遇到代理问题时自动下载MNIST数据集的Python代码
来源:互联网 发布:淘宝上如何关闭网店 编辑:程序博客网 时间:2024/05/29 05:02
from __future__ import print_functionimport gzipimport osimport numpyfrom six.moves import urllibfrom six.moves import xrange # pylint: disable=redefined-builtinSOURCE_URL = 'http://yann.lecun.com/exdb/mnist/'#代理部分import urllib.requesthandler=urllib.request.ProxyHandler({'http':'http://username:password@proxy_url:port'})opener=urllib.request.build_opener(handler)urllib.request.install_opener(opener)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.request.urlretrieve(SOURCE_URL + filename, filepath) statinfo = os.stat(filepath) print('Successfully downloaded', filename, statinfo.st_size, 'bytes.') return filepathdef _read32(bytestream): dt = numpy.dtype(numpy.uint32).newbyteorder('>') return numpy.frombuffer(bytestream.read(4), dtype=dt)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) return datadef 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_hotdef 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 labelsclass 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
- 遇到代理问题时自动下载MNIST数据集的Python代码
- python脚本下载并解码MNIST数据遇到的问题
- 自动下载和安装 MNIST 到 TensorFlow 的 python 源码
- Caffe训练mnist数据遇到的问题(GPU版)
- MNIST数据集的gist特征提取(含全部实例代码下载地址)
- TensorFlow运行MNIST样例碰到下载数据的问题
- 机器学习入门MNIST(代码)(自动下载和本地加载数据集两种方式)
- 【keras】解决 example 案例中 MNIST 数据集下载不了的问题
- MNIST 数据集可视化代码
- 读取 mnist 数据集 --- python
- python读取MNIST数据集
- Python解析MNIST数据集
- 使用tensorflow导入已经下载好的mnist数据集
- tensorflow笔记1——自动下载和安装 MNIST 到 TensorFlow 的 python 源码
- python下载xgboost遇到的问题
- 神经网络 tensorflow教程 2.2 下载MNIST 数据集 (自动版)
- 第一个network的代码实现基于mnist数据集
- Mnist下载 Python源代码
- SpringBoot 学习记录(八): properties 属性自定义
- Giraph superstep中做的事情,以及其与BSP模型的对比
- Java常用的组件,AWT
- 只用CSS修改radio的原点样式
- C#调用PowShell执行命令的两种方式
- 遇到代理问题时自动下载MNIST数据集的Python代码
- java synchronized详解
- 回文数(Noip1999 )
- Linux工作常用指令
- PHP 图形图像操作(生成图像验证码、添加水印等)
- spring-使用外部属性文件
- 敲黑板|Artifactory对接本地仓库
- 用echo输出多个空行
- 在linux内核中读写文件