紧接上篇，本篇将数据读取、建立网络以及模型训练整理成一个小样例，完整代码如下。
#coding:utf-8import tensorflow as tfimport osdef 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.cast(img, tf.float32) * (1. / 255) - 0.5)*2 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=1,capacity=2000,min_after_dequeue=1000) return images, label_batch class network(object): #构造函数初始化 卷积层 全连接层 def __init__(self): with tf.variable_scope("weights"): self.weights={ 'conv1':tf.get_variable('conv1',[4,4,3,20],initializer=tf.contrib.layers.xavier_initializer_conv2d()), 'conv2':tf.get_variable('conv2',[3,3,20,40],initializer=tf.contrib.layers.xavier_initializer_conv2d()), 'conv3':tf.get_variable('conv3',[3,3,40,60],initializer=tf.contrib.layers.xavier_initializer_conv2d()), 'fc1':tf.get_variable('fc1',[3*3*60,120],initializer=tf.contrib.layers.xavier_initializer()), 'fc2':tf.get_variable('fc2',[120,2],initializer=tf.contrib.layers.xavier_initializer()), } with tf.variable_scope("biases"): self.biases={ 'conv1':tf.get_variable('conv1',[20,],initializer=tf.constant_initializer(value=0.0, dtype=tf.float32)), 'conv2':tf.get_variable('conv2',[40,],initializer=tf.constant_initializer(value=0.0, dtype=tf.float32)), 'conv3':tf.get_variable('conv3',[60,],initializer=tf.constant_initializer(value=0.0, dtype=tf.float32)), 'fc1':tf.get_variable('fc1',[120,],initializer=tf.constant_initializer(value=0.0, dtype=tf.float32)), 'fc2':tf.get_variable('fc2',[2,],initializer=tf.constant_initializer(value=0.0, dtype=tf.float32)), } def buildnet(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='SAME'), 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]]) 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'] return fc2 #计算softmax交叉熵损失函数 def softmax_loss(self,predicts,labels): predicts=tf.nn.softmax(predicts) labels=tf.one_hot(labels,self.weights['fc2'].get_shape().as_list()[1]) loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits = predicts, labels =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(): image,label=read_and_decode("./train.tfrecords") batch_image,batch_label=get_batch(image,label,batch_size=30,crop_size=39) #建立网络,训练所用 net=network() inf=net.buildnet(batch_image) loss=net.softmax_loss(inf,batch_label) #计算loss opti=net.optimer(loss) #梯度下降 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=1000 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 结果如下：
Total memory: 10.91GiBFree memory: 10.16GiB2018-02-02 10:13:24.462286: I tensorflow/core/common_runtime/gpu/gpu_device.cc:961] DMA: 0 2018-02-02 10:13:24.462294: I tensorflow/core/common_runtime/gpu/gpu_device.cc:971] 0: Y 2018-02-02 10:13:24.462303: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1030] Creating TensorFlow device (/gpu:0) -> (device: 0, name: GeForce GTX 1080 Ti, pci bus id: 0000:03:00.0)trainloss: 0.745739trainloss: 0.330364trainloss: 0.317668trainloss: 0.314964trainloss: 0.314613trainloss: 0.314483trainloss: 0.314132trainloss: 0.313661