NO.3:自学tensorflow之路------MNIST识别,神经网络拓展

时间:2022-01-10 16:57:44

引言

  最近自学GRU神经网络,感觉真的不简单。为了能够快速跑完程序,给我的渣渣笔记本(GT650M)也安装了一个GPU版的tensorflow。顺便也更新了版本到了tensorflow-gpu 1.7。之前相关的程序代码依然兼容,可以运行。刚好遇到五一假期,一个人在实验室发霉,就顺便随手做了一下MNIST手写体数字的BP神经网络识别程序。做的比较简单,日后可能会扩充这一篇随笔,所以大概算是个草稿版。

正文

MNIST数据准备

  MNIST手写体数字识别,在人工智能中的地位有点像’hello world‘在编程中的地位,算是一个入门程序。从这个程序中其实可以扩展出很多tensorflow的使用方法。然而由于最近犯春困,就简单写一下。准备数据可以使用Google已经提供好的input_data.py文件。这里也一并提供一下源代码。

# 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

  下载保存后,将input_data.py文件放入工程目录中,然后新建工程文件,使用以下两行代码,就可以完成整个MNIST数据的准备。

import input_data

mnist =  input_data.read_data_sets('MNIST_data/', one_hot=True)

  这样,就会自动下载好数据文件到工程目录下的‘/MNIST_data/’中。如果已经下载就会跳过下载,然后将train,valiation和test三个数据集保存在mnist变量之中。

神经网络的扩展

  这一部分,以后慢慢填补,现在就用最简单的BP实现,BP的内容可以参考上一篇随笔。

损失函数

  神经网络模型的效果以及优化的目标是通过损失函数来定义的。不同的优化目标就对应需要采用不同的损失函数。分类问题中,交叉熵是判断输出向量和期望的向量接近程度的一种指标。

  摸了

优化算法

  摸了

过拟合

  摸了

滑动平均模型

  摸了

模型保存

  摸了

作业

  完成手写体数字识别程序,并尽可能提高识别的准确率。

#-*- coding:utf-8 -*-
#The MNIST database of handwritten digits
#Author:Kai Z import tensorflow as tf
import numpy as np
import input_data #创建MNIST数据,存储于/MNIST_data目录下
#mnist.train mnist.test
mnist = input_data.read_data_sets('MNIST_data/', one_hot=True) #神经网络超参数
input_node = 784
output_node = 10
hide_node = 100
batch_size = 100
learning_rate = 1e-3
training_steps = 5000 x = tf.placeholder(tf.float32,[None,input_node])
y = tf.placeholder(tf.float32,[None,output_node]) hidden_weight = tf.Variable(tf.random_normal([input_node,hide_node],stddev = 1,seed = 1))
hidden_bias = tf.Variable(tf.zeros([1,hide_node],tf.float32))
output_weight = tf.Variable(tf.random_normal([hide_node,output_node],stddev = 1,seed = 1))
output_bias = tf.Variable(tf.zeros([1,output_node],tf.float32)) h = tf.nn.tanh(tf.matmul(x,hidden_weight)+hidden_bias)
y_pred = tf.nn.sigmoid(tf.matmul(h,output_weight)+output_bias) correct_predict = tf.equal(tf.argmax(y_pred,1),tf.argmax(y,1))
accuracy = tf.reduce_mean(tf.cast(correct_predict,tf.float32)) cross_entropy = tf.nn.sparse_softmax_cross_entropy_with_logits(logits=y_pred,labels=tf.argmax(y,1))
cross_entropy_mean = tf.reduce_mean(cross_entropy) train_op = tf.train.AdamOptimizer(learning_rate).minimize(cross_entropy_mean)
init_op = tf.global_variables_initializer() with tf.Session() as sess:
sess.run(init_op) for i in range(training_steps):
input_batch,output_batch = mnist.train.next_batch(batch_size)
sess.run(train_op,feed_dict={x:input_batch,y:output_batch}) if i%100 == 0:
right_rate = sess.run(accuracy,feed_dict = {x:mnist.validation.images,y:mnist.validation.labels})
print('训练%d次后,训练正确率为百分之%f'%(i,right_rate*100))
right_rate = sess.run(accuracy,feed_dict = {x:mnist.test.images,y:mnist.test.labels})
print('训练%d次后,测试正确率为百分之%f'%(i,right_rate*100))

  最终,结果为,测试准确率达到了91%。仍然有改进的空间。