TensorFlow 安装

安装TensorFlow

1.安装docker ，具体参考我的上一篇博客

2.执行：

docker run -it b.gcr.io/tensorflow/tensorflow:latest-devel

如此就把TensorFlow的环境搭建好了...深深感觉docker是个好东西..

运行TensorFlow的Hello World ---MNIST手写体识别

虽然称他为hello world，但是要理解他还是有一定的难度的。我是参考了如下两篇博客：

http://www.jeyzhang.com/tensorflow-learning-notes.html

http://www.tensorfly.cn/tfdoc/tutorials/mnist_beginners.html

进入Python环境，然后具体代码如下：

__author__ = 'chapter'

import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data

mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)
print("Download Done!")

x = tf.placeholder(tf.float32, [None, 784])

# paras
W = tf.Variable(tf.zeros([784, 10]))
b = tf.Variable(tf.zeros([10]))

y = tf.nn.softmax(tf.matmul(x, W) + b)
y_ = tf.placeholder(tf.float32, [None, 10])

# loss func
cross_entropy = -tf.reduce_sum(y_ * tf.log(y))

train_step = tf.train.GradientDescentOptimizer(0.01).minimize(cross_entropy)

# init
init = tf.initialize_all_variables()

sess = tf.Session()
sess.run(init)

# train
for i in range(1000):
    batch_xs, batch_ys = mnist.train.next_batch(100)
    sess.run(train_step, feed_dict={x: batch_xs, y_: batch_ys})

correct_prediction = tf.equal(tf.arg_max(y, 1), tf.arg_max(y_, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))

print("Accuarcy on Test-dataset: ", sess.run(accuracy, feed_dict={x: mnist.test.images, y_: mnist.test.labels}))

这个有个问题就是加载训练集和测试集的文件时非常慢，

mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)

我采用的方法是直接到对应的网站上把如下四个文件下载下来：

t10k-images-idx3-ubyte.gz

 train-images-idx3-ubyte.gz

t10k-labels-idx1-ubyte.gz

 train-labels-idx1-ubyte.gz

然后放到MNIST_data这个目录下

运行结果如下：

('Accuarcy on Test-dataset: ', 0.91289997)

准确率为0.91