Tensorflow-MNIST数字识别练习代码

Tensorflow-MNIST数字识别练习代码

方案一 训练代码 + 验证代码

# -- coding: utf-8 --

import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data

#层节点
INPUT_NODE =
4000
784
LAYER1_NODE = 500
OUTPUT_NODE = 10

#数据batch大小
BATCH_SIZE = 100

#训练参数
LEARNING_RATE_BASE = 0.8
LEARNING_RATE_DECAY = 0.99
REGULARIZATION_RATE= 0.0001
TRAINING_STEPS = 30000
MOVING_AVERAGE_DECAY = 0.99

#前向传播函数
def inference(input_tensor, avg_class, weights1, biases1, weights2, biases2):
if avg_class == None:
layer1 = tf.nn.relu(tf.matmul(input_tensor, weights1) + biases1)
return tf.matmul(layer1, weights2) + biases2
else:
layer1 = tf.nn.relu(tf.matmul(input_tensor,avg_class.average(weights1))+avg_class.average(biases1))
return tf.matmul(layer1, avg_class.average(weights2)) + avg_class.average(biases2)

def train(mnist):
#输入层和数据label
x = tf.placeholder(tf.float32, [None, INPUT_NODE], name='x-input')
y_ = tf.placeholder(tf.float32, [None,OUTPUT_NODE], name='y-input')

#隐藏层参数初始化
weights1 = tf.Variable(tf.truncated_normal([INPUT_NODE,LAYER1_NODE], stddev=0.1))
biases1 = tf.Variable(tf.constant(0.1, shape=[LAYER1_NODE]))

#输出层参数初始化
weights2 = tf.Variable(tf.truncated_normal([LAYER1_NODE, OUTPUT_NODE], stddev=0.1))
biases2 = tf.Variable(tf.constant(0.1, shape=[OUTPUT_NODE]))

#前向传播结果y
y = inference(x, None, weights1, biases1, weights2, biases2)

#use for count the train step , trainable=False
global_step = tf.Variable(0, trainable=False)

#滑动平均模型，及加入滑动平均的前向传播结果average_y
variable_averages = tf.train.ExponentialMovingAverage(MOVING_AVERAGE_DECAY, global_step)
variables_averages_op = variable_averages.apply(tf.trainable_variables())
average_y = inference(x, variable_averages, weights1, biases1, weights2, biases2)

#计算交叉熵，并加入正则-->损失函数loss
cross_entropy = tf.nn.softmax_cross_entropy_with_logits(labels=y_,logits=y)
cross_entropy_mean = tf.reduce_mean(cross_entropy)
regularizer = tf.contrib.layers.l2_regularizer(REGULARIZATION_RATE)
regularization = regularizer(weights1) + regularizer(weights2)
loss = cross_entropy_mean + regularization
#学习率
learning_rate = tf.train.exponential_decay(LEARNING_RATE_BASE,global_step,mnist.train.num_examples/BATCH_SIZE,LEARNING_RATE_DECAY)
#train_step 梯度下降(学习率，损失函数，全局步数)
train_step = tf.train.GradientDescentOptimizer(learning_rate).minimize(loss, global_step=global_step)
#运算图控制，用train_op作集合
with tf.control_dependencies([train_step, variables_averages_op]):
train_op = tf.no_op(name='train')
#判断准确率
correct_prediction = tf.equal(tf.argmax(y,1),tf.argmax(y_,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction,tf.float32))

#持久化
saver = tf.train.Saver()

with tf.Session() as sess:
tf.initialize_all_variables().run()
validate_feed = {x:mnist.validation.images,y_:mnist.validation.labels}
test_feed = {x:mnist.test.images,y_:mnist.test.labels}

for i in range(TRAINING_STEPS):
#每1000轮测试一次
if i%1000 == 0:
validate_acc = sess.run(accuracy, feed_dict=validate_feed)
print("After %d training step(s), validation accuracy using average model is %g " %(i,validate_acc))

xs,ys = mnist.train.next_batch(BATCH_SIZE)
sess.run(train_op, feed_dict={x:xs, y_:ys})
saver.save(sess,"./model/model.ckpt")
test_acc = sess.run(accuracy, feed_dict=test_feed)
print("After %d training step(s), test accuracy using average model is %g" %(TRAINING_STEPS, test_acc))

def main(argv=None):
mnist = input_data.read_data_sets("mnist_data/", one_hot=True)
train(mnist)

if __name__== '__main__':
tf.app.run()

