842, learning rate: 0.009500
Minibatch error: 4.7%
Validation error: 1.3%
Step 1600 (epoch 1.86), 179.3 ms
Minibatch loss: 2.714, learning rate: 0.009500
Minibatch error: 1.6%
Validation error: 1.4%
Step 1700 (epoch 1.98), 167.7 ms
Minibatch loss: 2.650, learning rate: 0.009500
Minibatch error: 0.0%
Validation error: 1.3%
Step 1800 (epoch 2.09), 161.6 ms
Minibatch loss: 2.665, learning rate: 0.009025
Minibatch error: 1.6%
Validation error: 1.3%
Step 1900 (epoch 2.21), 170.9 ms
Minibatch loss: 2.633, learning rate: 0.009025
Minibatch error: 1.6%
Validation error: 1.2%
Step 2000 (epoch 2.33), 170.6 ms
Minibatch loss: 2.616, learning rate: 0.009025
Minibatch error: 3.1%
Validation error: 1.2%
Step 2100 (epoch 2.44), 166.5 ms
Minibatch loss: 2.590, learning rate: 0.009025
Minibatch error: 1.6%
Validation error: 1.1%
Step 2200 (epoch 2.56), 173.8 ms
Minibatch loss: 2.573, learning rate: 0.009025
Minibatch error: 1.6%
Validation error: 1.1%
Step 2300 (epoch 2.68), 165.6 ms
Minibatch loss: 2.553, learning rate: 0.009025
Minibatch error: 1.6%
Validation error: 1.1%
Step 2400 (epoch 2.79), 166.6 ms
Minibatch loss: 2.505, learning rate: 0.009025
Minibatch error: 0.0%
Validation error: 1.1%
Step 2500 (epoch 2.91), 163.8 ms
Minibatch loss: 2.482, learning rate: 0.009025
Minibatch error: 0.0%
Validation error: 1.2%
Step 2600 (epoch 3.03), 171.7 ms
Minibatch loss: 2.459, learning rate: 0.008574
Minibatch error: 0.0%
Validation error: 1.2%
Step 2700 (epoch 3.14), 168.4 ms
Minibatch loss: 2.485, learning rate: 0.008574
Minibatch error: 1.6%
Validation error: 1.1%
Step 2800 (epoch 3.26), 169.3 ms
Minibatch loss: 2.427, learning rate: 0.008574
Minibatch error: 1.6%
Validation error: 1.3%
Step 2900 (epoch 3.37), 170.1 ms
Minibatch loss: 2.446, learning rate: 0.008574
Minibatch error: 3.1%
Validation error: 1.1%
Step 3000 (epoch 3.49), 167.7 ms
Minibatch loss: 2.398, learning rate: 0.008574
Minibatch error: 0.0%
Validation error: 1.1%
Step 3100 (epoch 3.61), 165.4 ms
Minibatch loss: 2.374, learning rate: 0.008574
Minibatch error: 1.6%
Validation error: 1.0%
Step 3200 (epoch 3.72), 164.1 ms
Minibatch loss: 2.332, learning rate: 0.008574
Minibatch error: 0.0%
Validation error: 1.1%
Step 3300 (epoch 3.84), 176.3 ms
Minibatch loss: 2.310, learning rate: 0.008574
Minibatch error: 0.0%
Validation error: 1.3%
Step 3400 (epoch 3.96), 167.7 ms
Minibatch loss: 2.301, learning rate: 0.008574
Minibatch error: 1.6%
Validation error: 1.0%
Step 3500 (epoch 4.07), 172.6 ms
Minibatch loss: 2.276, learning rate: 0.008145
Minibatch error: 0.0%
Validation error: 1.0%
Step 3600 (epoch 4.19), 166.1 ms
Minibatch loss: 2.257, learning rate: 0.008145
Minibatch error: 0.0%
Validation error: 0.9%
Step 3700 (epoch 4.31), 173.9 ms
Minibatch loss: 2.233, learning rate: 0.008145
Minibatch error: 0.0%
Validation error: 0.9%
Step 3800 (epoch 4.42), 167.2 ms
Minibatch loss: 2.237, learning rate: 0.008145
Minibatch error: 1.6%
Validation error: 0.9%
