Tensorflow学习教程------lenet多标签分类

本文在上篇的基础上利用lenet进行多标签分类。五个分类标准，每个标准分两类。实际来说，本文所介绍的多标签分类属于多任务学习中的联合训练，具体代码如下。

#coding:utf-8
import tensorflow as tf
import os
def read_and_decode(filename):
    #根据文件名生成一个队列
    filename_queue = tf.train.string_input_producer([filename])
    reader = tf.TFRecordReader()
    _, serialized_example = reader.read(filename_queue)   #返回文件名和文件
    features = tf.parse_single_example(serialized_example,
                                       features={
                                           'label1': tf.FixedLenFeature([], tf.int64),
                                           'label2': tf.FixedLenFeature([], tf.int64),
                                           'label3': tf.FixedLenFeature([], tf.int64),
                                           'label4': tf.FixedLenFeature([], tf.int64),
                                           'label5': tf.FixedLenFeature([], tf.int64),
                                           'img_raw' : tf.FixedLenFeature([], tf.string),
                                       })

    img = tf.decode_raw(features['img_raw'], tf.uint8)
    img = tf.reshape(img, [227, 227, 3])
    img = (tf.cast(img, tf.float32) * (1. / 255) - 0.5)*2
    label1 = tf.cast(features['label1'], tf.int32)
    label2 = tf.cast(features['label2'], tf.int32)
    label3 = tf.cast(features['label3'], tf.int32)
    label4 = tf.cast(features['label4'], tf.int32)
    label5 = tf.cast(features['label5'], tf.int32)
    #print img,label
    return img, label1,label2,label3,label4,label5
    
def get_batch(image, label1,label2,label3,label4,label5, batch_size,crop_size):  
    #数据扩充变换  
    distorted_image = tf.random_crop(image, [crop_size, crop_size, 3])#随机裁剪  
    distorted_image = tf.image.random_flip_up_down(distorted_image)#上下随机翻转  
    distorted_image = tf.image.random_brightness(distorted_image,max_delta=63)#亮度变化  
    distorted_image = tf.image.random_contrast(distorted_image,lower=0.2, upper=1.8)#对比度变化  
  
    #生成batch  
    #shuffle_batch的参数：capacity用于定义shuttle的范围，如果是对整个训练数据集，获取batch，那么capacity就应该够大  
    #保证数据打的足够乱   
    images, label1_batch,label2_batch,label3_batch,label4_batch,label5_batch = tf.train.shuffle_batch([distorted_image,      label1,label2,label3,label4,label5],batch_size=batch_size,  
                                                 num_threads=1,capacity=20000,min_after_dequeue=1000) 

    return images, label1_batch,label2_batch,label3_batch,label4_batch,label5_batch
       
class network(object):  

    def lenet(self,images,keep_prob):

        '''
        根据tensorflow中的conv2d函数，我们先定义几个基本符号
        输入矩阵 W×W，这里只考虑输入宽高相等的情况，如果不相等，推导方法一样，不多解释。
        filter矩阵 F×F，卷积核 
        stride值 S，步长
        输出宽高为 new_height、new_width
        在Tensorflow中对padding定义了两种取值：VALID、SAME。下面分别就这两种定义进行解释说明。
        VALID
        new_height = new_width = (W – F + 1) / S  #结果向上取整
        SAME
        new_height = new_width = W / S    #结果向上取整
        '''
        
        images = tf.reshape(images,shape=[-1,32,32,3])
        #images = (tf.cast(images,tf.float32)/255.0-0.5)*2
        #第一层，卷积层 32,32,3--->5,5,3,6--->28,28,6
        #卷积核大小为5*5 输入层深度为3即三通道图像 卷积核深度为6即卷积核的个数
        conv1_weights = tf.get_variable("conv1_weights",[5,5,3,6],initializer = tf.truncated_normal_initializer(stddev=0.1))
        conv1_biases = tf.get_variable("conv1_biases",[6],initializer = tf.constant_initializer(0.0))
        #移动步长为1 不使用全0填充
        conv1 = tf.nn.conv2d(images,conv1_weights,strides=[1,1,1,1],padding='VALID')
        #激活函数Relu去线性化
        relu1 = tf.nn.relu(tf.nn.bias_add(conv1,conv1_biases))
        
        #第二层 最大池化层  28,28,6--->1,2,2,1--->14,14,6
        #池化层过滤器大小为2*2 移动步长为2 使用全0填充
        pool1 = tf.nn.max_pool(relu1, ksize=[1,2,2,1],strides=[1,2,2,1],padding='SAME')
        
