Tensorflow学习教程------读取数据、建立网络、训练模型，小巧而完整的代码示例
紧接上篇Tensorflow学习教程------tfrecords数据格式生成与读取，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-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={
'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<max_iter:
loss_np,_,label_np,image_np,inf_np=session.run([loss,opti,batch_image,batch_label,inf])
if iter%50==0:
print 'trainloss:',loss_np
iter+=1
coord.request_stop()#queue需要关闭，否则报错
coord.join(threads)
if __name__ == '__main__':
train()结果如下：
Total memory: 10.91GiB Free memory: 10.16GiB 2018-02-02 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: 0.745739 trainloss: 0.330364 trainloss: 0.317668 trainloss: 0.314964 trainloss: 0.314613 trainloss: 0.314483 trainloss: 0.314132 trainloss: 0.313661