tensorflow实战系列（三）一个完整的例子

#!/usr/bin/env python2
# -*- coding: utf-8 -*-
"""
Created on Wed Jan 18 08:42:55 2017

@author: root
"""

#!/usr/bin/env python2
# -*- coding: utf-8 -*-
"""
Created on Mon Jan 16 11:08:21 2017

@author: root
"""
import tensorflow as tf
import frecordfortrain
tf.device(0)
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={
                                           'label': 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.reshape(img, [39, 39, 3])
    img = tf.cast(img, tf.float32) * (1. / 255) - 0.5
    label = tf.cast(features['label'], tf.int32)
    print img,label
    return img, label
    
def get_batch(image, label, 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, label_batch = tf.train.shuffle_batch([distorted_image, label],batch_size=batch_size,  
 #                                                num_threads=16,capacity=50000,min_after_dequeue=10000)  
    images, label_batch = tf.train.shuffle_batch([distorted_image, label],batch_size=batch_size,  
                                                 num_threads=2,capacity=2,min_after_dequeue=10)
    #images, label_batch=tf.train.batch([distorted_image, label],batch_size=batch_size)  
    # 调试显示  
    #tf.image_summary('images', images)  
    print "in get batch"
    print images,label_batch
    return images, tf.reshape(label_batch, [batch_size])    
    
 
#from  data_encoder_decoeder import  encode_to_tfrecords,decode_from_tfrecords,get_batch,get_test_batch  
import  cv2  
import  os  
 
class network(object):  
    def inference(self,images):  
        # 向量转为矩阵  
      #  images = tf.reshape(images, shape=[-1, 39,39, 3])
        images = tf.reshape(images, shape=[-1, 227,227, 3])# [batch, in_height, in_width, in_channels]  
        images=(tf.cast(images,tf.float32)/255.-0.5)*2#归一化处理  
 
 
 
        #第一层  
        conv1=tf.nn.bias_add(tf.nn.conv2d(images, self.weights['conv1'], strides=[1, 4, 4, 1], padding='VALID'),  
                             self.biases['conv1'])  
 
        relu1= tf.nn.relu(conv1)  
        pool1=tf.nn.max_pool(relu1, ksize=[1, 3, 3, 1], strides=[1, 2, 2, 1], padding='VALID')  
 
 
        #第二层  
        conv2=tf.nn.bias_add(tf.nn.conv2d(pool1, self.weights['conv2'], strides=[1, 1, 1, 1], padding='SAME'),  
                             self.biases['conv2'])  
        relu2= tf.nn.relu(conv2)  
        pool2=tf.nn.max_pool(relu2, ksize=[1, 3, 3, 1], strides=[1, 2, 2, 1], padding='VALID')  
 
 
        # 第三层  
        conv3=tf.nn.bias_add(tf.nn.conv2d(pool2, self.weights['conv3'], strides=[1, 1, 1, 1], padding='SAME'),  
                             self.biases['conv3'])  
        relu3= tf.nn.relu(conv3)  
      #  pool3=tf.nn.max_pool(relu3, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='VALID')  
        conv4=tf.nn.bias_add(tf.nn.conv2d(relu3, self.weights['conv4'], strides=[1, 1, 1, 1], padding='SAME'),  
                             self.biases['conv4'])  
        relu4= tf.nn.relu(conv4)
        conv5=tf.nn.bias_add(tf.nn.conv2d(relu4, self.weights['conv5'], strides=[1, 1, 1, 1], padding='SAME'),  
                             self.biases['conv5'])  
        relu5= tf.nn.relu(conv5)
        pool5=tf.nn.max_pool(relu5, ksize=[1, 3, 3, 1], strides=[1, 2, 2, 1], padding='VALID')
        # 全连接层1，先把特征图转为向量  
        flatten = tf.reshape(pool5, [-1, self.weights['fc1'].get_shape().as_list()[0]])  
 
