经典卷积网络模型LeNet-5模型来解决MNIST数字识别问题(主要解决验证集正确率低的问题)
程序员文章站
2022-04-30 20:12:48
...
LeNet-5模型不是重点,重点是我当时遇到的问题,不知道你遇到了没?是不是发现你训练的正确率跟书本上或者正常情况下的相差甚远,尤其是在验证集上的正确率我当时才0.1,而我参考的那本书(《TensorFlow实战Google深度学习框架》)上的正确率是0.99!
解决办法:当时网上查找原因,下面这篇博客https://blog.csdn.net/wangdong2017/article/details/90176323说的很详细。但是没能解决。我的解决办法是调学习率,简单粗暴的办法。将mnist_train.py中的基础学习率修改为LEARNING_RATE_BASE = 0.01就OK啦。
这个模型很老了,我这里直接上代码吧!
mnist_inference.py中的代码:
import tensorflow as tf
#定义神经网络的相关参数
INPUT_NODE = 784
OUTPUT_NODE = 10
IMAGE_SIZE = 28
NUM_CHANNELS = 1
NUM_LABELS = 10
#第一层卷积层的尺寸和深度
CONV1_DEEP = 32
CONV1_SIZE = 5
#第二层卷积层的深度和尺寸
CONV2_DEEP = 64
CONV2_SIZE = 5
#全连接层的节点个数
FC_SIZE = 512
# def get_weight_variable(shape,regularizer):
# weights = tf.get_variable('weights',shape,
# initializer=tf.truncated_normal_initializer(stddev=0.1))
# if regularizer != None:
# tf.add_to_collection('losses',regularizer(weights))
# return weights
#定义卷积神经网络的前向传播过程,这里新添加了一个参数train用于区分训练过程和测试过程
def inference(input_tensor,train,regularizer):
#声明第一层卷积层的变量并实现前向传播的过程。
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(
'biases',[CONV1_DEEP],initializer=tf.constant_initializer(0.0))
#使用边长为5,深度为32的过滤器,过滤器移动步长为1,使用全零填充
conv1 = tf.nn.conv2d(
input_tensor,conv1_weights,strides=[1,1,1,1],padding="SAME")
reul1 = tf.nn.relu(tf.nn.bias_add(conv1,conv1_biases))
#类似的声明第二层池化层的前向传播过程。
#选用最大池化层,池化过滤器的边长为2,全零填充,步长为2。
with tf.name_scope('layer2-pool1'):
pool1 = tf.nn.max_pool(
reul1,ksize=[1,2,2,1],strides=[1,2,2,1],padding="SAME")
#声明第三层卷积层的变量并实现前向传播过程。
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))
#使用边长为5,深度为64的过滤器,过滤器移动步长为1,使用全零填充
conv2 = tf.nn.conv2d(pool1,conv2_weights,strides=[1,1,1,1],padding='SAME')
relu2 = tf.nn.relu(tf.nn.bias_add(conv2,conv2_biases))
#实现第四层 池化层的前向传播过程。这一层和第二层的结构一样
with tf.name_scope('layer4-pool2'):
pool2 = tf.nn.max_pool(relu2,ksize=[1,2,2,1],strides=[1,2,2,1],padding='SAME')
#第5层为全连接层,将第四层的池化层的输出转化为第5层的输入格式。
#第四层是7*7*64的矩阵 第5层是输入格式为向量,需要将第四层的矩阵拉成向量
pool_shape = pool2.get_shape().as_list()
#pool_shape[0]为一个batch中数据的个数
nodes = pool_shape[1]*pool_shape[2]*pool_shape[3]
#通过tf.reshape函数将第四层变成一个batch的向量
reshaped = tf.reshape(pool2,[pool_shape[0],nodes])
#声明第5层全连接层的变量并实现前向传播的过程
with tf.variable_scope('layer5-fc1'):
fc1_weights = tf.get_variable(
'weight',[nodes,FC_SIZE],
initializer=tf.truncated_normal_initializer(stddev=0.1))
#只有全连接层的权值需要加入正则化
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(reshaped,fc1_weights) + fc1_biases)
if train:
fc1 = tf.nn.dropout(fc1,0.5)
#声明第六层全连接层的变量并实现前向传播的过程
with tf.variable_scope('layer6-fc2'):
fc2_weights = tf.get_variable(
'weight', [FC_SIZE, NUM_LABELS],
initializer=tf.truncated_normal_initializer(stddev=0.1))
# 只有全连接层的权值需要加入正则化
if regularizer != None:
tf.add_to_collection('losses', regularizer(fc2_weights))
fc2_biases = tf.get_variable(
'bias', [NUM_LABELS], initializer=tf.constant_initializer(0.1))
logit = tf.matmul(fc1,fc2_weights)+fc2_biases
#返回第六层的输出
return logit
mnist_train.py中的代码:
import tensorflow as tf
import numpy as np
import os
from tensorflow.examples.tutorials.mnist import input_data
#加载mnist_inference.py中定义的常量和前向传播的函数
import mnist_inference
#配置神经网络的参数
BATCH_SIZE = 100
LEARNING_RATE_BASE = 0.01
LEARNING_RATE_DECAY = 0.99
REGULARAZTION_RATE = 0.0001
TRAINING_STEPS = 30000
MOVING_AVERAGE_DECAY = 0.99
#模型保存的路径和文件名
MODEL_SAVE_PATH = 'model'
MODEL_NAME = 'model.ckpt'
def train(mnist):
#将处理的输入数据的计算都放在名字为input的命名空间下
with tf.name_scope('input'):
#定义输入输出placeholder
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_NODE],name='y-input')
regularizer = tf.contrib.layers.l2_regularizer(REGULARAZTION_RATE)#L2正则化
#直接使用mnsit_inference中定义的前向传播过程
y = mnist_inference.inference(x,True,regularizer)
global_step = tf.Variable(0,trainable=False)
#定义损失函数、学习率、滑动平均操作及训练过程
#将处理滑动平均相关的计算都放在moving_average的命名空间下
with tf.name_scope('moving_average'):
variable_averages = tf.train.ExponentialMovingAverage(