方案二 训练 + 验证代码

文件 mnis_inference.py

# -- coding: utf-8 --

import tensorflow as tf

#层节点
INPUT_NODE = 784
LAYER1_NODE = 500
OUTPUT_NODE = 10

#获取权值weights
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))
print("test_test")

return weights

#前向传播函数
def inference(input_tensor, regularizer):
#layer1
with tf.variable_scope('layer1'):
weights = get_weight_variable([INPUT_NODE, LAYER1_NODE], regularizer)
biases = tf.get_variable("biases", [LAYER1_NODE], initializer=tf.constant_initializer(0.0))
layer1 = tf.nn.relu(tf.matmul(input_tensor, weights) + biases)
#layer2
with tf.variable_scope('layer2'):
weights = get_weight_variable([LAYER1_NODE, OUTPUT_NODE], regularizer)
biases = tf.get_variable("biases", [OUTPUT_NODE], initializer=tf.constant_initializer(0.0))
layer2 = tf.matmul(layer1, weights) + biases
return layer2

文件 mnist_train.py
# -- coding: utf-8 --

import os

import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data

import mnist_inference

#数据batch大小
BATCH_SIZE = 100

#训练参数
LEARNING_RATE_BASE = 0.8
LEARNING_RATE_DECAY = 0.99
REGULARIZATION_RATE= 0.0001
TRAINING_STEPS = 30000
MOVING_AVERAGE_DECAY = 0.99

#模型保存路径及文件名
MODEL_SAVE_PATH = "/model2/"
MODEL_NAME = "model.ckpt"

def train(mnist):
#输入层和数据label
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')

#前向传播结果y
regularizer = tf.contrib.layers.l2_regularizer(REGULARIZATION_RATE)
y = mnist_inference.inference(x, regularizer)
global_step = tf.Variable(0, trainable=False)

#滑动平均模型
variable_averages = tf.train.ExponentialMovingAverage(MOVING_AVERAGE_DECAY, global_step)
variables_averages_op = variable_averages.apply(tf.trainable_variables())

#计算交叉熵，并加入正则-->损失函数loss
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'))
#学习率
learning_rate = tf.train.exponential_decay(LEARNING_RATE_BASE,global_step,mnist.train.num_examples/BATCH_SIZE,LEARNING_RATE_DECAY)
#train_step 梯度下降(学习率，损失函数，全局步数)
train_step = tf.train.GradientDescentOptimizer(learning_rate).minimize(loss, global_step=global_step)
#运算图控制，用train_op作集合
with tf.control_dependencies([train_step, variables_averages_op]):
train_op = tf.no_op(name='train')

#持久化
saver = tf.train.Saver()

with tf.Session() as sess:
tf.initialize_all_variables().run()

for i in range(TRAINING_STEPS):
xs, ys = mnist.train.next_batch(BATCH_SIZE)
_, loss_value, step = sess.run([train_op, loss, global_step], feed_dict={x:xs, y_:ys})
#每1000轮保存一次
if i%1000 == 0:
print("After %d training step(s), loss on training batch is %g " %(step, loss_value))
saver.save(sess, "./model2/model.ckpt")

def main(argv=None):
mnist = input_data.read_data_sets("mnist_data/", one_hot=True)
train(mnist)

if __name__== '__main__':
tf.app.run()

文件 mnist_eval.py
# -- coding: utf-8 --

import os
import time

import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data

import mnist_inference
import mnist_train

EVAL_INTERVAL_SECS = 10

#模型保存路径及文件名
MODEL_SAVE_PATH = "/model2/"
MODEL_NAME = "model.ckpt"

def evaluate(mnist):
with tf.Graph().as_default() as g:
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')
validate_feed = {x: mnist.validation.images, y_ :mnist.validation.labels}

y = mnist_inference.inference(x, None)

correct_prediction = tf.equal(tf.argmax(y, 1), tf.argmax(y_, 1))
accuracy = tf.reduce_mean(tf.cast(correct_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:
saver.restore(sess, "./model2/model.ckpt")

accuracy_score = sess.run(accuracy, feed_dict=validate_feed)
print("**********accuracy = %g", accuracy_score)

def main(argv=None):
mnist = input_data.read_data_sets("mnist_data/", one_hot=True)
evaluate(mnist)

if __name__== '__main__':
tf.app.run()