        #第三层 卷积层   14,14,6--->5,5,6,16--->10,10,16
        #卷积核大小为5*5 当前层深度为6 卷积核的深度为16
        conv2_weights = tf.get_variable("conv_weights",[5,5,6,16],initializer = tf.truncated_normal_initializer(stddev=0.1))
        conv2_biases = tf.get_variable("conv2_biases",[16],initializer = tf.constant_initializer(0.0))
        
        conv2 = tf.nn.conv2d(pool1,conv2_weights,strides=[1,1,1,1],padding='VALID') #移动步长为1 不使用全0填充
        relu2 = tf.nn.relu(tf.nn.bias_add(conv2,conv2_biases))

        #第四层 最大池化层 10,10,16--->1,2,2,1--->5,5,16
        #池化层过滤器大小为2*2 移动步长为2 使用全0填充
        pool2 = tf.nn.max_pool(relu2,ksize = [1,2,2,1],strides=[1,2,2,1],padding='SAME')
        
        #第五层 全连接层 
        fc1_weights = tf.get_variable("fc1_weights",[5*5*16,1024],initializer = tf.truncated_normal_initializer(stddev=0.1))
        fc1_biases = tf.get_variable("fc1_biases",[1024],initializer = tf.constant_initializer(0.1)) #[1,1024]
        pool2_vector = tf.reshape(pool2,[-1,5*5*16]) #特征向量扁平化 原始的每一张图变成了一行9×9*64列的向量
        fc1 = tf.nn.relu(tf.matmul(pool2_vector,fc1_weights)+fc1_biases)
        
        #为了减少过拟合 加入dropout层
        
        fc1_dropout = tf.nn.dropout(fc1,keep_prob)
        
        #第六层 全连接层
        #神经元节点数为1024  分类节点2
        fc2_weights = tf.get_variable("fc2_weights",[1024,2],initializer=tf.truncated_normal_initializer(stddev=0.1))
        fc2_biases = tf.get_variable("fc2_biases",[2],initializer = tf.constant_initializer(0.1))
        fc2 = tf.matmul(fc1_dropout,fc2_weights) + fc2_biases
        

        return fc2
    def lenet_loss(self,fc2,y1_,y2_,y3_,y4_,y5_):
        
        #第七层 输出层
        #softmax
        y1_conv = tf.nn.softmax(fc2)  
        labels1=tf.one_hot(y1_,2)       
        #定义交叉熵损失函数
        #cross_entropy = tf.reduce_mean(-tf.reduce_sum(y_ * tf.log(y_conv),reduction_indices=[1]))
        loss1 = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits = y1_conv, labels =labels1))

        y2_conv = tf.nn.softmax(fc2)  
        labels2=tf.one_hot(y2_,2)       
        #定义交叉熵损失函数
        #cross_entropy = tf.reduce_mean(-tf.reduce_sum(y_ * tf.log(y_conv),reduction_indices=[1]))
        loss2 = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits = y2_conv, labels =labels2))

        y3_conv = tf.nn.softmax(fc2)  
        labels3=tf.one_hot(y3_,2)       
        #定义交叉熵损失函数
        #cross_entropy = tf.reduce_mean(-tf.reduce_sum(y_ * tf.log(y_conv),reduction_indices=[1]))
        loss3 = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits = y3_conv, labels =labels3))

        y4_conv = tf.nn.softmax(fc2)  
        labels4=tf.one_hot(y4_,2)       
        #定义交叉熵损失函数
        #cross_entropy = tf.reduce_mean(-tf.reduce_sum(y_ * tf.log(y_conv),reduction_indices=[1]))
        loss4 = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits = y4_conv, labels =labels4))

        y5_conv = tf.nn.softmax(fc2)  
        labels5=tf.one_hot(y5_,2)       
        #定义交叉熵损失函数
        #cross_entropy = tf.reduce_mean(-tf.reduce_sum(y_ * tf.log(y_conv),reduction_indices=[1]))
        loss5 = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits = y5_conv, labels =labels5))
        
        loss = (loss1 + loss2 + loss3 + loss4 + loss5)/5
        self.cost = loss
        return self.cost

    def lenet_optimer(self,loss):
        train_optimizer = tf.train.GradientDescentOptimizer(lr).minimize(loss)  
        return train_optimizer