        drop1=tf.nn.dropout(flatten,0.5)  
        fc1=tf.matmul(drop1, self.weights['fc1'])+self.biases['fc1']  
 
        fc_relu1=tf.nn.relu(fc1)  
 
        fc2=tf.matmul(fc_relu1, self.weights['fc2'])+self.biases['fc2']
        fc_relu2=tf.nn.relu(fc2)  
 
        fc3=tf.matmul(fc_relu2, self.weights['fc3'])+self.biases['fc3']
 
        return  fc3

def __init__(self):  
        with tf.variable_scope("weights"):
           self.weights={  
                #39*39*3->36*36*20->18*18*20  
                'conv1':tf.get_variable('conv1',[11,11,3,96],initializer=tf.contrib.layers.xavier_initializer_conv2d()),  
                #18*18*20->16*16*40->8*8*40  
                'conv2':tf.get_variable('conv2',[5,5,96,256],initializer=tf.contrib.layers.xavier_initializer_conv2d()),  
                #8*8*40->6*6*60->3*3*60  
                'conv3':tf.get_variable('conv3',[3,3,256,384],initializer=tf.contrib.layers.xavier_initializer_conv2d()),  
                #3*3*60->120  
                'conv4':tf.get_variable('conv4',[3,3,384,384],initializer=tf.contrib.layers.xavier_initializer_conv2d()),

'conv5':tf.get_variable('conv5',[3,3,384,256],initializer=tf.contrib.layers.xavier_initializer_conv2d()),

'fc1':tf.get_variable('fc1',[6*6*256,4096],initializer=tf.contrib.layers.xavier_initializer()),  
                'fc2':tf.get_variable('fc2',[4096,4096],initializer=tf.contrib.layers.xavier_initializer()),

#120->6  
                'fc3':tf.get_variable('fc3',[4096,2],initializer=tf.contrib.layers.xavier_initializer()),  
                }  
        with tf.variable_scope("biases"):  
            self.biases={  
                'conv1':tf.get_variable('conv1',[96,],initializer=tf.constant_initializer(value=0.0, dtype=tf.float32)),  
                'conv2':tf.get_variable('conv2',[256,],initializer=tf.constant_initializer(value=0.0, dtype=tf.float32)),  
                'conv3':tf.get_variable('conv3',[384,],initializer=tf.constant_initializer(value=0.0, dtype=tf.float32)),  
                'conv4':tf.get_variable('conv4',[384,],initializer=tf.constant_initializer(value=0.0, dtype=tf.float32)),  
                'conv5':tf.get_variable('conv5',[256,],initializer=tf.constant_initializer(value=0.0, dtype=tf.float32)),  
                
                'fc1':tf.get_variable('fc1',[4096,],initializer=tf.constant_initializer(value=0.0, dtype=tf.float32)),  
                'fc2':tf.get_variable('fc2',[4096,],initializer=tf.constant_initializer(value=0.0, dtype=tf.float32)),
                'fc3':tf.get_variable('fc3',[2,],initializer=tf.constant_initializer(value=0.0, dtype=tf.float32))

}
        
        
        
    def inference_test(self,images):  
                # 向量转为矩阵  
        images = tf.reshape(images, shape=[-1, 39,39, 3])# [batch, in_height, in_width, in_channels]  
        images=(tf.cast(images,tf.float32)/255.-0.5)*2#归一化处理  
 
 
 
        #第一层  
        conv1=tf.nn.bias_add(tf.nn.conv2d(images, self.weights['conv1'], strides=[1, 1, 1, 1], padding='VALID'),  
                             self.biases['conv1'])  
 
        relu1= tf.nn.relu(conv1)  
        pool1=tf.nn.max_pool(relu1, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='VALID')  
 
 
        #第二层  
        conv2=tf.nn.bias_add(tf.nn.conv2d(pool1, self.weights['conv2'], strides=[1, 1, 1, 1], padding='VALID'),  
                             self.biases['conv2'])  
        relu2= tf.nn.relu(conv2)  
        pool2=tf.nn.max_pool(relu2, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='VALID')  
 
