神经网络提升mnist识别率

跟着tensorflow入门学习构建一个神经网络提升mnist识别率，最终提升到接近1的正确率了，基本参考网站代码，自己打上去顺便理解下过程，不懂得地方做了中文标注

# -*- coding:gbk -*-import input_dataimport tensorflow as tfmnist=input_data.read_data_sets("MNIST_data/", one_hot=True)#添加x作为占位符x=tf.placeholder("float", [None, 784])#正确结果占位符y_=tf.placeholder("float", [None,10])#设置权重函数def weight_variable(shape):    #tf.truncated_normal(shape, mean, stddev) :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    #权重在初始化时应该加入少量的噪声来打破对称性以及避免0梯度    initial=tf.truncated_normal(shape, stddev=0.1)    return tf.Variable(initial)#设置偏置函数#由于我们使用的是ReLU神经元，因此比较好的做法是用一个较小的正数来初始化偏置项，以避免神经元节点输出恒为0的问题（dead neurons）def bias_variable(shape):    initial=tf.constant(0.1, shape=shape)    return tf.Variable(initial)#卷积函数#卷积使用1步长，0边距的模板，池化用2x2的模板def conv2d(x, W):#x：待卷积的矩阵具有[batch, in_height, in_width, in_channels]这样的shape#w：卷积核具有[filter_height, filter_width, in_channels, out_channels]这样的shape#strides：卷积时在图像每一维的步长，这是一个一维的向量，长度4    return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')#池化函数#和卷积基本相同def max_pool_2x2(x):    return tf.nn.max_pool(x, ksize=[1, 2, 2, 1],strides=[1, 2, 2, 1], padding='SAME')#卷积在每个5x5的patch中算出32个特征。#卷积的权重张量形状是[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W_conv1=weight_variable([5, 5, 1, 32])b_conv1=bias_variable([32])#shape:[batch, in_height, in_width, in_channels]x_image=tf.reshape(x, [-1,28,28,1])#卷积+偏置，然后给relu激活函数，最后激活函数返回值池化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)#dropout方法减轻过拟合问题keep_prob=tf.placeholder("float")h_fc1_drop=tf.nn.dropout(h_fc1, keep_prob)#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)#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 = tf.InteractiveSession()sess.run(tf.initialize_all_variables())for i in range(2000):    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}))