http://blog.csdn.net/xiazdong/article/details/7950084
线性回归
卷积神经网络
http://www.hackcv.com/index.php/archives/104/
https://github.com/aymericdamien/TensorFlow-Examples
http://bcomposes.com/2015/11/26/simple-end-to-end-tensorflow-examples/
# -*- coding: utf-8 -*-
# encoding: utf-8
"""
@author: monitor1379
@contact: yy4f5da2@hotmail.com
@site: www.monitor1379.com
@version: 1.0
@license: Apache Licence
@file: mnist_decoder.py
@time: 2016/8/16 20:03
对MNIST手写数字数据文件转换为bmp图片文件格式。
数据集下载地址为http://yann.lecun.com/exdb/mnist。
相关格式转换见官网以及代码注释。
========================
关于IDX文件格式的解析规则：
========================
THE IDX FILE FORMAT
the IDX file format is a simple format for vectors and multidimensional matrices of various numerical types.
The basic format is
magic number
size in dimension 0
size in dimension 1
size in dimension 2
.....
size in dimension N
data
The magic number is an integer (MSB first). The first 2 bytes are always 0.
The third byte codes the type of the data:
0x08: unsigned byte
0x09: signed byte
0x0B: short (2 bytes)
0x0C: int (4 bytes)
0x0D: float (4 bytes)
0x0E: double (8 bytes)
The 4-th byte codes the number of dimensions of the vector/matrix: 1 for vectors, 2 for matrices....
The sizes in each dimension are 4-byte integers (MSB first, high endian, like in most non-Intel processors).
The data is stored like in a C array, i.e. the index in the last dimension changes the fastest.
"""
import numpy as np
import struct
import matplotlib.pyplot as plt
import tensorflow as tf
# 训练集文件
train_images_idx3_ubyte_file = './train-images-idx3-ubyte/train-images.idx3-ubyte'
# 训练集标签文件
train_labels_idx1_ubyte_file = './train-labels-idx1-ubyte/train-labels.idx1-ubyte'
# 测试集文件
test_images_idx3_ubyte_file = './t10k-images-idx3-ubyte/t10k-images.idx3-ubyte'
# 测试集标签文件
test_labels_idx1_ubyte_file = './t10k-labels-idx1-ubyte/t10k-labels.idx1-ubyte'
def decode_idx3_ubyte(idx3_ubyte_file):
"""
解析idx3文件的通用函数
:param idx3_ubyte_file: idx3文件路径
:return: 数据集
"""
# 读取二进制数据
bin_data = open(idx3_ubyte_file, 'rb').read()
# 解析文件头信息，依次为魔数、图片数量、每张图片高、每张图片宽
offset = 0
fmt_header = '>iiii'
magic_number, num_images, num_rows, num_cols = struct.unpack_from(fmt_header, bin_data, offset)
print('魔数:%d, 图片数量: %d张, 图片大小: %d*%d' % (magic_number, num_images, num_rows, num_cols))
# 解析数据集
image_size = num_rows * num_cols
offset += struct.calcsize(fmt_header)
fmt_image = '>' + str(image_size) + 'B'
# images = np.empty((num_images, num_rows, num_cols))
# images = np.empty((num_images, num_rows, num_cols),dtype=np.uint8)
images = np.empty((num_images, image_size),dtype=np.uint8)
for i in range(num_images):
if (i + 1) % 10000 == 0:
print('已解析 %d' % (i + 1) + '张')
# images[i] = np.array(struct.unpack_from(fmt_image, bin_data, offset)).reshape((num_rows, num_cols))
images[i] = np.array(struct.unpack_from(fmt_image, bin_data, offset))
offset += struct.calcsize(fmt_image)
return images
def decode_idx1_ubyte(idx1_ubyte_file):
"""
解析idx1文件的通用函数
:param idx1_ubyte_file: idx1文件路径
:return: 数据集
"""
# 读取二进制数据
bin_data = open(idx1_ubyte_file, 'rb').read()
# 解析文件头信息，依次为魔数和标签数
offset = 0
fmt_header = '>ii'
magic_number, num_images = struct.unpack_from(fmt_header, bin_data, offset)
print('魔数:%d, 图片数量: %d张' % (magic_number, num_images))
# 解析数据集
offset += struct.calcsize(fmt_header)
fmt_image = '>B'
# labels = np.empty(num_images)
labels = np.empty(num_images,dtype=np.uint8)
for i in range(num_images):
if (i + 1) % 10000 == 0:
print('已解析 %d' % (i + 1) + '张')
labels[i] = struct.unpack_from(fmt_image, bin_data, offset)[0]
offset += struct.calcsize(fmt_image)
return labels
def load_train_images(idx_ubyte_file=train_images_idx3_ubyte_file):
"""
TRAINING SET IMAGE FILE (train-images-idx3-ubyte):
[offset] [type] [value] [description]
0000 32 bit integer 0x00000803(2051) magic number
0004 32 bit integer 60000 number of images
0008 32 bit integer 28 number of rows
0012 32 bit integer 28 number of columns
0016 unsigned byte ?? pixel
0017 unsigned byte ?? pixel
........
