Tensorflow深度学习入门——下载和读取MNIST数据
来源:互联网 发布:英语口语速成软件下载 编辑:程序博客网 时间:2024/05/18 20:37
Tensorflow下载和读取MNIST数据
from __future__ import print_functionimport gzipimport osimport urllibimport numpySOURCE_URL = 'http://yann.lecun.com/exdb/mnist/'WORK_DIRECTORY = 'data' #数据存放的文件夹 data/#将数据下载到本地文件夹def maybe_download(filename, work_directory): """Download the data from Yann's website, unless it's already here.""" if not os.path.exists(work_directory): os.mkdir(work_directory) filepath = os.path.join(work_directory, filename) if not os.path.exists(filepath): filepath, _ = urllib.urlretrieve(SOURCE_URL + filename, filepath) statinfo = os.stat(filepath) print('Succesfully downloaded', filename, statinfo.st_size, 'bytes.') return filepathdef _read32(bytestream): dt = numpy.dtype(numpy.uint32).newbyteorder('>') return numpy.frombuffer(bytestream.read(4), dtype=dt) #解压图像def extract_images(filename): """Extract the images into a 4D uint8 numpy array [index, y, x, depth].""" print('Extracting', filename) with gzip.open(filename) as bytestream: magic = _read32(bytestream) if magic != 2051: raise ValueError( 'Invalid magic number %d in MNIST image file: %s' % (magic, filename)) num_images = _read32(bytestream) rows = _read32(bytestream) cols = _read32(bytestream) buf = bytestream.read(rows * cols * num_images) data = numpy.frombuffer(buf, dtype=numpy.uint8) data = data.reshape(num_images, rows, cols, 1) #图像数据被压缩成两维的tensor张量: return data#压缩 def dense_to_one_hot(labels_dense, num_classes=10): """Convert class labels from scalars to one-hot vectors.""" num_labels = labels_dense.shape[0] index_offset = numpy.arange(num_labels) * num_classes labels_one_hot = numpy.zeros((num_labels, num_classes)) labels_one_hot.flat[index_offset + labels_dense.ravel()] = 1 return labels_one_hot #解压标签def extract_labels(filename, one_hot=False): """Extract the labels into a 1D uint8 numpy array [index].""" print('Extracting', filename) with gzip.open(filename) as bytestream: magic = _read32(bytestream) if magic != 2049: raise ValueError( 'Invalid magic number %d in MNIST label file: %s' % (magic, filename)) num_items = _read32(bytestream) buf = bytestream.read(num_items) labels = numpy.frombuffer(buf, dtype=numpy.uint8) if one_hot: return dense_to_one_hot(labels) return labels class DataSet(object): def __init__(self, images, labels, fake_data=False): if fake_data: self._num_examples = 10000 else: assert images.shape[0] == labels.shape[0], ( "images.shape: %s labels.shape: %s" % (images.shape, labels.shape)) self._num_examples = images.shape[0] # Convert shape from [num examples, rows, columns, depth] # to [num examples, rows*columns] (assuming depth == 1) assert images.shape[3] == 1 images = images.reshape(images.shape[0], images.shape[1] * images.shape[2]) # Convert from [0, 255] -> [0.0, 1.0]. images = images.astype(numpy.float32) images = numpy.multiply(images, 1.0 / 255.0) self._images = images self._labels = labels self._epochs_completed = 0 self._index_in_epoch = 0 @property def images(self): return self._images @property def labels(self): return self._labels @property def num_examples(self): return self._num_examples @property def epochs_completed(self): return self._epochs_completed def next_batch(self, batch_size, fake_data=False): """Return the next `batch_size` examples from this data set.""" if fake_data: fake_image = [1.0 for _ in xrange(784)] fake_label = 0 return [fake_image for _ in xrange(batch_size)], [ fake_label for _ in xrange(batch_size)] start = self._index_in_epoch self._index_in_epoch += batch_size if self._index_in_epoch > self._num_examples: # Finished epoch self._epochs_completed += 1 # Shuffle the data perm = numpy.arange(self._num_examples) numpy.random.shuffle(perm) self._images = self._images[perm] self._labels = self._labels[perm] # Start next epoch start = 0 self._index_in_epoch = batch_size assert batch_size <= self._num_examples end = self._index_in_epoch return self._images[start:end], self._labels[start:end]def read_data_sets(train_dir, fake_data=False, one_hot=False): class DataSets(object): pass data_sets = DataSets() if fake_data: data_sets.train = DataSet([], [], fake_data=True) data_sets.validation = DataSet([], [], fake_data=True) data_sets.test = DataSet([], [], fake_data=True) return data_sets TRAIN_IMAGES = 'train-images-idx3-ubyte.gz' TRAIN_LABELS = 'train-labels-idx1-ubyte.gz' TEST_IMAGES = 't10k-images-idx3-ubyte.gz' TEST_LABELS = 't10k-labels-idx1-ubyte.gz' VALIDATION_SIZE = 5000 local_file = maybe_download(TRAIN_IMAGES, train_dir) train_images = extract_images(local_file) local_file = maybe_download(TRAIN_LABELS, train_dir) train_labels = extract_labels(local_file, one_hot=one_hot) local_file = maybe_download(TEST_IMAGES, train_dir) test_images = extract_images(local_file) local_file = maybe_download(TEST_LABELS, train_dir) test_labels = extract_labels(local_file, one_hot=one_hot) validation_images = train_images[:VALIDATION_SIZE] validation_labels = train_labels[:VALIDATION_SIZE] train_images = train_images[VALIDATION_SIZE:] train_labels = train_labels[VALIDATION_SIZE:] data_sets.train = DataSet(train_images, train_labels) data_sets.validation = DataSet(validation_images, validation_labels) data_sets.test = DataSet(test_images, test_labels) return data_sets
0 0
- Tensorflow深度学习入门——下载和读取MNIST数据
- Tensorflow深度学习入门——优化训练MNIST数据和调用训练模型识别图片
- Tensorflow深度学习入门——采用卷积和池化优化训练MNIST数据——代码+注释
- TensorFlow入门(三)——MNIST数据下载
- Tensorflow深度学习入门——TF自带的数据文件读取及下载
- 深度学习小白——Tensorflow(三) 读取数据
- Ubuntu下Tensorflow加载MNIST数据集(数据下载和读取)
- Ubuntu下Tensorflow加载MNIST数据集(数据下载和读取)
- TensorFlow官方教程学习笔记(四)——MNIST数据集的读取
- 深度学习数据集——MNIST
- Tensorflow深度学习入门——自制数据集
- 深度学习框架TensorFlow学习与应用(六)——卷积神经网络应用于MNIST数据集分类
- TensorFlow【深度学习】MNIST 视觉数据集 初级
- Tensorflow系列——MNIST(针对机器学习入门者)
- Tensorflow教程-MNIST 数据下载
- TENSORFLOW官方文档-MNIST机器学习入门-数据集准备
- tensorflow MNIST机器学习入门
- tensorflow- MNIST机器学习入门
- <Retrofit2> 添加header和baseparam
- 基于Solr的HBase多条件查询测试
- 常用centos命令
- linux网卡配置文件详解
- postman 发送带cookie的请求
- Tensorflow深度学习入门——下载和读取MNIST数据
- 斐波那契数列
- Windows(64bit)下Python2.7环境安装paramiko模块
- 欢迎使用CSDN-markdown编辑器
- Codeforces Round #381 (Div. 2) C. Alyona and mex(模拟)
- Android设置背景透明的一些问题
- MySQL 及 SQL 注入
- 反卷积与语义分割
- Android-使用Android Studio实现第三方QQ登录