 
        # 第三层  
        conv3=tf.nn.bias_add(tf.nn.conv2d(pool2, self.weights['conv3'], strides=[1, 1, 1, 1], padding='VALID'),  
                             self.biases['conv3'])  
        relu3= tf.nn.relu(conv3)  
        pool3=tf.nn.max_pool(relu3, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='VALID')  
 
 
        # 全连接层1，先把特征图转为向量  
        flatten = tf.reshape(pool3, [-1, self.weights['fc1'].get_shape().as_list()[0]])  
 
        fc1=tf.matmul(flatten, self.weights['fc1'])+self.biases['fc1']  
        fc_relu1=tf.nn.relu(fc1)  
 
        fc2=tf.matmul(fc_relu1, self.weights['fc2'])+self.biases['fc2']  
 
        return  fc2  
 
    #计算softmax交叉熵损失函数  
    def sorfmax_loss(self,predicts,labels):  
        predicts=tf.nn.softmax(predicts)  
        labels=tf.one_hot(labels,self.weights['fc3'].get_shape().as_list()[1])  
        loss = tf.nn.softmax_cross_entropy_with_logits(predicts, labels)
      #  loss =-tf.reduce_mean(labels * tf.log(predicts))# tf.nn.softmax_cross_entropy_with_logits(predicts, labels)  
        self.cost= loss  
        return self.cost  
    #梯度下降  
    def optimer(self,loss,lr=0.01):  
        train_optimizer = tf.train.GradientDescentOptimizer(lr).minimize(loss)  
 
        return train_optimizer  
 
 
def train():  
  #  encode_to_tfrecords("data/train.txt","data",'train.tfrecords',(45,45))  
  #  image,label=decode_from_tfrecords('data/train.tfrecords')
  #  image,label=read_and_decode("/home/zenggq/data/imagedata/data.tfrecords")
    batch_image,batch_label=read_and_decode("/home/zenggq/data/imagedata/data.tfrecords")
 #   batch_image = tf.random_crop(batch_image1, [39, 39, 3])
 #   batch_image,batch_label=get_batch(image,label,batch_size=5,crop_size=227)#batch 生成测试  
   #网络链接,训练所用  
    net=network()  
    inf=net.inference(batch_image)  
    loss=net.sorfmax_loss(inf,batch_label)  
    opti=net.optimer(loss)  
    #验证集所用  
    """ encode_to_tfrecords("data/val.txt","data",'val.tfrecords',(45,45))  
    test_image,test_label=decode_from_tfrecords('data/val.tfrecords',num_epoch=None)  
    test_images,test_labels=get_test_batch(test_image,test_label,batch_size=120,crop_size=39)#batch 生成测试  
    test_inf=net.inference_test(test_images)  
    correct_prediction = tf.equal(tf.cast(tf.argmax(test_inf,1),tf.int32), test_labels)  
    accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))  """
    init=tf.initialize_all_variables()
    with tf.Session() as session:  
        with tf.device("/gpu:1"):
            session.run(init)  
            coord = tf.train.Coordinator()  
            threads = tf.train.start_queue_runners(coord=coord)  
            max_iter=9000  
            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])  
                #print image_np.shape  
                #cv2.imshow(str(label_np[0]),image_np[0])  
                #print label_np[0]  
                #cv2.waitKey()  
                #print label_np  
                if iter%50==0:  
                    print 'trainloss:',loss_np  
         #       if iter%500==0:  
         #           accuracy_np=session.run([accuracy])  
          #          print '***************test accruacy:',accuracy_np,'*******************'  
         #           tf.train.Saver(max_to_keep=None).save(session, os.path.join('model','model.ckpt'))  
                iter+=1  
            coord.request_stop()#queue需要关闭，否则报错  
            coord.join(threads)
       #     session.close()

if __name__ == '__main__':
    train()