黑马程序员技术交流社区
标题: 【上海校区】TensorFlow简要教程系列（四）TensorFlow实现Softma... [打印本页]
作者: 梦缠绕的时候 时间: 2018-8-28 09:20
标题: 【上海校区】TensorFlow简要教程系列（四）TensorFlow实现Softma...
本节我们建立Softmax回归用于经典的MNIST图像识别数据集作为深度学习入门。主要是学习TensorFlow时作的笔记，大家可以参考官网，本系列增加了自己在学习过程中对于不理解的地方的学习笔记，希望能对大家有所帮助。
这里我们开始实现Softmax，数据集下载在http://yann.lecun.com/exdb/mnist/上，大家也可以自己下载处理。我们利用input_data导入数据（input_data代码在文末），建立模型，具体见注释，最终准确率93%左右。
# -*- coding: utf-8 -*-
"""
Created on Sat Apr 1 09:35:59 2017
@author: chenbin
"""
import input_data
mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)
import tensorflow as tf
x = tf.placeholder('float',[None,784])
"""x不是一个特定的值，而是一个占位符placeholder，我们在TensorFlow运行计算时输入这个值。我们希望能够输入任意数量的MNIST图像，每一张图展平成784维的向量。我们用2维的浮点数张量来表示这些图，这个张量的形状是[None，784 ]。（这里的None表示此张量的第一个维度可以是任何长度的。）"""
W = tf.Variable(tf.zeros([784,10]))
b = tf.Variable(tf.zeros([10]))
"""我们赋予tf.Variable不同的初值来创建不同的Variable：在这里，
我们都用全为零的张量来初始化W和b。因为我们要学习W和b的值，它们的初值可以随意设置。"""
y = tf.nn.softmax(tf.matmul(x,W) + b) #matmul 矩阵相乘
y_ = tf.placeholder("float", [None,10]) #记录真实值
cross_entropy = -tf.reduce_sum(y_*tf.log(y))
#计算交叉熵,tf.redece_sum是求和
train_step = tf.train.GradientDescentOptimizer(0.01).minimize(cross_entropy)
"""我们要求TensorFlow用梯度下降算法（gradient descent algorithm）
以0.01的学习速率最小化交叉熵。
"""
init = tf.initialize_all_variables() #初始化变量
sess = tf.Session()
sess.run(init) #在一个Session里面启动我们的模型，并且初始化变量
#训练模型
for i in range(1000):
batch_xs, batch_ys = mnist.train.next_batch(100)
sess.run(train_step, feed_dict={x: batch_xs, y_: batch_ys})
"""
该循环的每个步骤中，我们都会随机抓取训练数据中的100个批处理数据点，next_batch随机选
然后我们用这些数据点作为参数替换之前的占位符来运行train_step。
"""
#评估模型
correct_prediction = tf.equal(tf.argmax(y,1), tf.argmax(y_,1))
"""
tf.argmax 是一个非常有用的函数，它能给出某个tensor对象在某一维上的
其数据最大值所在的索引值。由于标签向量是由0,1组成，因此最大值1所在的索引位置就是类别标签，
比如tf.argmax(y,1)返回的是模型对于任一输入x预测到的标签值，
而 tf.argmax(y_,1) 代表正确的标签，
我们可以用 tf.equal 来检测我们的预测是否真实标签匹配(索引位置一样表示匹配)
"""
#取平均值得到准确率
accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))
"""将x或者x.values转换为dtype
tensor a is [1.8, 2.2], dtype=tf.float
tf.cast(a, tf.int32) ==> [1, 2] # dtype=tf.int32
"""
print (sess.run(accuracy, feed_dict={x: mnist.test.images, y_: mnist.test.labels}))
input_data代码：
# ==============================================================================
"""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 numpy
from six.moves import urllib
from six.moves import xrange # pylint: disable=redefined-builtin
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)
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):
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
作者: 不二晨 时间: 2018-8-30 17:10
奈斯，加油加油
| 欢迎光临 黑马程序员技术交流社区 (http://bbs.itheima.com/) |
黑马程序员IT技术论坛 X3.2 |