最近keras使用太多,准备重拾一下keras,所以趁机重温一下tensorflow官方文档。
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets('MNIST_data', one_hot=True)
Tensorflow依赖于一个高效的C++后端来进行计算。与后端的这个连接叫做session。一般而言,使用TensorFlow程序的流程是先创建一个图,然后在session中启动它。
这里,我们使用更加方便的InteractiveSession类。通过它,你可以更加灵活地构建你的代码。它能让你在运行图的时候,插入一些计算图,这些计算图是由某些操作(operations)构成的。这对于工作在交互式环境中的人们来说非常便利,比如使用IPython。如果你没有使用InteractiveSession,那么你需要在启动session之前构建整个计算图,然后启动该计算图。
sess=tf.InteractiveSession()
1.构建简单的Softmax 回归模型
#占位符--为输入图像和目标输出类别创建节点
x=tf.placeholder('float',[None,784])
y_=tf.placeholder('float',[None,10])
#变量--为模型定义权重W和偏置b
W = tf.Variable(tf.zeros([784,10]))
b = tf.Variable(tf.zeros([10]))
sess.run(tf.initialize_all_variables())#初始化
#类别预测与损失函数
y=tf.nn.softmax(tf.matmul(x,W)+b)
cross_entropy=-tf.reduce_sum(y_*tf.log(y))
##训练模型
train_step = tf.train.GradientDescentOptimizer(0.01).minimize(cross_entropy)
for i in range(1000):
batch = mnist.train.next_batch(50)
train_step.run(feed_dict={x: batch[0], y_: batch[1]})
#评估模型
correct_prediction = tf.equal(tf.argmax(y,1), tf.argmax(y_,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))
print(accuracy.eval(feed_dict={x: mnist.test.images, y_: mnist.test.labels}))
结果如下:
WARNING:tensorflow:From /home/larry/anaconda3/lib/python3.5/site-packages/tensorflow/python/util/tf_should_use.py:170: 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.
0.91700006
2.构建一个多层卷积网络
####先期函数定义
#权重初始化
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)
#卷积和池化
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')
####模型构建
#c1
W_conv1 = weight_variable([5, 5, 1, 32])
b_conv1 = bias_variable([32])
x_image = tf.reshape(x, [-1,28,28,1])
h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1)
h_pool1 = max_pool_2x2(h_conv1)
#c2
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)
#f1
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)
#Dropout
keep_prob = tf.placeholder("float")
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)
#out
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)
####训练和评估模型
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.run(tf.initialize_all_variables())
for i in range(20000):
batch = mnist.train.next_batch(50)
if i%100 == 0:
train_accuracy = accuracy.eval(feed_dict={
x:batch[0], y_: batch[1], keep_prob: 1.0})
print ("step %d, training accuracy %g"%(i, train_accuracy))
train_step.run(feed_dict={x: batch[0], y_: batch[1], keep_prob: 0.5})
print ("test accuracy %g"%accuracy.eval(feed_dict={
x: mnist.test.images, y_: mnist.test.labels, keep_prob: 1.0}))
结果如下:
step 19400, training accuracy 1
step 19500, training accuracy 1
step 19600, training accuracy 1
step 19700, training accuracy 1
step 19800, training accuracy 0.98
step 19900, training accuracy 1
test accuracy 0.9922
3.总结
可以看到:
1.tensorflow还是比较偏底层的,使用原始框架时,卷基层的参数都需要自己手动初始化。不方便但是让新手对整个计算图的矩阵运算有了一个清晰的了解吧
2.使用tensoflow进行深度学习无非包括以下几个部分:
- 占位符设置
- 模型构建(你可以自己手动定义卷积层,也可以使用tflearn/slim等高级库)
- 损失函数定义
- 优化器定义
- 模型训练(run之前记得对所有变量初始化,当然初始化也可以在模型构建那一步完成)
- 模型评估与保存