tensorflow mnist神经网络示例

本文讲述使用tensorflow解决mnist分类问题：

1. 使用一个隐藏层神经网络784 * 10分类mnist

2. 使用两个隐藏层神经网络784 * 300 * 10分类mnist

其中单层784 * 4隐藏层的网络构架如下图:

具体代码如下:

# coding:utf-8

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

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

image_size = 28
labels_size = 10
learning_rate = 0.05
steps_number = 1000
batch_size = 100

# Define placeholders
training_data = tf.placeholder(tf.float32, [None, image_size*image_size])
labels = tf.placeholder(tf.float32, [None, labels_size])

# Variables to be tuned
W = tf.Variable(tf.truncated_normal([image_size*image_size, labels_size], stddev=0.1))
b = tf.Variable(tf.constant(0.1, shape=[labels_size]))

# Build the network (only output layer)
output = tf.matmul(training_data, W) + b

# Define the loss function
loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=labels, logits=output))

# 梯度下降法，学习速率为0.5
optimizer = tf.train.GradientDescentOptimizer(0.5)
# 训练目标：最小化损失函数
train_step = optimizer.minimize(loss)

# Accuracy calculation
correct_prediction = tf.equal(tf.argmax(output, 1), tf.argmax(labels, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))

# Run the training
sess = tf.InteractiveSession()
sess.run(tf.global_variables_initializer())

for i in range(steps_number):
    # Get the next batch
    input_batch, labels_batch = mnist.train.next_batch(batch_size)
    feed_dict = {training_data: input_batch, labels: labels_batch}

    # Run the training step
    train_step.run(feed_dict=feed_dict)

    # Print the accuracy progress on the batch every 100 steps
    if i % 100 == 0:
        train_accuracy = accuracy.eval(feed_dict=feed_dict)
        print("Step %d, training batch accuracy %g %%" % (i, train_accuracy * 100))

# Evaluate on the test set
test_accuracy = accuracy.eval(feed_dict={training_data: mnist.test.images, labels: mnist.test.labels})
print("Test accuracy: %g %%" % (test_accuracy*100))

单层的识别效果一般，测试集上面的结果勉强达到90%,运行结果如下:

下面看下 784 * 300 * 10 结构的网络的结构，代码如下:

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

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

# Python optimisation variables
learning_rate = 0.5
epochs = 10
batch_size = 100

# declare the training data placeholders
# input x - for 28 x 28 pixels = 784
x = tf.placeholder(tf.float32, [None, 784])
# now declare the output data placeholder - 10 digits
y = tf.placeholder(tf.float32, [None, 10])

# now declare the weights connecting the input to the hidden layer
W1 = tf.Variable(tf.random_normal([784, 300], stddev=0.03), name='W1')
b1 = tf.Variable(tf.random_normal([300]), name='b1')
# and the weights connecting the hidden layer to the output layer
W2 = tf.Variable(tf.random_normal([300, 10], stddev=0.03), name='W2')
b2 = tf.Variable(tf.random_normal([10]), name='b2')

# calculate the output of the hidden layer
hidden_out = tf.add(tf.matmul(x, W1), b1)
hidden_out = tf.nn.relu(hidden_out)

# now calculate the hidden layer output - in this case, let's use a softmax activated
# output layer
y_ = tf.nn.softmax(tf.add(tf.matmul(hidden_out, W2), b2))

y_clipped = tf.clip_by_value(y_, 1e-10, 0.9999999)
cross_entropy = -tf.reduce_mean(tf.reduce_sum(y * tf.log(y_clipped)
                                              + (1 - y) * tf.log(1 - y_clipped), axis=1))

# add an optimiser
optimiser = tf.train.GradientDescentOptimizer(learning_rate=learning_rate).minimize(cross_entropy)

# finally setup the initialisation operator
init_op = tf.global_variables_initializer()

# define an accuracy assessment operation
correct_prediction = tf.equal(tf.argmax(y, 1), tf.argmax(y_, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))

# start the session
with tf.Session() as sess:
    # initialise the variables
    sess.run(init_op)
    total_batch = int(len(mnist.train.labels) / batch_size)
    for epoch in range(epochs):
        avg_cost = 0
        for i in range(total_batch):
            batch_x, batch_y = mnist.train.next_batch(batch_size=batch_size)
            _, c = sess.run([optimiser, cross_entropy],
                            feed_dict={x: batch_x, y: batch_y})
            avg_cost += c / total_batch
        print("Epoch:", (epoch + 1), "cost =", "{:.3f}".format(avg_cost))

    print(sess.run(accuracy, feed_dict={x: mnist.test.images, y: mnist.test.labels}))

运行输出结果如下,识别结果，测试集97.7%，相对1提升了很多:

参考:

https://blog.csdn.net/u014595019/article/details/52677412

https://www.katacoda.com/basiafusinska/courses/tensorflow-getting-started/tensorflow-mnist-beginner