init

.gitignore

@@ -58,3 +58,4 @@ docs/_build/
 # PyBuilder
 target/
 
+/MNIST_data

MNIST_data/说明.txt

@@ -0,0 +1 @@
+数据文件夹

README.md

@@ -1,3 +1,14 @@
 # mnist
 
-tensorflow机器学习简单学习。
+tensorflow机器学习简单学习。
+
+#使用说明：
+下载mnist，数据文件夹如下：
+MNIST_data
+	t10k-images-idx3-ubyte.gz
+	t10k-labels-idx1-ubyte.gz
+	train-images-idx3-ubyte.gz
+	train-labels-idx1-ubyte.gz
+
+input_data.py读取数据，数据最好迅雷下载，已经注释了下载。
+python main.py即可获取结果，运行20000太久，已经设置运行1000次。

input_data.py

@@ -0,0 +1,247 @@
+# 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
+#from mnist_demo import * 
+
+import os
+
+import gzip
+import os
+import tempfile
+
+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."""
+  filepath = os.path.join(work_directory, filename)
+  print(filepath)
+#  if not tf.gfile.Exists(filepath):
+#    with tempfile.NamedTemporaryFile() as tmpfile:
+#      temp_file_name = tmpfile.name
+#      urllib.request.urlretrieve(SOURCE_URL + filename, temp_file_name)
+#      tf.gfile.Copy(temp_file_name, filepath)
+#      with tf.gfile.GFile(filepath) as f:
+#        size = f.Size()
+#      print('Successfully downloaded', filename, 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 open(filename, 'rb') as f, gzip.GzipFile(fileobj=f) 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):
+  #print(labels_dense.shape)
+  #print(labels_dense)
+  """Convert class labels from scalars to one-hot vectors."""
+  num_labels = labels_dense.shape[0]
+  #print(num_labels)
+  index_offset = numpy.arange(num_labels) * num_classes
+  #print(index_offset)
+  labels_one_hot = numpy.zeros((num_labels, num_classes))
+  #print(labels_one_hot.shape)
+  #print(labels_one_hot)
+  #print(labels_dense.shape)
+  labels_one_hot.flat[index_offset + labels_dense.ravel()] = 1
+  #print(labels_one_hot.shape)
+  return labels_one_hot
+
+
+def extract_labels(filename, one_hot=False, num_classes=10):
+  """Extract the labels into a 1D uint8 numpy array [index]."""
+  print('Extracting', filename)
+#  with tf.gfile.Open(filename, 'rb') as f, gzip.GzipFile(fileobj=f) as bytestream:
+  with open(filename, 'rb') as f, gzip.GzipFile(fileobj=f) 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, num_classes)
+    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
+#    print(self._images[start])
+    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)
+
+  test_images = test_images[VALIDATION_SIZE:]
+  test_labels = test_labels[VALIDATION_SIZE:]
+  data_sets.test = DataSet(test_images, test_labels, dtype=dtype)
+  data_sets.validation = DataSet(validation_images, validation_labels,dtype=dtype)
+
+  #print(test_images[3][15]);
+  #print(len(test_images[0][0]));
+  # print (len(test_images))
+  # if(files==null) return
+  # test_images1,test_labels1=GetImage(files)
+  # # print(((test_images1[0])))
+  # # test_images=array(test_images1)
+  # # test_labels=array(test_labels1)
+  # # print (test_labels[0])
+  # # test_images_demo=empty(1)
+  # # test_images_demo.append(test_images1)
+  # # print(shape((test_images1)))
+  # data_sets.test = DataSet(test_images1, test_labels1, dtype=dtype)
+  return data_sets

main.py

@@ -0,0 +1,112 @@
+
+# coding: utf-8
+
+# In[2]:
+
+import tensorflow as tf
+import numpy as np
+import input_data
+from nt import chdir
+
+chdir("C:/Users/dell/workspace/firstPython/mnist")
+mnist = input_data.read_data_sets('MNIST_data', one_hot=True)
+
+
+# In[3]:
+
+#启动.Tensorflow依赖于一个高效的C++后端来进行计算。与后端的这个连接叫做session。
+sess = tf.InteractiveSession()
+#占位符
+x = tf.placeholder("float", shape=[None, 784])
+y_ = tf.placeholder("float", shape=[None, 10])
+#变量
+W = tf.Variable(tf.zeros([784,10]))
+b = tf.Variable(tf.zeros([10]))
+#run
+sess.run(tf.initialize_all_variables())
+#类别预测与损失函数
+y = tf.nn.softmax(tf.matmul(x,W) + b)
+cross_entropy = -tf.reduce_sum(y_*tf.log(y))
+#训练模型
+train_step = tf.train.GradientDescentOptimizer(0.01).minimize(cross_entropy)
+for i in range(1000):
+  batch = mnist.train.next_batch(50)
+  train_step.run(feed_dict={x: batch[0], y_: batch[1]})
+#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(accuracy.eval(feed_dict={x: mnist.test.images, y_: mnist.test.labels}))
+
+
+# In[4]:
+
+#权重初始化
+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)
+#卷积和池化
+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)
+#Dropout
+
+
+# In[5]:
+
+keep_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_prediction = tf.equal(tf.argmax(y_conv,1), tf.argmax(y_,1))
+accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))
+sess.run(tf.initialize_all_variables())
+
+
+# In[8]:
+
+#for i in range(20000):
+for i in range(1000):
+    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})
+
+
+# In[7]:
+
+print("test accuracy %g"%accuracy.eval(feed_dict={
+    x: mnist.test.images, y_: mnist.test.labels, keep_prob: 1.0}))
+