Windows环境下本地数据源Mnist的Tensorflow实例(Python3.6)
闲篇不扯,关于Mnist,Tensorflow的简介请自己看博客。
操作系统:Windows10
Python环境:3.6,并已经安装了numpy,Tensorflow等必备库
问题:网上很多文章了,现在修改的点就是使用本地已经下载的Mnist学习数据,而不再去下载。
第一步:下载Mnist数据,Mnist数据下载地址:http://yann.lecun.com/exdb/mnist/
下方红色的四个文件就是下载的文件。下载后保存,我的保存地址是D:\python\Python36\testdata
第二步:新建数据装载程序,也就是Input_data.py文件,我是把全部的input_data文件代码复制过来的。我复制的input_data文件地址是:http://blog.csdn.net/FANGPINLEI/article/details/51790284
第三步:修改复制代码改为本地数据源读取
1.一些库文件导入的差别:
改为
import urllib #from six.moves import xrange # pylint: disable=redefined-builtin
2.增加本地数据源路径的变量localpath
3.因为我们不使用xrange,所以将Input_data.py文件中的next_batch函数的范围判断改为range方法(python3不再使用xrange)
4.修改Input_data.py的 read_data_sets函数,不再下载文件而是使用本地数据源
1)文件名前面+\\符号
2.不再使用maybe_download函数去获取地址,直接使用localpath+filename获取数据文件
第四步:编写测试代码,新建一个py文件,我的文件是test_minst.py,还是在http://blog.csdn.net/FANGPINLEI/article/details/51790284,复制代码
只需要修改一处,将init初始化tensorflow方法改为
init = tf.global_variables_initializer()
第五步:debug一下,搞定
代码:
input_data.py
#coding=utf-8 """Functions for downloading and reading MNIST data.""" #2017-10-08将文件下载改写为本地读取 from __future__ import absolute_import from __future__ import division from __future__ import print_function import gzip import os import tensorflow.python.platform import numpy import urllib #from six.moves import xrange # pylint: disable=redefined-builtin import tensorflow as tf #本地minst数据地址 localpath =r'D:\python\Python36\testdata' SOURCE_URL = 'http://yann.lecun.com/exdb/mnist/' #该方法在此案例不使用,保留 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 range(batch_size)], [ fake_label for _ in range(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 #改为读取本地文件,不再调用Maybe_download文件 #local_file = maybe_download(TRAIN_IMAGES, train_dir) local_file = localpath+TRAIN_IMAGES train_images = extract_images(local_file) #local_file = maybe_download(TRAIN_LABELS, train_dir) local_file = localpath+TRAIN_LABELS train_labels = extract_labels(local_file, one_hot=one_hot) #local_file = maybe_download(TEST_IMAGES, train_dir) local_file = localpath+TEST_IMAGES test_images = extract_images(local_file) #local_file = maybe_download(TEST_LABELS, train_dir) local_file = localpath+TEST_LABELS 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
test_mnist.py
# coding=utf-8 # File Name:test_mnist.py.py # Author: weironghao import input_data import tensorflow as tf mnist = input_data.read_data_sets("MNIST_data/", one_hot=True) # soft回归模型 x = tf.placeholder("float", [None, 784]) W = tf.Variable(tf.zeros([784,10])) b = tf.Variable(tf.zeros([10])) y = tf.nn.softmax(tf.matmul(x,W) + b) # 训练模型 y_ = tf.placeholder("float", [None,10]) cross_entropy = -tf.reduce_sum(y_*tf.log(y)) train_step = tf.train.GradientDescentOptimizer(0.01).minimize(cross_entropy) init = tf.global_variables_initializer() sess = tf.Session() sess.run(init) 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}) # 评估模型 correct_prediction = tf.equal(tf.argmax(y,1), tf.argmax(y_,1)) accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float")) print(sess.run(accuracy, feed_dict={x: mnist.test.images, y_: mnist.test.labels}))