十二.TensorFlow之分类学习

TensorFlow之分类学习

这次课程主要通过官方MNIST_data这个数据级做为例子.来训练并预测手写数字,最终得到识别的概率.

"""
Please note, this code is only for python 3+. If you are using python 2+, please modify the code accordingly.
"""
import tensorflow as tf

from tensorflow.examples.tutorials.mnist import input_data
# number 1 to 10 data
#if no have the data.this download the data.
mnist = input_data.read_data_sets('MNIST_data', one_hot=True)
 
def add_layer(inputs, in_size, out_size, activation_function=None,):
    # add one more layer and return the output of this layer
    Weights = tf.Variable(tf.random_normal([in_size, out_size]))
    biases = tf.Variable(tf.zeros([1, out_size]) + 0.1,)
    Wx_plus_b = tf.matmul(inputs, Weights) + biases
    if activation_function is None:
        outputs = Wx_plus_b
    else:
        outputs = activation_function(Wx_plus_b,)
    return outputs
 
def compute_accuracy(v_xs, v_ys):
    global prediction
    y_pre = sess.run(prediction, feed_dict={xs: v_xs})
    correct_prediction = tf.equal(tf.argmax(y_pre,1), tf.argmax(v_ys,1))
    accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
    result = sess.run(accuracy, feed_dict={xs: v_xs, ys: v_ys})
    return result
 
# define placeholder for inputs to network
xs = tf.placeholder(tf.float32, [None, 784]) # 28x28,784pixel
ys = tf.placeholder(tf.float32, [None, 10])
 
# add output layer
#xs,input_szie,output_size,activation_function
prediction = add_layer(xs, 784, 10,  activation_function=tf.nn.softmax)
 
# the error between prediction and real data
#this is the loss
# loss
cross_entropy = tf.reduce_mean(-tf.reduce_sum(ys * tf.log(prediction),reduction_indices=[1]))

train_step = tf.train.GradientDescentOptimizer(0.5).minimize(cross_entropy)
 
sess = tf.Session()
# important step
sess.run(tf.global_variables_initializer())
 
for i in range(1000):
    #100 by 100, study
    batch_xs, batch_ys = mnist.train.next_batch(100)
    #train data
    sess.run(train_step, feed_dict={xs: batch_xs, ys: batch_ys})
    if i % 50 == 0:
        #data test
        print(compute_accuracy(mnist.test.images, mnist.test.labels))

输出结果是:

RESTART: /Users/dongsai/Documents/MachineLearning/tensorflow/TensorFlow_Study/csdn/tf_lesson16.py 
Extracting MNIST_data/train-images-idx3-ubyte.gz
Extracting MNIST_data/train-labels-idx1-ubyte.gz
Extracting MNIST_data/t10k-images-idx3-ubyte.gz
Extracting MNIST_data/t10k-labels-idx1-ubyte.gz
0.2002
0.6402
0.7428
0.7783
0.8043
0.8208
0.8303
0.8395
0.8464
0.8516
0.855
0.8594
0.8618
0.8655
0.8696
0.8678
0.8701
0.868
0.8766
0.8769

>>> 

能看了最终的识别率可以到达87%.代码中有详细的注释.

--------------------------

关注微信公众号:玉麒麟百科

回复'tensorflow代码',即可获取系列教程源码.