用tensorflow实现MNIST（手写数字识别）

自动下载和导入MNIST数据集

# Copyright 2015 The TensorFlow Authors. 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 tempfileimport numpyfrom six.moves import urllibfrom six.moves import xrange  # pylint: disable=redefined-builtinimport tensorflow as tffrom tensorflow.contrib.learn.python.learn.datasets.mnist import read_data_sets

MNIST（手写数字识别）

#!usr/bin/python#coding:utf-8import input_dataimport tensorflow as tf#权值初始化def weight_variable(shape):  initial = tf.truncated_normal(shape, stddev=0.1)  #随机数  return tf.Variable(initial)  def bias_variable(shape):  initial = tf.constant(0.1, shape=shape)  return tf.Variable(initial)#卷积 def conv2d(x, W):  return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')#池化def max_pool_2x2(x):  return tf.nn.max_pool(x, ksize=[1, 2, 2, 1],                        strides=[1, 2, 2, 1], padding='SAME')mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)sess = tf.InteractiveSession()x = tf.placeholder(tf.float32, [None, 784])   #占位符，为输入图像和输出类别创建节点y_ = tf.placeholder("float", shape=[None, 10])x_image = tf.reshape(x, [-1,28,28,1])   #-1为缺省值，由python根据实际情况推算#第一层卷积池化W_conv1 = weight_variable([5, 5, 1, 32])#前两个维度是patch的大小，接着是输入的通道数目，最后是输出的通道数目b_conv1 = bias_variable([32])# 一句话概括：不用simgoid和tanh作为激活函数，而用ReLU作为激活函数的原因是：加速收敛。# 因为sigmoid和tanh都是饱和(saturating)的。何为饱和？个人理解是把这两者的函数曲线和导数曲线plot出来就知道了：#他们的导数都是倒过来的碗状，也就是，越接近目标，对应的导数越小。而ReLu的导数对于大于0的部分恒为1。于是ReLU确实#可以在BP的时候能够将梯度很好地传到较前面的网络。ReLU（线性纠正函数）取代sigmoid函数去激活神经元h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1) h_pool1 = max_pool_2x2(h_conv1)#第二层卷积池化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)#全连接层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)keep_prob = tf.placeholder("float")   #每个神经元被保留下来的概率h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)  #防止过拟合#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)#将任意实值向量映射到0-1范围内，元素总和为1##########训练和评估模型##########cross_entropy = -tf.reduce_sum(y_*tf.log(y_conv))  #交叉熵train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy) #1e-4:学习速率#tf.argmax给出某个tensor对象在某一维上的其数据最大值所在的索引值#由于标签向量是由0,1组成，因此最大值1所在的索引位置就是类别标签correct_prediction = tf.equal(tf.argmax(y_conv,1), tf.argmax(y_,1)) accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))#计算均值sess.run(tf.initialize_all_variables())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})print "test accuracy %g"%accuracy.eval(feed_dict={x: mnist.test.images, y_: mnist.test.labels, keep_prob: 1.0})