tensorflow- MNIST机器学习入门
2016-10-02 15:30
225 查看
实现回归模型
使用TensorFlow之前,首先导入它:import tensorflow as tf #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。 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) #模型表示 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) # 在运行计算之前,我们需要添加一个操作来初始化我们创建的变量 init = tf.initialize_all_variables() # 现在我们可以在一个Session里面启动我们的模型,并初始化变量: sess = tf.Session() sess.run(init) # 开始训练模型,1000次 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})
以上是斯坦福官网教程。今天自己跟着做了一遍,具体代码如下:
>>> import tensorflow as tf >>> 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) >>> 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}) ... >>> >>> 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}) 0.9103 >>>
可以看到,效果真的达到了91%,而且速度快的超出了我的想象,几乎一下子就出来,收到了惊吓。
不过之前因为下载不到数据,一直没有实现,下载数据的代码如下:
input_data.py
# 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 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: ra df5f ise 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
相关文章推荐
- tensorflow学习(2)MNIST机器学习入门
- TensorFlow教程之MNIST机器学习入门测试
- tensorflow-MNIST机器学习入门
- TENSORFLOW官方文档-MNIST机器学习入门-建立模型
- TensorFlow 教程 - MNIST机器学习入门完整代码
- Tensorflow教程-MNIST机器学习入门
- TensorFlow之MNIST机器学习入门
- <二>、TensorFlow之MNIST机器学习入门(1)
- TensorFlow框架之MNIST机器学习入门
- TENSORFLOW官方文档-MNIST机器学习入门-训练模型
- TENSORFLOW官方文档-MNIST机器学习入门-数据集准备
- 入门GAN小示例tensorflow代码解析
- 从零开始,TensorFlow详细安装入门图文教程!
- TensorFlow入门(二)——基本用法
- Tensorflow快速入门2--实现手写数字识别
- tensorflow 神经网络入门例子
- 真正从零开始,TensorFlow详细安装入门图文教程
- 快速上手|TensorFlow从入门到实战资料汇总
- TensorFlow 入门
- TensorFlow入门教程集合