Step 3900 (epoch 4.54), 173.0 ms
Minibatch loss: 2.285, learning rate: 0.008145
Minibatch error: 3.1%
Validation error: 0.9%
Step 4000 (epoch 4.65), 173.5 ms
Minibatch loss: 2.210, learning rate: 0.008145
Minibatch error: 1.6%
Validation error: 1.0%
Step 4100 (epoch 4.77), 177.2 ms
Minibatch loss: 2.167, learning rate: 0.008145
Minibatch error: 0.0%
Validation error: 0.9%
Step 4200 (epoch 4.89), 179.8 ms
Minibatch loss: 2.216, learning rate: 0.008145
Minibatch error: 1.6%
Validation error: 1.0%
Step 4300 (epoch 5.00), 171.8 ms
Minibatch loss: 2.190, learning rate: 0.007738
Minibatch error: 1.6%
Validation error: 0.9%
Step 4400 (epoch 5.12), 169.9 ms
Minibatch loss: 2.159, learning rate: 0.007738
Minibatch error: 3.1%
Validation error: 1.0%
Step 4500 (epoch 5.24), 176.5 ms
Minibatch loss: 2.160, learning rate: 0.007738
Minibatch error: 4.7%
Validation error: 0.9%
Step 4600 (epoch 5.35), 174.5 ms
Minibatch loss: 2.095, learning rate: 0.007738
Minibatch error: 0.0%
Validation error: 0.9%
Step 4700 (epoch 5.47), 167.3 ms
Minibatch loss: 2.086, learning rate: 0.007738
Minibatch error: 1.6%
Validation error: 0.9%
Step 4800 (epoch 5.59), 171.5 ms
Minibatch loss: 2.056, learning rate: 0.007738
Minibatch error: 0.0%
Validation error: 1.0%
Step 4900 (epoch 5.70), 171.8 ms
Minibatch loss: 2.050, learning rate: 0.007738
Minibatch error: 0.0%
Validation error: 1.0%
Step 5000 (epoch 5.82), 166.5 ms
Minibatch loss: 2.142, learning rate: 0.007738
Minibatch error: 3.1%
Validation error: 1.0%
Step 5100 (epoch 5.93), 180.8 ms
Minibatch loss: 2.007, learning rate: 0.007738
Minibatch error: 0.0%
Validation error: 1.0%
Step 5200 (epoch 6.05), 172.6 ms
Minibatch loss: 2.054, learning rate: 0.007351
Minibatch error: 1.6%
Validation error: 0.9%
Step 5300 (epoch 6.17), 168.5 ms
Minibatch loss: 1.991, learning rate: 0.007351
Minibatch error: 1.6%
Validation error: 1.0%
Step 5400 (epoch 6.28), 163.2 ms
Minibatch loss: 1.955, learning rate: 0.007351
Minibatch error: 0.0%
Validation error: 0.8%
Step 5500 (epoch 6.40), 172.3 ms
Minibatch loss: 1.954, learning rate: 0.007351
Minibatch error: 0.0%
Validation error: 0.9%
Step 5600 (epoch 6.52), 173.5 ms
Minibatch loss: 1.926, learning rate: 0.007351
Minibatch error: 0.0%
Validation error: 0.8%
Step 5700 (epoch 6.63), 175.1 ms
Minibatch loss: 1.913, learning rate: 0.007351
Minibatch error: 0.0%
Validation error: 0.9%
Step 5800 (epoch 6.75), 182.6 ms
Minibatch loss: 1.900, learning rate: 0.007351
Minibatch error: 0.0%
Validation error: 0.9%
Step 5900 (epoch 6.87), 171.0 ms
Minibatch loss: 1.886, learning rate: 0.007351
Minibatch error: 0.0%
Validation error: 0.8%
Step 6000 (epoch 6.98), 163.7 ms
Minibatch loss: 1.882, learning rate: 0.007351
Minibatch error: 0.0%
Validation error: 1.0%
Step 6100 (epoch 7.10), 172.6 ms
Minibatch loss: 1.862, learning rate: 0.006983
Minibatch error: 0.0%
Validation error: 0.8%
Step 6200 (epoch 7.21), 170.8 ms
Minibatch loss: 1.844, learning rate: 0.006983
