手写数字识别是入门的教程,利用这个学习一下深度学习原理以及tensorflow的使用
1、前向过程 mnist_inference.py
#coding:utf-8
import tensorflow as tf
#定义神经网络结构相关的参数
INPURT_NODE = 784
OUTPUT_NIDE = 10
IMAGE_SIZE = 28
NUM_CHANNELS = 1
NUM_LABELS = 10
#第一层卷积层的尺寸和深度
CONV1_SIZE = 5
CONV1_DEEP = 32
#第二层的卷积层的尺寸和深度
CONV2_SIZE = 5
CONV2_DEEP = 64
#全连接层的节点个数
FC_SIZE = 512
def inference(input_tensor,train,regularizer):
with tf.variable_scope("layer1-conv1"):
conv1_weights = tf.get_variable("weight",[CONV1_SIZE,CONV1_SIZE,NUM_CHANNELS,CONV1_DEEP],initializer=tf.truncated_normal_initializer(stddev=0.1))
conv1_biases = tf.get_variable("bias",[CONV1_DEEP],initializer=tf.constant_initializer(0.0))
conv1 = tf.nn.conv2d(input_tensor,conv1_weights,strides = [1,1,1,1],padding = "SAME")
relu1 = tf.nn.relu(tf.nn.bias_add(conv1,conv1_biases))
with tf.variable_scope("layer2-pool1"):
pool1 = tf.nn.pool(relu1,ksize = [1,2,2,1],strides=[1,2,2,1],padding = "SAME")
with tf.variable_scope("layer3-conv2"):
conv2_weights = tf.get_variable("weight",[CONV2_SIZE,CONV2_SIZE,CONV1_DEEP,CONV2_DEEP],initializer=tf.truncated_normal_initializer(stddev=0.1))
conv2_biases = tf.get_variable("bias",[CONV2_DEEP],initializer=tf.constant_initializer(0.0))
conv2 = tf.nn.conv2d(relu1,conv2_weights,[1,1,1,1],padding="SAME")
relu2 = tf.nn.relu(tf.nn.bias_add(conv2,conv2_biases))
with tf.variable_scope("layer4-pool2"):
pool2 = tf.nn.pool(relu2,kszie=[1,2,2,1],strides=[1,2,2,1],padding="SAME")
pool_shape = pool2.get_shape().as_list()
nodes = pool_shape[1]*pool_shape[2]*pool_shape[3]
reshaped = tf.reshape(pool2,[pool_shape[0],nodes])
with tf.variable_scope("layer5-fc1"):
fc1_weights = tf.get_variable("weight",[nodes,FC_SIZE],initializer=tf.truncated_normal_initializer(stddev=0.1))
if regularizer !=None:
tf.add_to_collection("losses",regularizer(fc1_weights))
fc1_biases = tf.get_variable("bias",[FC_SIZE],initializer=tf.constant_initializer(0.1))
fc1 = tf.nn.relu(tf.matmul(reshape,fc1_weights)+fc1_biases)
#一般只在全连接层进行dropout操作,而不在卷积层或者池化层
if train:
fc1 = tf.nn.dropout(fc1,0.7)
with tf.variable_scope("layer6-fc2"):
fc2_weights = tf.get_variable("weight",[FC_SIZE,NUM_LABELS],initializer=tf.truncated_normal_initializer(stddev=0.1))
if regularizer != None:
tf.add_to_collection("losses",regularizer(fc2_weights))
fc2_biases=tf.get_variable("bias",[NUM_LABELS],initializer=tf.constant_initializer(0.0))
logit = tf.matmul(fc1,fc2_weights)+fc2_biases
return logit
2、进行训练,误差反向传播tensorflow内部自动求解,mnsit_train.py,这里涉及到模型的保存
#coding:utf-8
import tensorflow as tf
import os
from tensorflow.examples.tutorials.mnist import input_data
#加载刚刚些的前向传播过程
import mnist_inference
#配置神经网络的参数
BATCH_SIZE = 100
LEARNING_RATE_BASE = 0.8#指数衰减基础学习率
LEARNING_RATE_DECAY = 0.99#衰减率
REGULARAZTION_RATE = 0.0001#正则化的权重
TRAIN_STEP = 30000
MOVING_AVERAGE_DECAY = 0.99#滑动平均率
MODEL_SAVE_PATH = "./model"
MODEL_NAME = "model.ckpt"
def train(mnist):
x = tf.placeholder(tf.float32,[
BATCH_SIZE,
mnist_inference.IMAGE_SIZE,
mnist_inference.IMAGE_SIZE,
mnist_inference.NUM_CHANNELS],
name="x-input")
y_ = tf.placeholder(tf.float32,[None,mnist_inference.OUTPUT_NIDE],name="y-input")
regularizer = tf.contrib.layers.l2_regularizer(REGULARAZTION_RATE)
y = mnist_inference.inference(x,regularizer)
