本文共 6199 字，大约阅读时间需要 20 分钟。
参考：http://hacker.duanshishi.com/?p=1661
使用LR可以得到0.92的分类正确率
使用AlexNet可以得到0.95的分类正确率
使用LR
# -*- coding: utf-8 -*-"""Created on Mon Jul 17 16:26:57 2017@author: bryan"""import tensorflow as tffrom tensorflow.examples.tutorials.mnist import input_datamnist = input_data.read_data_sets("F:\\learning\\tf\\mnist", one_hot=True)#parameterslearning_rate=0.01training_epochs=25batch_size=100display_step=1#tf gragh inputx=tf.placeholder(tf.float32,[None,784])#28*28=784y=tf.placeholder(tf.float32,[None,10]) #10 class#set model weightW=tf.Variable(tf.zeros([784,10]))b=tf.Variable(tf.zeros([10]))#construct modelpred=tf.nn.softmax(tf.matmul(x,W)+b) #softmax#Minimize error using corss entropycost=tf.reduce_mean(-tf.reduce_sum(y*tf.log(pred),reduction_indices=1))#Gradient Descentoptimizer=tf.train.GradientDescentOptimizer(learning_rate).minimize(cost)#initializing the variablesinit=tf.initialize_all_variables()#Launch the graghwith tf.Session() as sess: sess.run(init) #train cycle for epoch in range(training_epochs): avg_cost=0. total_batch=int(mnist.train.num_examples/batch_size) #Loop over all batches for i in range(total_batch): batch_xs, batch_ys = mnist.train.next_batch(batch_size) # Run optimization op (backprop) and cost op (to get loss value) _,c = sess.run([optimizer, cost], feed_dict={x: batch_xs,y: batch_ys}) # compute avg loss avg_cost+=c/total_batch #display logs per epoch step if(epoch+1)% display_step==0: print ("Epoch:", '%04d' % (epoch+1), "cost=", "{:.9f}".format(avg_cost)) print( "Optimization Finished!") #test model correct_prediction=tf.equal(tf.argmax(pred,1),tf.argmax(y,1)) #calculate accuracy accuracy=tf.reduce_mean(tf.cast(correct_prediction,tf.float32)) print( "Accuracy:", accuracy.eval({x: mnist.test.images, y: mnist.test.labels})) 使用AlexNet
# -*- coding: utf-8 -*-"""Created on Tue Jul 18 15:48:07 2017@author: bryan"""import tensorflow as tffrom tensorflow.examples.tutorials.mnist import input_datamnist = input_data.read_data_sets("F:\\learning\\tf\\mnist", one_hot=True)# 定义网络超参数learning_rate = 0.001training_iters = 200000batch_size = 64display_step = 20# 定义网络参数n_input = 784 # 输入的维度n_classes = 10 # 标签的维度dropout = 0.8 # Dropout 的概率# 占位符输入x = tf.placeholder(tf.float32, [None, n_input])y = tf.placeholder(tf.float32, [None, n_classes])keep_prob = tf.placeholder(tf.float32)# 卷积操作def conv2d(name, l_input, w, b): return tf.nn.relu(tf.nn.bias_add(tf.nn.conv2d(l_input, w, strides=[1, 1, 1, 1], padding='SAME'),b), name=name)# 最大下采样操作def max_pool(name, l_input, k): return tf.nn.max_pool(l_input, ksize=[1, k, k, 1], strides=[1, k, k, 1], padding='SAME', name=name)# 归一化操作def norm(name, l_input, lsize=4): return tf.nn.lrn(l_input, lsize, bias=1.0, alpha=0.001 / 9.0, beta=0.75, name=name)# 定义整个网络 def alex_net(_X, _weights, _biases, _dropout): # 向量转为矩阵 _X = tf.reshape(_X, shape=[-1, 28, 28, 1]) # 卷积层 conv1 = conv2d('conv1', _X, _weights['wc1'], _biases['bc1']) # 