MNIST自学

各个函数的参数含义：

$tf.truncated\_normal(shape,mean=0.0,stddev=1.0,dtype=tf.float32,seed=None,name=None)$ $shape$表示生成张量的维度，$mean$是均值，$stddev$是标准差。这个函数产生正态分布，均值和标准差自己设定。产生截断正态分布随机数，取值范围为$[mean-2\ast stddev,mean+2\ast stddev]$

卷积：$tf.nn.conv2d(input,filter,strides,padding,use\_cudnn\_on\_gpu=None,name=None)$

$input$：输入的要做卷积的图片，要求为一个张量，$shape$为$[batch,in\_height,in\_weight,in\_channel]$，其中$batch$为图片的数量，$in\_height$为图片高度，$in\_weight$为图片宽度，$in\_channel$为图片的通道数，灰度图该值为1，彩色图为3。 $filter$：卷积核，要求也是一个张量，$shape$为$[filter\_height,filter\_weight,in\_channel,out\_channels]$，其中$filter\_height$为卷积核高度，$filter\_weight$为卷积核宽度，$in\_channel$是图像通道数 ，和$input$的$in\_channel$要保持一致，$out\_channel$是卷积核数量。 $strides$：卷积时在图像每一维的步长，这是一个一维的向量，$[1,strides,strides,1]$，第一位和最后一位固定必须是1。 $padding$：$string$类型，值为$“SAME”$和$“VALID”$，表示的是卷积的形式，是否考虑边界。$“SAME”$是考虑边界，不足的时候用0去填充周围，$“VALID”$则不考虑。 $use\_cudnn\_on\_gpu$:$bool$类型，是否使用$cudnn$加速，默认为$true$。

最大池化：$tf.nn.max\_pool(value,ksize,strides,padding,name=None)$

$value$：需要池化的输入，一般池化层接在卷积层后面，所以输入通常是$featuremap$，依然是[batch, height, width, channels]这样的shape $ksize$：池化窗口的大小，取一个四维向量，一般是$[1,height,width,1]$，因为我们不想在$batch$和$channels$上做池化，所以这两个维度设为了1。 $strides$：和卷积类似，窗口在每一个维度上滑动的步长，一般也是$[1,stride,stride,1]$ $padding$：和卷积类似，可以取${}^{\prime }VALI{D}^{\prime }$ 或者${}^{\prime }SAM{E}^{\prime }$。

Dropout（一般用在全连接层）$tf.nn.dropout(x,keep\_prob,noise\_shape=None,seed=None,name=None)$

$x$：指输入，输入$tensor$ $kee{p}_{p}rob$：$float$类型，每个元素被保留下来的概率，设置神经元被选中的概率,在初始化时$keep\_prob$是一个占位符。 $noise\_shape$：一个1维的$int32$张量，表示随机生成“保留/丢弃”标志的$shape$。在默认情况下，每个元素独立安排保留或者丢弃。如果已经指定$noise\_shape$，则$x$的形状必须为可广播的。

代码部分：全部来自于Tensorflow中文社区（http://www.tensorfly.cn/tfdoc/tutorials/mnist_pros.html）

源代码1（爬虫）：

# -*- coding: utf-8 -*- """ Created on Tue Jul 16 09:09:01 2019 @author: Administrator """ 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

源代码2（用CNN对MNIST数据集进行分析）：

# -*- coding: utf-8 -*- """ Created on Wed Jul 17 15:56:44 2019 @author: Administrator """ import tensorflow as tf import input_data #读取数据 mnist = input_data.read_data_sets('MNIST_data', one_hot=True) #用占位符申明变量 x = tf.placeholder("float", [None, 784]) y_ = tf.placeholder("float", [None,10]) #构建会话 sess=tf.InteractiveSession() #用于生成初始权重矩阵W，即filter def weight_variable(shape): initial = tf.truncated_normal(shape, stddev=0.1) return tf.Variable(initial) #设置偏置值b def bias_variable(shape): initial = tf.constant(0.1, shape=shape) return tf.Variable(initial) #卷积函数 def conv2d(x, W): return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME') #最大池化函数 def max_pool_2x2(x): return tf.nn.max_pool(x, ksize=[1, 2, 2, 1],strides=[1, 2, 2, 1], padding='SAME') #filter大小为[5,5]，图片通道为1，filter数量为32 W_conv1 = weight_variable([5, 5, 1, 32]) #设置偏置值 b_conv1 = bias_variable([32]) #将图片向量变为shape[28,28]的矩阵，第一个变量为-1表示根据实际维度计算出这个shape，实则为图片数量，1表示图片通道 x_image = tf.reshape(x, [-1,28,28,1]) #进行第一次卷积，我们把x_image和权值向量W_conv1进行卷积，加上偏置项，然后应用ReLU激活函数，最后进行max pooling。 h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1) h_pool1 = max_pool_2x2(h_conv1) #进行第二次卷积，因为上次卷积应用了32个filter，因此图片通道变为32，此次使用64个filter（经验） 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) #因为通过两次卷积池化操作后，图片大小变为[7,7]，此层为密集连接层，图片通道为64，此时考虑将图片再一维化，即变为shape(1，7*7*64)的向量，考虑全连接1024个神经元，故如此设置W_fc1与b_fc1 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) #考虑减少过拟合，因此使用dropout来关闭部分神经元 keep_prob = tf.placeholder("float") h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob) #输出层，添加一个softmax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) #使用交叉熵作为loss函数 cross_entropy = -tf.reduce_sum(y_*tf.log(y_conv)) #采用ADAM优化器来做梯度最速下降 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")) #会话初始化 sess.run(tf.initialize_all_variables()) #迭代20000次，每100次迭代，输出一次迭代误差结果 for i in range(20000): batch = mnist.train.next_batch(50) if i0 == 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}) #输出最终测试结果 print("test accuracy %g"