Tensorflow mnist手写数字识别

 

1、mnist数据集转图片

import os
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'
import tensorflow as tf 
import numpy as np 
from tensorflow.contrib.learn.python.learn.datasets.mnist import read_data_sets
from PIL import Image

import matplotlib.pyplot as plt

def ImageToMatrix(filename):
    # 读取图片
    im = Image.open(filename)
    # 显示图片
#     im.show()  
    width,height = im.size
    im = im.convert("L") 
    data = im.getdata()
    data = np.matrix(data,dtype='float')/255.0
    #new_data = np.reshape(data,(width,height))
    new_data = np.reshape(data,(height,width))
    return new_data
#     new_im = Image.fromarray(new_data)
#     # 显示图片
#     new_im.show()
def MatrixToImage(data):
    data = data*255
    new_im = Image.fromarray(data.astype(np.uint8))
    return new_im

mnist = read_data_sets('MNIST_data', one_hot=True)
train_data = mnist.train.images
pngroot = 'train_png'
if not os.path.exists(pngroot):
    os.mkdir(pngroot)
for i in range(train_data.shape[0]):

	train_data_0 = train_data[i].reshape(28,-1)

	#调用Image库，数组归一化
	new_im = MatrixToImage(train_data_0)
	plt.imshow(train_data_0, cmap=plt.cm.gray, interpolation='nearest')
	#new_im.show()
	new_im.save('train_png/lena_'+str(i)+'.png')

运行结果如下图：

2、实现卷积神经网络

import numpy as np
import tensorflow as tf 
from tensorflow.contrib.learn.python.learn.datasets.mnist import read_data_sets
from PIL import Image

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)

mnist = read_data_sets('MNIST_data', one_hot=True)

x = tf.placeholder('float',shape=[None,784])
y_ = tf.placeholder('float',shape=[None,10])

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')

def ImageToMatrix(filename):
    # 读取图片
    im = Image.open(filename)
    # 显示图片
#     im.show()  
    width,height = im.size
    im = im.convert("L") 
    data = im.getdata()
    data = np.matrix(data,dtype='float')/255.0
    #new_data = np.reshape(data,(width,height))
    new_data = np.reshape(data,(height,width))
    return new_data

#第一层卷积
W = tf.Variable(tf.zeros([784,10]))
b = tf.Variable(tf.zeros([10]))
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)

#第二层卷积
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)

#密集连接层
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)

#输出层
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)

with tf.Session() as sess:
	
	#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(1000):
		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})
    #手写数字图片路径
	filename_test = 'train_png/lena_20.png'
    #图片转矩阵
	data_test = ImageToMatrix(filename_test)
	#print("test accuracy %g"%accuracy.eval(feed_dict={x: data_test.reshape(1,-1), y_: [[0,0,0,1,0,0,0,0,0,0]], keep_prob: 1.0}))
	pre_y = y_conv.eval(feed_dict={x: data_test.reshape(1,-1),keep_prob: 1.0})
	print('result:',np.argmax(pre_y))

参考资源：

http://yann.lecun.com/exdb/mnist/  MNIST数据源

http://www.tensorfly.cn/tfdoc/tutorials/mnist_pros.html  MNIST进阶

https://blog.csdn.net/lql0716/article/details/52416086  Python图片转换成矩阵，矩阵数据转换成图片