MNIST_Basic_Method

数据导入

import numpy as np
import struct
import matplotlib.pyplot as plt

#---------------文件路径：--------------------------------------------
# 训练集文件
train_images_idx3_ubyte_file = 'MNIST_data/train-images.idx3-ubyte'
# 训练集标签文件
train_labels_idx1_ubyte_file = 'MNIST_data/train-labels.idx1-ubyte'
# 测试集文件
test_images_idx3_ubyte_file = 'MNIST_data/t10k-images.idx3-ubyte'
# 测试集标签文件
test_labels_idx1_ubyte_file = 'MNIST_data/t10k-labels.idx1-ubyte'
#-------------idx-ubyte数据格式---------------------------------------
'''
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.
'''
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'
    #因为数据结构中前4行的数据类型都是32位整型，所以采用i格式，但我们需要读取前4行数据，所以需要4个i。我们后面会看到标签集中，只使用2个ii。
    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))
    for i in range(num_images):
        
        images[i] = np.array(struct.unpack_from(fmt_image, bin_data, offset)).reshape((num_rows, num_cols))
        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)
    for i in range(num_images):
        
        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()
    return (train_images,train_labels),(test_images,test_labels)

    # 查看前十个数据及其标签以读取是否正确

(train_images,train_labels),(test_images,test_labels) = run()

train_images.shape,train_labels.shape,test_images.shape,test_labels.shape

return : ((60000, 28, 28), (60000,), (10000, 28, 28), (10000,))
尝试得到一个数据：

img = train_images[0]
img /= 255
img = np.array(img)
plt.imshow(img)

train_label_new = []
a = [0,0,0,0,0,0,0,0,0,0]
for i in train_labels:
    a[int(i)]=1
    train_label_new.append(a)
    a = [0,0,0,0,0,0,0,0,0,0]

test_label_new = []
a = [0,0,0,0,0,0,0,0,0,0]
for i in test_labels:
    a[int(i)]=1
    test_label_new.append(a)
    a = [0,0,0,0,0,0,0,0,0,0]

train_label = np.array(train_label_new,dtype=np.float32)
test_label = np.array(test_label_new,dtype=np.float32)

train_image = np.array(train_images,dtype=np.float32).reshape(-1,784)
test_image = np.array(test_images,dtype=np.float32).reshape(-1,784)```

# 定义变量

```python

import tensorflow as tf
x = tf.placeholder(tf.float32,[None,784],name='input_x')
y = tf.placeholder(tf.float32,[None,1],name='input_y')
W1 = tf.Variable(tf.random_normal([784,10]),name = 'W1',dtype=tf.float32)
b1 = tf.Variable(tf.zeros([10]),name='b1',dtype=tf.float32)

前向传递函数，loss， optimizer，initializer

前向传递

y_out = tf.nn.relu(tf.matmul(x,W1) + b1)

loss

loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=y_out,labels=y))
#交叉熵

optimizer

optimizer = tf.train.AdamOptimizer(0.01).minimize(loss)

initializer

initializer = tf.global_variables_initializer()

accuracy = tf.reduce_mean(tf.cast(tf.equal(tf.argmax(y_out,axis=1),tf.argmax(y,axis=1)),tf.float32))

with tf.Session() as sess:
    sess.run(initializer)
    
    for epoch in range(100) :
        
        #print(sess.run(y,feed_dict={y:train_labels}))
        for i in range(1000):
            timg = train_image[60*i:60*(i+1)]
            tlab = train_label[60*i:60*(i+1)]
            sess.run(optimizer,feed_dict={x:timg,y:tlab})
            l,a = sess.run([loss,accuracy],feed_dict={x:timg,y:tlab})
            
       
        
        print('Epoch {0} : loss = {1}, accuracy = {2}'.format(epoch+1,l,a))
    l,a = sess.run([loss,accuracy],feed_dict={x:test_image,y:test_label})
    print('Test: loss = {0}, accuracy = {1}'.format(l,a))

参考：