TensorFlow入门

2019-02-20  本文已影响0人  蜉蝣之翼

基础知识

  1. 使用图 (graph) 来表示计算任务.
  2. 在被称之为 会话 (Session) 的上下文 (context) 中执行图.
  3. 使用 tensor 表示数据.
  4. 通过 变量 (Variable) 维护状态.
  5. 使用 feed 和 fetch 可以为任意的操作(arbitrary operation) 赋值或者从其中获取数据.

A Graph contains a set of Operation objects, which represent units of computation; and Tensor objects, which represent the units of data that flow between operations.

  1. 创建图:
    构建图的第一步, 是创建源 op (source op). 源 op 不需要任何输入, 例如 常量 (Constant). 源 op 的输出被传递给其它 op 做运算.
    Python 库中, op 构造器的返回值代表被构造出的 op 的输出, 这些返回值可以传递给其它 op 构造器作为输入.
  2. 在一个会话中启动图

会话

  1. session 类 (http://wiki.jikexueyuan.com/project/tensorflow-zh/api_docs/python/client.html
  2. InteractiveSession 类

获取中间变量

sess.run(variable)

构建多层卷积网络模型

from tensorflow.examples.tutorials.mnist import input_data
import tensorflow as tf
mnist=input_data.read_data_sets("/home/yangshuhui/code/dataset/MNIST_data",one_hot=True)

# initial function
def weight_variable(shape):
    initial=tf.truncated_normal(shape,stddev=0.1)
    return tf.Variable(initial)
def bias_variable(shape):
    initial=tf.constant(0.1,shape=shape)
    return tf.Variable(initial)

def conv2d(x,W):
    return tf.nn.conv2d(x,W,strides=[1,1,1,1],padding='SAME')
def max_pool_2x2(x):
    return tf.nn.max_pool(x,ksize=[1,2,2,1],strides=[1,2,2,1],padding='SAME')

#1
x=tf.placeholder("float",[None,784])
x_image=tf.reshape(x,[-1,28,28,1])
w_conv1=weight_variable([5,5,1,32])
b_conv1=bias_variable([32])
h_conv1=tf.nn.relu(conv2d(x_image,w_conv1)+b_conv1)
h_pool1=max_pool_2x2(h_conv1)

#2

W_conv2=weight_variable([5,5,32,64])
b_conv2=bias_variable([64])
h_conv2=tf.nn.relu(conv2d(h_pool1,W_conv2)+b_conv2)
h_pool2=max_pool_2x2(h_conv2)

#3
W_fc1=weight_variable([7*7*64,1024])
b_fc1=bias_variable([1024])
h_pool2_flat=tf.reshape(h_pool2,[-1,7*7*64])
h_fc1=tf.nn.relu(tf.matmul(h_pool2_flat,W_fc1)+b_fc1)
keep_prob=tf.placeholder("float")
h_fc1_drop=tf.nn.dropout(h_fc1,keep_prob)

#output
W_fc2=weight_variable([1024,10])
b_fc2=bias_variable([10])
y_conv=tf.nn.softmax(tf.matmul(h_fc1_drop,W_fc2)+b_fc2)

# train and evaluate
y_=tf.placeholder("float",[None,10])
cross_entropy=-tf.reduce_sum(y_*tf.log(y_conv))
train_step=tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)
correct_prediction=tf.equal(tf.argmax(y_conv,1),tf.argmax(y_,1))
accuracy=tf.reduce_mean(tf.cast(correct_prediction,"float"))

sess=tf.Session()
sess.run(tf.initialize_all_variables())
for i in range(20000):
    batch=mnist.train.next_batch(50)
    if i%100==0:
        train_accuracy=accuracy.eval(session=sess,feed_dict={x:batch[0],y_:batch[1],keep_prob:1.0})
        print "step %d, training accuracy %g"%(i,train_accuracy)
    train_step.run(session=sess,feed_dict={x:batch[0],y_:batch[1],keep_prob:0.5})       
print "test accuracy %g"%accuracy.eval(session=sess,feed_dict={x:mnist.test.images,y_:mnist.test.labels,keep_prob:1.0})

上一篇下一篇

猜你喜欢

热点阅读