下载MNIST数据集脚本input_data源码
# Copyright 2015 Google Inc. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
# ==============================================================================
"""Functions for downloading and reading MNIST data."""
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import gzip
import os
import tensorflow.python.platform
import numpy
from six.moves import urllib
from six.moves import xrange # pylint: disable=redefined-builtin
import tensorflow as tf
SOURCE_URL = 'http://yann.lecun.com/exdb/mnist/'
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 filepath
def _read32(bytestream):
dt = numpy.dtype(numpy.uint32).newbyteorder('>')
return numpy.frombuffer(bytestream.read(4), dtype=dt)[0]
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 data
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
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, one_hot=False,
dtype=tf.float32):
"""Construct a DataSet.
one_hot arg is used only if fake_data is true. `dtype` can be either
`uint8` to leave the input as `[0, 255]`, or `float32` to rescale into
`[0, 1]`.
"""
dtype = tf.as_dtype(dtype).base_dtype
if dtype not in (tf.uint8, tf.float32):
raise TypeError('Invalid image dtype %r, expected uint8 or float32' %
dtype)
if fake_data:
self._num_examples = 10000
self.one_hot = one_hot
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])
if dtype == tf.float32:
# 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] * 784
if self.one_hot:
fake_label = [1] + [0] * 9
else:
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, dtype=tf.float32):
class DataSets(object):
pass
data_sets = DataSets()
if fake_data:
def fake():
return DataSet([], [], fake_data=True, one_hot=one_hot, dtype=dtype)
data_sets.train = fake()
data_sets.validation = fake()
data_sets.test = fake()
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, dtype=dtype)
data_sets.validation = DataSet(validation_images, validation_labels,
dtype=dtype)
data_sets.test = DataSet(test_images, test_labels, dtype=dtype)
return data_sets
下载MNIST数据集脚本input_data源码的更多相关文章
- mnist 数据集的识别源码解析
在基本跑完识别代码后,再来谈一谈自己对代码的理解: 1 前向传播过程文件(mnist_forward.py) 第一个函数get_weight(shape, regularizer); 定义了 ...
- 下载 LFS所需要的源码包的脚本程序及检验方法
下载 LFS所需要的源码包的脚本程序及检验方法 http://blog.csdn.net/yygydjkthh/article/details/45315143
- openJDK之如何下载各个版本的openJDK源码
如果我们需要阅读openJDK的源码,那么需要下载,那么该去哪下载呢? 现在JDK已经发展到版本10了,11已经处于计划中,如果需要特定版本的openJDK,它们的下载链接在哪呢? 1.openJDK ...
- scikit-learn使用fetch_mldata无法下载MNIST数据集的问题
scikit-learn使用fetch_mldata无法下载MNIST数据集的问题 0. 写在前面 参考书 <Python数据科学手册> 工具 python3.5.1,Jupyter La ...
- 下载Google官方/CM Android源码自己主动又一次開始的Shell脚本
国内因为某种原因,下载CM或Google官方的Android源码总easy中断.总看着机器.一中断就又一次运行repo sync还太麻烦,所以我特意编写了一段shell脚本(download.sh). ...
- GitHub超详细图文攻略 - Git客户端下载安装 GitHub提交修改源码工作流程 Git分支 标签 过滤 Git版本工作流
最近听同事说他都在使用GitHub,GitHub是程序员的社区,在里面可以学到很多书上学不到的东西,所以最近在准备入手这方面的知识去尝试学习,正好碰到这么详细完整的文章,就转载了,希望对自己和大家有帮 ...
- 【代码管理】GitHub超详细图文攻略 - Git客户端下载安装 GitHub提交修改源码工作流程 Git分支 标签 过滤 Git版本工作流
GitHub操作总结 : 总结看不明白就看下面的详细讲解. . 作者 :万境绝尘 转载请注明出处 : http://blog.csdn.net/shulianghan/article/details ...
- python脚本使用源码安装不同版本的python
# coding=utf-8 import os import sys # 判断是否是root用户 if os.getuid() == 0: pass else: print('当前用户不是root用 ...
- openWRT自学---自己编译的第一个 backfire10.03 版本的过程记录 --- 实际是由于下载了错误的backfire源码包导致的
基于 backfire10.03(从http://downloads.openwrt.org/backfire/10.03/ 中下砸的源码包backfire_10.03_source.tar.bz2: ...
随机推荐
- Kotlin 类和对象
类定义 Kotlin 类可以包含:构造函数和初始化代码块.函数.属性.内部类.对象声明. Kotlin 中使用关键字 class 声明类,后面紧跟类名: class Runoob { // 类名为 R ...
- JDK内置工具使用
- react state成员
组件中包括state,props与render成员函数. react中,主要通过定义state,根据不同state渲染对应用户界面. 过程调用了成员函数setState(data,callback). ...
- hadoop多文件输出MultipleOutputFormat和MultipleOutputs
1.MultipleOutputFormat可以将相似的记录输出到相同的数据集.在写每条记录之前,MultipleOutputFormat将调用generateFileNameForKeyValue方 ...
- 【Python】Scrapy基础
一.Scrapy 架构 Engine(引擎):负责 Spider(爬虫).Item Pipeline(管道).Downloader(下载器).Scheduler(调度器)中的通讯和数据传递. Sche ...
- 【转】IIS - 自动申请、部署Let's Encrypt的免费SSL证书
IIS - 自动申请.部署Let's Encrypt的免费SSL证书(让网站实现HTTPS协议) 2017-12-19发布:hangge阅读:161 一.HTTPS 协议介绍 1,什么是 HTTP ...
- [LeetCode] 26. Remove Duplicates from Sorted Array ☆(从有序数组中删除重复项)
[LeetCode] Remove Duplicates from Sorted Array 有序数组中去除重复项 描述 Given a sorted array nums, remove the d ...
- PHP设置凌晨时间戳
这种需求应是很常见的,但一直没有时间整理. 一天可以领取2次奖励,今天领完了那就等明天再来. 这里面涉及到一个很重要的一点就是凌晨12点的时间戳,以前一直在前端去做判断.最近发现在后端用PHP获取凌晨 ...
- PCA算法数学原理及实现
数学原理参考:https://blog.csdn.net/aiaiai010101/article/details/72744713 实现过程参考:https://www.cnblogs.com/ec ...
- git命令简介
git作为版本控制器,多分支功能能够很好的协同开发.其中分支中分为主分支和辅助分支 主分支包括:master分支和develop分支,不多做解释 辅助分支包括一下三种分支,其中 需求分支(Featur ...