下采样层 pool1 = max_pool('pool1', conv1, k=2) # 归一化层 norm1 = norm('norm1', pool1, lsize=4) # Dropout norm1 = tf.nn.dropout(norm1, _dropout) # 卷积 conv2 = conv2d('conv2', norm1, _weights['wc2'], _biases['bc2']) # 下采样 pool2 = max_pool('pool2', conv2, k=2) # 归一化 norm2 = norm('norm2', pool2, lsize=4) # Dropout norm2 = tf.nn.dropout(norm2, _dropout) # 卷积 conv3 = conv2d('conv3', norm2, _weights['wc3'], _biases['bc3']) # 下采样 pool3 = max_pool('pool3', conv3, k=2) # 归一化 norm3 = norm('norm3', pool3, lsize=4) # Dropout norm3 = tf.nn.dropout(norm3, _dropout) # 全连接层，先把特征图转为向量 dense1 = tf.reshape(norm3, [-1, _weights['wd1'].get_shape().as_list()[0]]) dense1 = tf.nn.relu(tf.matmul(dense1, _weights['wd1']) + _biases['bd1'], name='fc1') # 全连接层 dense2 = tf.nn.relu(tf.matmul(dense1, _weights['wd2']) + _biases['bd2'], name='fc2') # Relu activation # 网络输出层 out = tf.matmul(dense2, _weights['out']) + _biases['out'] return out# 存储所有的网络参数weights = { 'wc1': tf.Variable(tf.random_normal([3, 3, 1, 64])), 'wc2': tf.Variable(tf.random_normal([3, 3, 64, 128])), 'wc3': tf.Variable(tf.random_normal([3, 3, 128, 256])), 'wd1': tf.Variable(tf.random_normal([4*4*256, 1024])), 'wd2': tf.Variable(tf.random_normal([1024, 1024])), 'out': tf.Variable(tf.random_normal([1024, 10]))}biases = { 'bc1': tf.Variable(tf.random_normal([64])), 'bc2': tf.Variable(tf.random_normal([128])), 'bc3': tf.Variable(tf.random_normal([256])), 'bd1': tf.Variable(tf.random_normal([1024])), 'bd2': tf.Variable(tf.random_normal([1024])), 'out': tf.Variable(tf.random_normal([n_classes]))}# 构建模型pred = alex_net(x, weights, biases, keep_prob)# 定义损失函数和学习步骤cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=pred, labels=y))#cost=tf.reduce_mean(-tf.reduce_sum(y*tf.log(pred),reduction_indices=1))optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(cost)#optimizer=tf.train.GradientDescentOptimizer(learning_rate).minimize(cost)# 测试网络correct_pred = tf.equal(tf.argmax(pred,1), tf.argmax(y,1))accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32))# 初始化所有的共享变量init = tf.initialize_all_variables()# 开启一个训练with tf.Session() as sess: sess.run(init) step = 1 # Keep training until reach max iterations while step * batch_size < training_iters: batch_xs, batch_ys = mnist.train.next_batch(batch_size) # 获取批数据 sess.run(optimizer, feed_dict={x: batch_xs, y: batch_ys, keep_prob: dropout}) if step % display_step == 0: # 计算精度 acc = sess.run(accuracy, feed_dict={x: batch_xs, y: batch_ys, keep_prob: 1.}) # 计算损失值 loss = sess.run(cost, feed_dict={x: batch_xs, y: batch_ys, keep_prob: 1.}) print ("Iter " + str(step*batch_size) + ", Minibatch Loss= " + "{:.6f}".format(loss) + ", Training Accuracy= " + "{:.5f}".format(acc)) step += 1 print ("Optimization Finished!") # 计算测试精度 print ("Testing Accuracy:", sess.run(accuracy, feed_dict={x: mnist.test.images[:256], y: mnist.test.labels[:256], keep_prob: 1.})) 转载地址：http://almvb.baihongyu.com/