Tensorflow实现Softmax Regression识别手写数字

实现代码：

#coding:utf-8

# load MNIST datasets
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("MNIST_data/", one_hot = True)

# View the information of MNIST_dataset
print(mnist.train.images.shape, mnist.train.labels.shape)
print(mnist.test.images.shape, mnist.test.labels.shape)
print(mnist.validation.images.shape, mnist.validation.labels.shape)

import tensorflow as tf 
sess = tf.InteractiveSession()
x = tf.placeholder(tf.float32, [None, 784])

w = tf.Variable(tf.zeros([784,10])) #Variable用来存储参数
b = tf.Variable(tf.zeros([10]))

# softmax regression
y = tf.nn.softmax(tf.matmul(x,w) + b)

# define loss function: use cross-entropy as loss function
y_ = tf.placeholder(tf.float32, [None,10])
cross_entropy = tf.reduce_mean(-tf.reduce_sum(y_ * tf.log(y),reduction_indices=[1]))

# define optimizer
train_step = tf.train.GradientDescentOptimizer(0.5).minimize(cross_entropy)

tf.global_variables_initializer().run()

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

# start validation
correct_prediction =  tf.equal(tf.argmax(y,1), tf.argmax(y_,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))

print(accuracy.eval({x:mnist.test.images, y_:mnist.test.labels}))

备注：

one-hot编码:https://yq.aliyun.com/articles/126741?utm_content=m_25962