TensorFlow学习:MNIST
来源:互联网 发布:淘宝客公司 编辑:程序博客网 时间:2024/05/21 07:56
本部分学习自:极客学院
使用MNIST手写数字入门TensorFLow使用,按照教程码写代码并得到结果。
读取数据(此部分教程中预先给出):
# 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_importfrom __future__ import divisionfrom __future__ import print_functionimport gzipimport osimport tensorflow.python.platformimport numpyfrom six.moves import urllibfrom six.moves import xrange # pylint: disable=redefined-builtinimport tensorflow as tfSOURCE_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 filepathdef _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 datadef 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_hotdef 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 labelsclass 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
使用Softmax Regression模型:
#coding: utf-8import tensorflow as tfimport input_data #读入数据集的py文件mnist = input_data.read_data_sets("Mnist_data/",one_hot=True)#实现回归模型y=softmax(Wx+b)x = tf.placeholder(tf.float32,[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 成本函数:交叉熵 H(y)=-sum(yi_ * log(yi)) y:预测分布 y_:实际分布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.initialize_all_variables()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})
结果:
使用卷积神经网络:
#coding: utf-8import tensorflow as tfimport input_datamnist = input_data.read_data_sets('Mnist_data', one_hot = True)sess = tf.InteractiveSession()#占位符x = tf.placeholder("float", shape=[None, 784]) #shape可以自动捕捉因数据维度不一致导致的错误y_ = tf.placeholder("float", shape=[None, 10])#变量,机器学习中的模型参数一遍都用变量定义W = tf.Variable(tf.zeros([784, 10])) #784个特征和10个输出b = tf.Variable(tf.zeros([10])) #10个分类#类别预测与损失函数y = tf.nn.softmax(tf.matmul(x,W) + b)#构建一个多层卷积网络#定义初始化的权重函数def weight_variable(shape): initial = tf.truncated_normal(shape, stddev=0.1) return tf.Variable(initial)def bias_variable(shape): initial = tf.constant(0.1, shape=shape) return tf.Variable(initial)#定义卷积和池化函数def conv2d(x,W): return tf.nn.conv2d(x, W, strides=[1,1,1,1], padding='SAME')def max_pool_2x2(x): return tf.nn.max_pool(x, ksize=[1,2,2,1], strides=[1,2,2,1], padding='SAME')#第一层卷积W_conv1 = weight_variable([5, 5, 1, 32])b_conv1 = bias_variable([32])x_image = tf.reshape(x, [-1, 28, 28, 1])h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1)h_pool1 = max_pool_2x2(h_conv1)#第二层卷积W_conv2 = weight_variable([5, 5, 32, 64])b_conv2 = bias_variable([64])h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2)h_pool2 = max_pool_2x2(h_conv2)#密集连接层W_fc1 = weight_variable([7 *7 *64, 1024])b_fc1 = bias_variable([1024])h_pool2_flat = tf.reshape(h_pool2, [-1, 7*7*64])h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)#dropoutkeep_prob = tf.placeholder("float")h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)#输出层W_fc2 = weight_variable([1024, 10])b_fc2 = bias_variable([10])y_conv = tf.nn.softmax(tf.matmul(h_fc1_drop, W_fc2) + b_fc2)#训练和评估模型cross_entropy = -tf.reduce_sum(y_ * tf.log(y_conv))train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)correct_prediciton = tf.equal(tf.argmax(y_conv, 1), tf.argmax(y_, 1))accuracy = tf.reduce_mean(tf.cast(correct_prediciton, "float"))sess.run(tf.initialize_all_variables())for i in range(20000): batch = mnist.train.next_batch(50) if i%100 == 0: train_accuracy = accuracy.eval(feed_dict={x:batch[0], y_:batch[1], keep_prob: 1.0}) print "step %d, training accuracy %g"%(i, train_accuracy) train_step.run(feed_dict={x: batch[0], y_: batch[1], keep_prob: 0.5})print "test accuracy %g"%accuracy.eval(feed_dict={x: mnist.test.images, y_: mnist.test.labels, keep_prob: 1.0})
结果(每迭代100次输出一次结果,这里只截取最后的部分):
阅读全文
0 0
- Tensorflow学习:MNIST 识别
- TensorFlow-mnist-学习
- TensorFlow-mnist-学习-2
- TensorFlow学习:MNIST
- Tensorflow学习始于MNIST
- tensorflow MNIST机器学习入门
- tensorflow- MNIST机器学习入门
- Tensorflow入门程序MNIST学习
- tensorflow-MNIST机器学习入门
- tensorflow教程学习二MNIST
- tensorflow 学习2--- mnist测试
- Tensorflow入门(MNIST学习)
- tensorflow学习案例之MNIST
- Tensorflow MNIST机器学习入门 分类学习
- tensorflow学习(2)MNIST机器学习入门
- TensorFlow学习二:MNIST机器学习入门
- 【深度学习】Tensorflow学习笔记--MNIST
- 学习TensorFlow,邂逅MNIST数据集
- Chrome安全政策收紧,同时提升网站权重与排名
- new Handler()和new Handler(Looper.getMainLooper())的使用区别
- Go学习笔记(四)
- 一款极度偷懒的假分页js代码(只适用于要求很低的页面)
- MySQL函数一览_MySQL函数全部汇总
- TensorFlow学习:MNIST
- jquery的绑定事件有几种方式
- Spring 学习笔记(5)—— 简化xml配置文件的配置方式
- Wannafly挑战赛2 B 题 Travel 【最短路 + 思维】
- python3及wxpythonGUI多线程防假死与线程消息传递消息(最新)
- J2EE学习笔记
- List、Map、Set三个接口,存取元素的特点
- 洛谷 P2564 [SCOI2009]生日礼物
- [ [资源贴] ]数据集、函数、python、tensorflow、caffe等相关的资源分享