MOVING_AVERAGE_DECAY,global_step)
variable_averages_op = variable_averages.apply(tf.trainable_variables())
#将计算损失函数相关的计算放在名为loss_function的命名空间下
with tf.name_scope('loss_function'):
cross_entropy = tf.nn.sparse_softmax_cross_entropy_with_logits(
logits=y,labels=tf.argmax(y_,1))
cross_entropy_mean = tf.reduce_mean(cross_entropy)
loss = cross_entropy_mean + tf.add_n(tf.get_collection('losses'))
#将剩下的放在'train_step'
with tf.name_scope('train_step'):
learning_rate = tf.train.exponential_decay(
LEARNING_RATE_BASE,
global_step,
mnist.train.num_examples / BATCH_SIZE,
LEARNING_RATE_DECAY
)
train_step = tf.train.GradientDescentOptimizer(learning_rate).minimize(
loss,global_step=global_step)
with tf.control_dependencies([train_step,variable_averages_op]):
train_op = tf.no_op(name='train')
#初始化TensorFlow持久化层
saver = tf.train.Saver()
with tf.Session() as sess:
tf.global_variables_initializer().run()
for i in range(TRAINING_STEPS):
xs,ys = mnist.train.next_batch(BATCH_SIZE)
reshaped_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:reshaped_xs,y_:ys})
#每1000轮保存一次模型
if i%1000 == 0:
print('After %d training step(s),loss on training batch is %g.'%(step,loss_value))
saver.save(sess,os.path.join(MODEL_SAVE_PATH,MODEL_NAME),global_step=global_step)
#将当前的计算图输出到TensorBoard日志文件
writer = tf.summary.FileWriter('log',tf.get_default_graph())
writer.close()
def main(argv = None):
mnsit = input_data.read_data_sets('mnsit_data',one_hot=True)
train(mnsit)
if __name__ == '__main__':
tf.app.run()
mnist_eval.py中的代码:
import tensorflow as tf
import time
import numpy as np
from tensorflow.examples.tutorials.mnist import input_data
#加载mnist_inference.py中定义的常量和前向传播的函数
import mnist_inference
import mnist_train
#每10秒加载一次最新的模型,并在测试集上测试最新模型的正确率
EVAL_INTERVAL_SECS = 10
def evaluate(mnist):
with tf.Graph().as_default() as g:
#定义输入输出placeholder
x = tf.placeholder(tf.float32,
[mnist.validation.images.shape[0],
mnist_inference.IMAGE_SIZE,
mnist_inference.IMAGE_SIZE,
mnist_inference.NUM_CHANNELS],
name='x-input')
# x = tf.placeholder(
# tf.float32,[None,mnist_inference.INPUT_NODE],name='x-input'
# )
y_ = tf.placeholder(tf.float32,[None,mnist_inference.OUTPUT_NODE],name='y-input')
xs = mnist.validation.images
reshaped_xs = np.reshape(xs,[mnist.validation.images.shape[0],
mnist_inference.IMAGE_SIZE,
mnist_inference.IMAGE_SIZE,
mnist_inference.NUM_CHANNELS])
validate_feed = {x:reshaped_xs,
y_:mnist.validation.labels}
#直接使用mnsit_inference中定义的前向传播过程
y = mnist_inference.inference(x,None,None)
#使用前向传播的结果计算正确率。如果需要对未知的样例进行分类,那么使用
#tf.argmax(y,1)就可以得到输入样例的预测类别
correct_prediction = tf.equal(tf.argmax(y,1),tf.argmax(y_,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction,tf.float32))
#定义损失函数、学习率、滑动平均操作及训练过程
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)
if ckpt and ckpt.model_checkpoint_path:
#加载模型
saver.restore(sess,ckpt.model_checkpoint_path)
#通过文件名得到当时迭代的轮数
global_step = ckpt.model_checkpoint_path.split('/')[-1].split('-')[-1]
accuracy_score = sess.run(accuracy,feed_dict=validate_feed)
print('After %s training step(s),validation accuracy= %g.'%(global_step,accuracy_score))
else:
print('No checkpoint file found')
return
#每隔10秒调用一次计算正确率以检测训练过程中正确率的变化
# while True:
# with tf.Session() as sess:
# ckpt = tf.train.get_checkpoint_state(mnist_train.MODEL_SAVE_PATH)
# if ckpt and ckpt.model_checkpoint_path:
# #加载模型
# saver.restore(sess,ckpt.model_checkpoint_path)
# #通过文件名得到当时迭代的轮数
# global_step = ckpt.model_checkpoint_path.split('/')[-1].split('-')[-1]
# accuracy_score = sess.run(accuracy,feed_dict=validate_feed)
#
# print('After %s training step(s),validation accuracy= %g.'%(global_step,accuracy_score))
# else:
# print('No checkpoint file found')
# return
# time.sleep(EVAL_INTERVAL_SECS)
def main(argv = None):
mnsit = input_data.read_data_sets('mnsit_data',one_hot=True)
evaluate(mnsit)
if __name__ == '__main__':
tf.app.run()
下面是我的文件结构: