python读取MNIST数据集
发布时间:2017-09-07 14:47:21
python读取MNIST数据集

在学习ufldl课程时需要用到MNIST数据集。但由于该数据集为IDX文件格式,是一种用来存储向量与多维度矩阵的文件格式,不能直接读取。

mnist的结构如下

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. 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

Label File

先是一个32位的整形 表示的是Magic Number,这是用来标示文件格式的用的。一般默认不变。2049。第二是图片的的数量。
接下来就是一次排列图片的标示Label

Image File

也是Magic Number。同上。保持不变2051。接下来依次是
图片的数量,图片的高,图片的宽,图片的像素点[灰度 256位]。

因此想要读出数据集的图片矩阵和标签的话,需要先读出Magic Number等数据。代码如下:

# encoding: utf-8 """ 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。 相关格式转换见官网以及代码注释。 """ import numpy as np import struct import matplotlib.pyplot as plt # 训练集文件 train_images_idx3_ubyte_file = 'E:/important_dataset/train-images.idx3-ubyte' # 训练集标签文件 train_labels_idx1_ubyte_file = 'E:/important_dataset/train-labels.idx1-ubyte' # 测试集文件 test_images_idx3_ubyte_file = 'E:/important_dataset/t10k-images.idx3-ubyte' # 测试集标签文件 test_labels_idx1_ubyte_file = 'E:/important_dataset/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' #'>IIII'是说使用大端法读取4个unsinged int32 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) print("offset: ",offset) fmt_image = '>' + str(image_size) + 'B' # '>784B'的意思就是用大端法读取784个unsigned byte images = np.empty((num_images, num_rows*num_cols)) 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)) offset += struct.calcsize(fmt_image) return images.T 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): 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() #(num_rows*num_cols,num_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' if __name__ == '__main__': run()

企业建站2800元起,携手武汉肥猫科技,做一个有见地的颜值派!更多优惠请戳:襄阳网站建设公司 https://www.jingchucn.com/zt/xiangyang_wangzhanjianshe/