MNIST数据集格式转化

来源：互联网发布：苹果版软件商店编辑：程序博客网时间：2024/05/20 06:10

MNIST数据集是ubyte格式存储的，现在转化为png格式：
训练集：

import numpy as npimport structfrom PIL import Imageimport osdata_file = 'train-images-idx3-ubyte'# It's 47040016B, but we should set to 47040000Bdata_file_size = 47040016data_file_size = str(data_file_size - 16) + 'B'data_buf = open(data_file, 'rb').read()magic, numImages, numRows, numColumns = struct.unpack_from(    '>IIII', data_buf, 0)datas = struct.unpack_from(    '>' + data_file_size, data_buf, struct.calcsize('>IIII'))datas = np.array(datas).astype(np.uint8).reshape(    numImages, 1, numRows, numColumns)label_file = 'train-labels-idx1-ubyte'# It's 60008B, but we should set to 60000Blabel_file_size = 60008label_file_size = str(label_file_size - 8) + 'B'label_buf = open(label_file, 'rb').read()magic, numLabels = struct.unpack_from('>II', label_buf, 0)labels = struct.unpack_from(    '>' + label_file_size, label_buf, struct.calcsize('>II'))labels = np.array(labels).astype(np.int64)datas_root = 'mnist_train'if not os.path.exists(datas_root):    os.mkdir(datas_root)for i in range(10):    file_name = datas_root + os.sep + str(i)    if not os.path.exists(file_name):        os.mkdir(file_name)for ii in range(numLabels):    img = Image.fromarray(datas[ii, 0, 0:28, 0:28])    label = labels[ii]    file_name = datas_root + os.sep + str(label) + os.sep + \        'mnist_train_' + str(ii) + '.png'    img.save(file_name)

测试集：

import numpy as npimport structfrom PIL import Imageimport osdata_file = 't10k-images-idx3-ubyte'# It's 7840016B, but we should set to 7840000Bdata_file_size = 7840016data_file_size = str(data_file_size - 16) + 'B'data_buf = open(data_file, 'rb').read()magic, numImages, numRows, numColumns = struct.unpack_from(    '>IIII', data_buf, 0)datas = struct.unpack_from(    '>' + data_file_size, data_buf, struct.calcsize('>IIII'))datas = np.array(datas).astype(np.uint8).reshape(    numImages, 1, numRows, numColumns)label_file = 't10k-labels-idx1-ubyte'# It's 10008B, but we should set to 10000Blabel_file_size = 10008label_file_size = str(label_file_size - 8) + 'B'label_buf = open(label_file, 'rb').read()magic, numLabels = struct.unpack_from('>II', label_buf, 0)labels = struct.unpack_from(    '>' + label_file_size, label_buf, struct.calcsize('>II'))labels = np.array(labels).astype(np.int64)datas_root = 'mnist_test'if not os.path.exists(datas_root):    os.mkdir(datas_root)for i in range(10):    file_name = datas_root + os.sep + str(i)    if not os.path.exists(file_name):        os.mkdir(file_name)for ii in range(numLabels):    img = Image.fromarray(datas[ii, 0, 0:28, 0:28])    label = labels[ii]    file_name = datas_root + os.sep + str(label) + os.sep + \        'mnist_test_' + str(ii) + '.png'    img.save(file_name)

0 0