xxxx unsigned byte ?? pixel
Pixels are organized row-wise. Pixel values are 0 to 255. 0 means background (white), 255 means foreground (black).
:param idx_ubyte_file: idx文件路径
:return: n*row*col维np.array对象，n为图片数量
"""
return decode_idx3_ubyte(idx_ubyte_file)
def load_train_labels(idx_ubyte_file=train_labels_idx1_ubyte_file):
"""
TRAINING SET LABEL FILE (train-labels-idx1-ubyte):
[offset] [type] [value] [description]
0000 32 bit integer 0x00000801(2049) magic number (MSB first)
0004 32 bit integer 60000 number of items
0008 unsigned byte ?? label
0009 unsigned byte ?? label
........
xxxx unsigned byte ?? label
The labels values are 0 to 9.
:param idx_ubyte_file: idx文件路径
:return: n*1维np.array对象，n为图片数量
"""
return decode_idx1_ubyte(idx_ubyte_file)
def load_test_images(idx_ubyte_file=test_images_idx3_ubyte_file):
"""
TEST SET IMAGE FILE (t10k-images-idx3-ubyte):
[offset] [type] [value] [description]
0000 32 bit integer 0x00000803(2051) magic number
0004 32 bit integer 10000 number of images
0008 32 bit integer 28 number of rows
0012 32 bit integer 28 number of columns
0016 unsigned byte ?? pixel
0017 unsigned byte ?? pixel
........
xxxx unsigned byte ?? pixel
Pixels are organized row-wise. Pixel values are 0 to 255. 0 means background (white), 255 means foreground (black).
:param idx_ubyte_file: idx文件路径
:return: n*row*col维np.array对象，n为图片数量
"""
return decode_idx3_ubyte(idx_ubyte_file)
def load_test_labels(idx_ubyte_file=test_labels_idx1_ubyte_file):
"""
TEST SET LABEL FILE (t10k-labels-idx1-ubyte):
[offset] [type] [value] [description]
0000 32 bit integer 0x00000801(2049) magic number (MSB first)
0004 32 bit integer 10000 number of items
0008 unsigned byte ?? label
0009 unsigned byte ?? label
........
xxxx unsigned byte ?? label
The labels values are 0 to 9.
:param idx_ubyte_file: idx文件路径
:return: n*1维np.array对象，n为图片数量
"""
return decode_idx1_ubyte(idx_ubyte_file)
'''
def run():
train_images = load_train_images()
train_labels = load_train_labels()
# test_images = load_test_images()
# test_labels = load_test_labels()
# 查看前十个数据及其标签以读取是否正确
for i in range(10):
print(train_labels[i])
plt.imshow(train_images[i], cmap='gray')
plt.show()
print('done')
'''
def loaddata():
train_images = load_train_images()
train_labels = load_train_labels()
test_images = load_test_images()
test_labels = load_test_labels()
return (train_images,train_labels,test_images,test_labels)
'''
样本读取之后要归一化处理
'''
def normalize(train_images,train_labels,test_images,test_labels):
train_images = train_images/255
new_lables = np.zeros((60000,10))
for i in range(60000):
l = train_labels[i]
new_lables[i][int(l)] = 1
train_labels = new_lables
test_images = test_images/255
new_lables = np.zeros((10000,10))
for i in range(10000):
l = test_labels[i]
new_lables[i][int(l)] = 1
test_labels = new_lables
return (train_images,train_labels,test_images,test_labels)
def nextbatch(num):
pass
'''
随机从样本中获取num个样本
初期的想法：
使用np.random.permutation打乱样本
这里打乱样本和标签要一起打乱，这就需要把两者组合在一起，然后打乱
组合需要np.hstack函数，分解用np.hsplit函数
'''
def gettrains(train_images,train_labels,num):
start = np.random.randint(60000)
limit = 60000-num
if start>limit:
start = limit
t_x = train_images[start:start+num]
t_y = train_labels[start:start+num]
return (t_x,t_y)
'''
卷积部分
'''
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 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 cnn_train(train_images,train_labels,test_images,test_labels):
x = tf.placeholder("float", [None, 784])
y_ = tf.placeholder("float", [None,10])
x_image = tf.reshape(x, [-1,28,28,1])
'''
卷积第一层
'''
