1 MNIST介绍
MNIST是一个入门级的计算机视觉数据集,它包含各种手写数字图片。关于其详细讲解,详见:MNIST机器学习入门,英文版MNIST For ML Beginners 。如果对于代码中一些关于tensorflow的API不了解,可查找官网手册:All symbols in TensorFlow。
2.代码实现
代码中需要使用MNIST数据集,如果发现在代码里下载老是出现错误的话。建议直接下载,放到当前运行目录下即可(包括整个文件夹)。
my_mnist_softmax.py
# -*- coding: utf-8 -*-
# @Time : 17-11-27
# @Author : yeqiang19910412
# @FileName: my_mnist_softmax.py
# @Software: PyCharm Community Edition with python3.5 tensorflow1.4
# @Blog :http://blog.csdn.net/yeqiang19910412/article/details/78646069
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
# Import data
mnist = input_data.read_data_sets("MNIST_data/",one_hot=True)
# Create the model
x = tf.placeholder(tf.float32, [None, 784])
W = tf.Variable(tf.zeros([784, 10]))
b = tf.Variable(tf.zeros([10]))
y = tf.matmul(x, W) + b
# Define loss and optimizer
y_ = tf.placeholder(tf.float32, [None, 10])
cross_entropy = tf.reduce_mean(
tf.nn.softmax_cross_entropy_with_logits(labels=y_, logits=y))
train_step = tf.train.GradientDescentOptimizer(0.5).minimize(cross_entropy)
sess = tf.InteractiveSession()
tf.global_variables_initializer().run()
# Train
for _ in range(1000):
batch_xs, batch_ys = mnist.train.next_batch(100)
sess.run(train_step, feed_dict={x: batch_xs, y_: batch_ys})
# Test trained model
correct_prediction = tf.equal(tf.argmax(y, 1), tf.argmax(y_, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
print(sess.run(accuracy, feed_dict={x: mnist.test.images,
y_: mnist.test.labels}))
my_mnist_multilayer_convolutional_network.py
# -*- coding: utf-8 -*-
# @Time : 17-11-27
# @Author : yeqiang19910412
# @FileName: my_mnist_multilayer_convolutional_network.py
# @Software: PyCharm Community Edition with python3.5 tensorflow1.4
# @Blog :http://blog.csdn.net/yeqiang19910412/article/details/78646069
import tensorflow as tf
# 加载数据
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("MNIST_data/",one_hot=True)
x = tf.placeholder(tf.float32, [None, 784])
y_ = tf.placeholder(tf.float32, [None, 10])
# 初始化卷积核的权重参数
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')
x_image = tf.reshape(x, [-1,28,28,1])
# 第一个卷积层
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)
# 第二个卷积层
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)
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(tf.float32)
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)
W_fc2 = weight_variable([1024, 10])
b_fc2 = bias_variable([10])
y_conv = tf.matmul(h_fc1_drop, W_fc2) + b_fc2
cross_entropy = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=y_, logits=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, tf.float32))
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
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}))
my_mnist_multilayer_convolutional_network.py 完整代码
注意:这其中还涉及到卷积神经网络的一些基本概念,可以参看 CS231n课程卷积神经网络笔记,英文版CS231n Convolutional Neural Networks for Visual Recognition
接下来要结合tensorboard
参考文献:
1.[tensorflow在mnist集上的使用示例(一)](http://blog.csdn.net/nnnnnnnnnnnny/article/details/56845456
主要贡献在于两个程序的源代码
2.Tensorflow学习笔记(4)-mnist(Multilayer_Convolutional_Network)
主要贡献在于my_mnist_multilayer_convolutional_network.py 的详细解读