手寫數字識別是入門的教程,利用這個學習一下深度學習原理以及tensorflow的使用
1、前向過程 mnist_inference.py
#coding:utf-8
import tensorflow as tf
#定義神經網絡結構相關的參數
INPURT_NODE = 784
OUTPUT_NIDE = 10
IMAGE_SIZE = 28
NUM_CHANNELS = 1
NUM_LABELS = 10
#第一層卷積層的尺寸和深度
CONV1_SIZE = 5
CONV1_DEEP = 32
#第二層的卷積層的尺寸和深度
CONV2_SIZE = 5
CONV2_DEEP = 64
#全連接層的節點個數
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)
#一般只在全連接層進行dropout操作,而不在卷積層或者池化層
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、進行訓練,誤差反向傳播tensorflow內部自動求解,mnsit_train.py,這裏涉及到模型的保存
#coding:utf-8
import tensorflow as tf
import os
from tensorflow.examples.tutorials.mnist import input_data
#加載剛剛些的前向傳播過程
import mnist_inference
#配置神經網絡的參數
BATCH_SIZE = 100
LEARNING_RATE_BASE = 0.8#指數衰減基礎學習率
LEARNING_RATE_DECAY = 0.99#衰減率
REGULARAZTION_RATE = 0.0001#正則化的權重
TRAIN_STEP = 30000
MOVING_AVERAGE_DECAY = 0.99#滑動平均率
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)#設置global_step爲不可訓練數值,在訓練過程中它不進行相應的更新
#對w,b進行滑動平均操作
variable_average = tf.train.ExponentialMovingAverage(MOVING_AVERAGE_DECAY,global_step)#對滑動平均函數進行輸入滑動平均率以及步數
variable_average_op = variable_average.apply(tf.trainable_variables())#對所以可訓練的參數進行滑動平均操作
#計算損失函數
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"))#這裏計算collection裏的所有的和。之前把w正則化的值放在了collection裏
#對 學習率 進行指數衰減
learning_rate = tf.train.exponential_decay(LEARNING_RATE_BASE,global_step,mnist.train.num_examples/BATCH_SIZE,LEARNING_RATE_DECAY)
#定義訓練過程
train_step = tf.train.GradientDescentOptimizer(learning_rate).minimize(loss,global_step=global_step)#每當進行一次訓練global_step會加1
#一次進行多個操作,既進行反向傳播更新神經網絡中的參數,又更新每一個參數的滑動平均值(滑動平均是影子操作)
with tf.control_dependencies([train_step,variable_average_op]):
train_op = tf.no_op(name="train")
#保存操作
saver = tf.train.Saver()
#啓動程序
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輪保存一次模型
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、模型評價,這裏涉及到模型的加載
#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)#前向傳播,這裏不需要對參數使用正則化
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)#該函數會自動根據地址找到最新的文件
if ckpt and ckpt.model_checkpoint_path:
#加載模型
saver.restore(sess,ckpt.model_checkpoint_path)
#通過文件名稱得到模型保存時迭代的輪數
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()