with tf.name_scope('first_conv'):
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)
'''
卷积第二层
'''
with tf.name_scope('second_conv'):
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)
'''
全连接层
'''
with tf.name_scope('full_connect1'):
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)
'''
抛弃部分节点
'''
with tf.name_scope('dropout'):
keep_prob = tf.placeholder(tf.float32)
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)
'''
输出层
'''
with tf.name_scope('out'):
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(logits=y_conv, labels=y_))
tf.summary.scalar('cross_entropy', cross_entropy)
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))
tf.summary.scalar('accuracy', accuracy)
merged = tf.summary.merge_all()
sess = tf.Session()
train_writer = tf.summary.FileWriter('./traindata',sess.graph)
sess.run(tf.global_variables_initializer())
for i in range(1000):
batch_xs, batch_ys = gettrains(train_images,train_labels,100)
if i%100 == 0:
summary,_ = sess.run([merged,train_step],feed_dict={x:batch_xs, y_: batch_ys, keep_prob: 1.0})
train_accuracy = accuracy.eval(session=sess,feed_dict={x:batch_xs, y_: batch_ys, keep_prob: 1.0})
train_writer.add_summary(summary,i)
print("step %d, training accuracy %g"%(i, train_accuracy))
else:
train_step.run(session=sess,feed_dict={x: batch_xs, y_: batch_ys, keep_prob: 0.5})
print("test accuracy %g"%accuracy.eval(session=sess,feed_dict={x: test_images, y_: test_labels, keep_prob: 1.0}))
def runtraining(train_images,train_labels,test_images,test_labels):
x = tf.placeholder("float", [None, 784])
W = tf.Variable(tf.zeros([784,10]))
b = tf.Variable(tf.zeros([10]))
y = tf.nn.softmax(tf.matmul(x,W) + b)
y_ = tf.placeholder("float", [None,10])
cross_entropy = -tf.reduce_sum(y_*tf.log(y))
train_step = tf.train.GradientDescentOptimizer(0.01).minimize(cross_entropy)
init = tf.global_variables_initializer()
sess = tf.Session()
sess.run(init)
for i in range(1000):
batch_xs, batch_ys = gettrains(train_images,train_labels,100) #随机产生100个点
sess.run(train_step, feed_dict={x: batch_xs, y_: batch_ys})
correct_prediction = tf.equal(tf.argmax(y,1), tf.argmax(y_,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))
print(sess.run(accuracy, feed_dict={x: test_images, y_: test_labels}))
def start():
train_images,train_labels,test_images,test_labels = loaddata()
t,l,ti,tl = normalize(train_images,train_labels,test_images,test_labels)
runtraining(t,l,ti,tl)
def start_cnn():
train_images,train_labels,test_images,test_labels = loaddata()
t,l,ti,tl = normalize(train_images,train_labels,test_images,test_labels)
cnn_train(t,l,ti,tl)
if __name__ == '__main__':
#run()
'''
train_images = load_train_images()
train_labels = load_train_labels()
train_images = train_images/255
new_lables = np.zeros((60000,10))
for i in range(60000):
l = train_labels[i]
new_lables[i][int(l)] = 1
plt.imshow(train_images[0].reshape(28,28), cmap='gray')
plt.show()
print(new_lables[0])
'''
start_cnn()
'''
------------------------------------------------
'''
'''
x = tf.placeholder("float", [None, 784])
W = tf.Variable(tf.zeros([784,10]))
b = tf.Variable(tf.zeros([10]))
y = tf.nn.softmax(tf.matmul(x,W) + b)
y_ = tf.placeholder("float", [None,10])
cross_entropy = -tf.reduce_sum(y_*tf.log(y))
train_step = tf.train.GradientDescentOptimizer(0.01).minimize(cross_entropy)
init = tf.initialize_all_variables()
sess = tf.Session()
sess.run(init)
for i in range(1000):
batch_xs, batch_ys = mnist.train.next_batch(100) #随机产生100个点
sess.run(train_step, feed_dict={x: batch_xs, y_: batch_ys})
'''