  
  
def train():  
    image,label1,label2,label3,label4,label5=read_and_decode("./train.tfrecords")
    testimage,testlabel1,testlabel2,testlabel3,testlabel4,testlabel5=read_and_decode("./test.tfrecords")
    batch_image,batch_label1,batch_label2,batch_label3,batch_label4,batch_label5=get_batch(image,label1,label2,label3,label4,label5,batch_size=30,crop_size=32) 
    testbatch_image,testbatch_label1,testbatch_label2,testbatch_label3,testbatch_label4,testbatch_label5=get_batch(testimage,testlabel1,testlabel2,testlabel3,testlabel4,testlabel5,batch_size=30,crop_size=32) 
    #测试数据集
    
   #建立网络,训练所用  
    x = tf.placeholder("float",shape=[None,32,32,3],name='x-input')
    y1_ = tf.placeholder("int32",shape=[None])
    y2_ = tf.placeholder("int32",shape=[None])
    y3_ = tf.placeholder("int32",shape=[None])
    y4_ = tf.placeholder("int32",shape=[None])
    y5_ = tf.placeholder("int32",shape=[None])

    keep_prob = tf.placeholder(tf.float32)

    net=network()  
    #inf=net.buildnet(batch_image)  
    inf = net.lenet(x,keep_prob)
    loss=net.lenet_loss(inf,y1_,y2_,y3_,y4_,y5_)  #计算loss
    opti=net.optimer(loss)  #梯度下降
    
    correct_prediction1 = tf.equal(tf.cast(tf.argmax(inf,1),tf.int32),testbatch_label1)
    accuracy1 = tf.reduce_mean(tf.cast(correct_prediction1,tf.float32))

    correct_prediction2 = tf.equal(tf.cast(tf.argmax(inf,1),tf.int32),testbatch_label2)
    accuracy2 = tf.reduce_mean(tf.cast(correct_prediction2,tf.float32))

    correct_prediction3 = tf.equal(tf.cast(tf.argmax(inf,1),tf.int32),testbatch_label3)
    accuracy3 = tf.reduce_mean(tf.cast(correct_prediction3,tf.float32))

    correct_prediction4 = tf.equal(tf.cast(tf.argmax(inf,1),tf.int32),testbatch_label4)
    accuracy4 = tf.reduce_mean(tf.cast(correct_prediction4,tf.float32))

    correct_prediction5 = tf.equal(tf.cast(tf.argmax(inf,1),tf.int32),testbatch_label5)
    accuracy5 = tf.reduce_mean(tf.cast(correct_prediction5,tf.float32))
   
    accuracy = (accuracy1+accuracy2+accuracy3+accuracy4+accuracy5)/5
    
    init=tf.global_variables_initializer()
    with tf.Session() as session:  
        with tf.device("/gpu:0"):
            session.run(init)  
            coord = tf.train.Coordinator()  
            threads = tf.train.start_queue_runners(coord=coord)  
            max_iter=10000  
            iter=0  
            if os.path.exists(os.path.join("model",'model.ckpt')) is True:  
                tf.train.Saver(max_to_keep=None).restore(session, os.path.join("model",'model.ckpt'))  
            while iter<max_iter:  
                #loss_np,_,label_np,image_np,inf_np=session.run([loss,opti,batch_image,batch_label,inf]) 
                b_batch_image,b_batch_label1,b_batch_label2,b_batch_label3,b_batch_label4,b_batch_label5 = session.run([batch_image,batch_label1,batch_label2,batch_label3,batch_label4,batch_label5])    
                testb_batch_image,testb_batch_label1,testb_batch_label2,testb_batch_label3,testb_batch_label4,testb_batch_label5 = session.run([testbatch_image,testbatch_label1,testbatch_label2,testbatch_label3,testbatch_label4,testbatch_label5])         
                loss_np,_=session.run([loss,opti],feed_dict={x:b_batch_image,y1_:b_batch_label1,y2_:b_batch_label2,y3_:b_batch_label3,y4_:b_batch_label4,y5_:b_batch_label5,keep_prob:0.6})   
                if iter%50==0:  
                    print 'trainloss:',loss_np   
                if iter%500==0:
                    #accuracy_np = session.run([accuracy])
                    accuracy_np = session.run([accuracy],feed_dict={x:testb_batch_image,y1_:testb_batch_label1,y2_:testb_batch_label2,y3_:testb_batch_label3,y4_:testb_batch_label4,y5_:testb_batch_label5,keep_prob:1.0})
                    print '测试集准确率为：',accuracy_np
                iter+=1  
            coord.request_stop()#queue需要关闭，否则报错  
            coord.join(threads)           
if __name__ == '__main__':
    train()