global_step = tf.Variable(0,trainable=False)#设置global_step为不可训练数值,在训练过程中它不进行相应的更新
#对w,b进行滑动平均操作
variable_average = tf.train.ExponentialMovingAverage(MOVING_AVERAGE_DECAY,global_step)#对滑动平均函数进行输入滑动平均率以及步数
variable_average_op = variable_average.apply(tf.trainable_variables())#对所以可训练的参数进行滑动平均操作
#计算损失函数
cross_entropy = tf.nn.softmax_cross_entropy_with_logits(labels = y_,logits = y)
cross_entropy_mean = tf.reduce_mean(cross_entropy)
loss = cross_entropy_mean+tf.add_n(tf.get_collection("losses"))#这里计算collection里的所有的和。之前把w正则化的值放在了collection里
#对 学习率 进行指数衰减
learning_rate = tf.train.exponential_decay(LEARNING_RATE_BASE,global_step,mnist.train.num_examples/BATCH_SIZE,LEARNING_RATE_DECAY)
#定义训练过程
train_step = tf.train.GradientDescentOptimizer(learning_rate).minimize(loss,global_step=global_step)#每当进行一次训练global_step会加1
#一次进行多个操作,既进行反向传播更新神经网络中的参数,又更新每一个参数的滑动平均值(滑动平均是影子操作)
with tf.control_dependencies([train_step,variable_average_op]):
train_op = tf.no_op(name="train")
#保存操作
saver = tf.train.Saver()
#启动程序
with tf.Session() as sess:
tf.global_variables_initializer().run()
for i in range(TRAIN_STEP):
xs,ys = mnist.train.next_batch(BATCH_SIZE)
reshapeed_xs = np.reshape(xs,(BATCH_SIZE,
mnist_inference.IMAGE_SIZE,
mnist_inference.IMAGE_SIZE,
mnist_inference.NUM_CHANNELS
))
_,loss_value,step = sess.run([train_op,loss,global_step],feed_dict={x:reshapeed_xs,y_:ys})
#每1000轮保存一次模型
if i%1000 ==0:
print "step ",step," ","loss ",loss_value
saver.save(sess,os.path.join(MODEL_SAVE_PATH,MODEL_NAME),global_step = global_step)
def main(argv=None):
mnist = input_data.read_data_sets("/tmp/data",one_hot=True)
train(mnist)
if __name__ =="__main__":
tf.app.run()
3、模型评价,这里涉及到模型的加载
#coding:utf-8
import tensorflow as tf
import time
from tensorflow.examples.tutorials.mnist import input_data
import mnist_inference
import mnist_train
EVAL_INTERVAL_TRAIN = 10
def evaluate(mnist):
with tf.Graph().as_default() as g:
x = tf.placeholder(tf.float32,[None,mnist_inference.INPURT_NODE],name = "x-input")
y_ = tf.placeholder(tf.float32,[None,mnist_inference.OUTPUT_NIDE],name = "y-input")
validfeed = {x:mnist.validation.images,y_:mnist.validation.labels}
y = mnist_inference.inference(x,None)#前向传播,这里不需要对参数使用正则化
corrent_prediction = tf.equal(tf.argmax(y,1),tf.argmax(y_,1))
accuracy = tf.reduce_mean(tf.cast(corrent_prediction,tf.float32))
######################################################################
variable_averages = tf.train.ExponentialMovingAverage(mnist_train.MOVING_AVERAGE_DECAY)
variables_to_restore = variable_averages.variables_to_restore()
saver = tf.train.Saver(variables_to_restore)
####################################################################
with tf.Session() as sess:
ckpt = tf.train.get_checkpoint_state(mnist_train.MODEL_SAVE_PATH)#该函数会自动根据地址找到最新的文件
if ckpt and ckpt.model_checkpoint_path:
#加载模型
saver.restore(sess,ckpt.model_checkpoint_path)
#通过文件名称得到模型保存时迭代的轮数
global_step = ckpt.model_checkpoint_path.split("/")[-1].split("-")[-1]#
accuracy_score = sess.run(accuracy,feed_dict=validfeed)
print "step= ",global_step," accuracy= ",accuracy_score
else:
print "no checkpoint file found"
return
def main(argv=None):
mnist = input_data.read_data_sets("/tmp/data",one_hot=True)
evaluate(mnist)
if __name__ =='__main__':
tf.app.run()