Minibatch error: 0.0%
Validation error: 0.9%
Step 6300 (epoch 7.33), 164.1 ms
Minibatch loss: 1.837, learning rate: 0.006983
Minibatch error: 0.0%
Validation error: 0.9%
Step 6400 (epoch 7.45), 175.3 ms
Minibatch loss: 1.881, learning rate: 0.006983
Minibatch error: 1.6%
Validation error: 0.8%
Step 6500 (epoch 7.56), 166.3 ms
Minibatch loss: 1.809, learning rate: 0.006983
Minibatch error: 0.0%
Validation error: 0.8%
Step 6600 (epoch 7.68), 166.6 ms
Minibatch loss: 1.821, learning rate: 0.006983
Minibatch error: 1.6%
Validation error: 0.8%
Step 6700 (epoch 7.80), 161.2 ms
Minibatch loss: 1.783, learning rate: 0.006983
Minibatch error: 0.0%
Validation error: 0.8%
Step 6800 (epoch 7.91), 162.8 ms
Minibatch loss: 1.771, learning rate: 0.006983
Minibatch error: 0.0%
Validation error: 0.8%
Step 6900 (epoch 8.03), 172.2 ms
Minibatch loss: 1.760, learning rate: 0.006634
Minibatch error: 0.0%
Validation error: 0.9%
Step 7000 (epoch 8.15), 168.9 ms
Minibatch loss: 1.777, learning rate: 0.006634
Minibatch error: 1.6%
Validation error: 0.8%
Step 7100 (epoch 8.26), 171.7 ms
Minibatch loss: 1.744, learning rate: 0.006634
Minibatch error: 0.0%
Validation error: 0.9%
Step 7200 (epoch 8.38), 168.3 ms
Minibatch loss: 1.757, learning rate: 0.006634
Minibatch error: 1.6%
Validation error: 0.8%
Step 7300 (epoch 8.49), 175.4 ms
Minibatch loss: 1.734, learning rate: 0.006634
Minibatch error: 1.6%
Validation error: 0.8%
Step 7400 (epoch 8.61), 162.9 ms
Minibatch loss: 1.703, learning rate: 0.006634
Minibatch error: 0.0%
Validation error: 0.9%
Step 7500 (epoch 8.73), 171.5 ms
Minibatch loss: 1.705, learning rate: 0.006634
Minibatch error: 0.0%
Validation error: 0.8%
Step 7600 (epoch 8.84), 162.1 ms
Minibatch loss: 1.807, learning rate: 0.006634
Minibatch error: 1.6%
Validation error: 0.8%
Step 7700 (epoch 8.96), 181.6 ms
Minibatch loss: 1.667, learning rate: 0.006634
Minibatch error: 0.0%
Validation error: 1.0%
Step 7800 (epoch 9.08), 166.3 ms
Minibatch loss: 1.662, learning rate: 0.006302
Minibatch error: 0.0%
Validation error: 0.9%
Step 7900 (epoch 9.19), 169.1 ms
Minibatch loss: 1.646, learning rate: 0.006302
Minibatch error: 0.0%
Validation error: 0.9%
Step 8000 (epoch 9.31), 167.1 ms
Minibatch loss: 1.654, learning rate: 0.006302
Minibatch error: 0.0%
Validation error: 0.9%
Step 8100 (epoch 9.43), 163.9 ms
Minibatch loss: 1.626, learning rate: 0.006302
Minibatch error: 0.0%
Validation error: 0.9%
Step 8200 (epoch 9.54), 166.5 ms
Minibatch loss: 1.634, learning rate: 0.006302
Minibatch error: 0.0%
Validation error: 0.9%
Step 8300 (epoch 9.66), 169.6 ms
Minibatch loss: 1.608, learning rate: 0.006302
Minibatch error: 0.0%
Validation error: 0.9%
Step 8400 (epoch 9.77), 173.0 ms
Minibatch loss: 1.596, learning rate: 0.006302
Minibatch error: 0.0%
Validation error: 0.8%
Step 8500 (epoch 9.89), 163.6 ms
Minibatch loss: 1.615, learning rate: 0.006302
Minibatch error: 1.6%
Validation error: 0.9%
Test error: 0.8%

END