Tensorflow官方文档 input_data.py 下载
说明: 本篇文章适用于MNIST教程下载数据集。
# 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
Tensorflow官方文档 input_data.py 下载的更多相关文章
- 人工智能系统Google开源的TensorFlow官方文档中文版
人工智能系统Google开源的TensorFlow官方文档中文版 2015年11月9日,Google发布人工智能系统TensorFlow并宣布开源,机器学习作为人工智能的一种类型,可以让软件根据大量的 ...
- tensorflow官方文档中的sub 和mul中的函数已经在API中改名了
在照着tensorflow 官方文档和极客学院中tensorflow中文文档学习tensorflow时,遇到下面的两个问题: 1)AttributeError: module 'tensorflow' ...
- TensorFlow 官方文档中文版 --技术文档
1.文档预览 2.文档下载 TensorFlow官方文档中文版-v1.2.pdf 提取码:pt7p
- TensorFlow 官方文档中文版【转】
转自:http://wiki.jikexueyuan.com/project/tensorflow-zh/ TensorFlow 官方文档中文版 你正在阅读的项目可能会比 Android 系统更加深远 ...
- TensorFlow 官方文档中文版
http://wiki.jikexueyuan.com/list/deep-learning/ TensorFlow 官方文档中文版 你正在阅读的项目可能会比 Android 系统更加深远地影响着世界 ...
- jQuery Form 表单提交插件----Form 简介,官方文档,官方下载地址
一.jQuery Form简介 jQuery Form插件是一个优秀的Ajax表单插件,可以非常容易地.无侵入地升级HTML表单以支持Ajax.jQuery Form有两个核心方法 -- ajaxF ...
- TensorFlow官方文档
关于<TensorFlow官方文档> <TensorFlow官方文档>原文地址:http://devdocs.io/tensorflow~python/ ,本次经过W3Csch ...
- TensorFlow 官方文档中文版学习
TensorFlow 官方文档中文版 地址:http://wiki.jikexueyuan.com/project/tensorflow-zh/
- 在 Ubuntu 上安装 TensorFlow (官方文档的翻译)
本指南介绍了如何在 Ubuntu 上安装 TensorFlow.这些指令也可能对其他 Linux 变体起作用, 但是我们只在Ubuntu 14.04 或更高版本上测试了(我们只支持) 这些指令. 一 ...
随机推荐
- 洛谷 P1119 灾后重建(Floyd)
嗯... 题目链接:https://www.luogu.org/problem/P1119 这道题是一个Floyd的很好的题目,在Floyd的基础上加一点优化: 中转点k在这里不能暴力枚举,否则会超时 ...
- 树莓派4B踩坑指南 - (6)安装常用软件及相关设置
安装软件 安装LibreOffice中文包 sudo apt-get install libreoffice-l10n-zh-cn sudo reboot 安装codeblocks并汉化: sudo ...
- ES建立索引步骤, 1,index 2.mapping 3,别名
1.建立索引PUT /index_trans_detail 2.建立mappingPOST /index_trans_detail/type_trans_detail/_mapping{ " ...
- python浅谈编程规范和软件开发目录规范的重要性
前言 我们这些初学者,目前要做的就是遵守代码规范,这是最基本的,而且每个团队的规范可能还不一样,以后工作了,尽可能和团队保持一致,目前初学者就按照官方的要求即可 新人进入一个企业,不会接触到核心的架构 ...
- 记数问题(0)<P2013_1>
记数问题 (count.cpp/c/pas) [问题描述] 试计算在区间1到n的所有整数中,数字x(0≤x≤9)共出现了多少次?例如,在1到11中,即在1.2.3.4.5.6.7.8.9.10.11 ...
- 夯实Java基础系列目录
自进入大学以来,学习的编程语言从最初的C语言.C++,到后来的Java,. NET.而在学习编程语言的同时也逐渐决定了以后自己要学习的是哪一门语言(Java).到现在为止,学习Java语言也有很长一段 ...
- TensorFlow 训练只用cpu
os.environ["CUDA_VISIBLE_DEVICES"] = ""
- 苹果系统 MacOS 安装根证书
12306 网上购票以及一些其他内部使用的系统,需要安装.cer扩展名的根证书的情况,windows安装较为简单大家也比较熟悉,使用mac安装根证书在此做下详细介绍. 当前以10.13.5版本为例,其 ...
- jquery 单选框 radio是否选择问题
业务需求是当用户勾选中的时候删除数据,取消勾选的时候数据取消 //单选事件,获取到每行数据ID $('.checkItem').change(function(){ // checkItem是给rad ...
- Linux 长时间操作设置不断开
1.第一次尝试失败 修改/etc/ssh/sshd_config文件, 找到 ClientAliveInterval 0 ClientAliveCountMax 3 并将注释符号("#&qu ...