TensorFlow使用经典卷积神经网络实现对手写数字mnist的训练和测试
两个卷积,两个池化,两个全连接层。
代码如下:(在上一篇的基础上更改网络lenet5)
代码分为3部分,网络-训练和测试
# -*- coding: utf-8 -*-
"""
Created on Tue Jul 25 10:04:39 2017
@author: mnist_inference.py
"""
import tensorflow as tf
#配置神经网络的参数
INPUT_NODE = 784
OUTPUT_NODE = 10
IMAGE_SIZE = 28
NUM_CHANNELS = 1
NUM_LABELS = 10
#第一层卷积层的尺寸的深度
CONV1_DEEP = 32
CONV1_SIZE = 5
#第二层卷积层的尺寸和深度
CONV2_DEEP = 64
CONV2_SIZE = 5
#全连接层的节点个数
FC_SIZE = 512
#定义卷积神经网络前向传播过程
def inference(input_tensor, train, regularizer):
#声明第一层神经网络的变量并完成前向传播过程
with tf.variable_scope('layer1-conv1'):
conv1_weights = tf.get_variable("weights", [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))
#使用边长为5, 深度为32的过滤器, 过滤器的移动步长是1, 且使用全零填充。
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))
#实现第二层池化层的前向传播过程
#使用全零填充,移动的步长为2,这一层的输入是上一层的输出,也就是28*28*32
with tf.name_scope('layer2-pool1'):
pool1 = tf.nn.max_pool(relu1, ksize=[1,2,2,1],strides=[1,2,2,1],padding='SAME')
#声明第三层的卷积变量并实现前向传播过程。这一层的输入为14*14*32的矩阵
with tf.variable_scope('layer3-conv2'):
conv2_weighs = tf.get_variable('weights',[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, 步长为1, 且使用全零填充
conv2 = tf.nn.conv2d(pool1, conv2_weighs, 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
#这一层的输入是14*14*64的矩阵,输出是7*7*64的矩阵
with tf.name_scope('layer4-pool2'):
pool2 = tf.nn.max_pool(relu2, ksize=[1,2,2,1], strides=[1,2,2,1], padding='SAME')
#将第四层池化层的输出转化为第五层全连接层的输入格式
pool_shape = pool2.get_shape().as_list()
#计算将矩阵拉直成向量的长度
nodes = pool_shape[1]*pool_shape[2]*pool_shape[3]
#变成一个batch 的向量
reshaped = tf.reshape(pool2, [pool_shape[0], nodes])
#声明第五层全连接层的变量并实现前向传播过程
with tf.variable_scope('layer5-fc1'):
fc1_weights = tf.get_variable("weights", [nodes,FC_SIZE],
initializer=tf.truncated_normal_initializer(stddev=0.1))
#只有全连接层的权重需要加入正则化
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过程
with tf.variable_scope('layer6-fc2'):
fc2_weights = tf.get_variable('weights', [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(0.1))
logit = tf.matmul(fc1,fc2_weights)+fc2_biases
#返回最后前向传播的结果
return logit
# -*- coding: utf-8 -*-
"""
Created on Tue Jul 25 14:00:16 2017
@author: mnist_train.py
"""
import os
import tensorflow as tf
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
#配置神经网络的参数
BATCH_SIZE = 100
LEARNING_RATE_BASE = 0.05
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 = r"C:\Users\alienware\Desktop\mnist3\ckpt"
MODEL_NAME = "model.ckpt"
def train(mnist):
#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)
#前向传播
y = mnist_inference.inference(x, True,regularizer)
global_step = tf.Variable(0, trainable=False)
#定义损失函数、学习率、滑动平滑操作以及训练过程
variable_averages = tf.train.ExponentialMovingAverage(MOVING_AVERAGE_DECAY, global_step)
variable_averages_op = variable_averages.apply(tf.trainable_variables())
cross_entropy = tf.nn.sparse_softmax_cross_entropy_with_logits(logits=y, labels=tf.arg_max(y_,1))
cross_entropy_mean = tf.reduce_mean(cross_entropy)
loss = cross_entropy_mean + tf.add_n(tf.get_collection('losses'))
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tensor持久化类
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)
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:
#输出当前的训练情况
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)
def main(argv=None):
mnist = input_data.read_data_sets(r"F:\Tensor\MNIST_data", one_hot=True)
train(mnist)
if __name__ == '__main__':
tf.app.run()
训练的结果为:
Extracting F:\Tensor\MNIST_data\train-images-idx3-ubyte.gz
Extracting F:\Tensor\MNIST_data\train-labels-idx1-ubyte.gz
Extracting F:\Tensor\MNIST_data\t10k-images-idx3-ubyte.gz
Extracting F:\Tensor\MNIST_data\t10k-labels-idx1-ubyte.gz
WARNING:tensorflow:From C:/Users/alienware/Desktop/mnist3/mnist_train.py:55: initialize_all_variables (from tensorflow.python.ops.variables) is deprecated and will be removed after 2017-03-02.
Instructions for updating:
Use `tf.global_variables_initializer` instead.
After 1 training step(s), loss on training batch is 5.18155.
After 1001 training step(s), loss on training batch is 0.689416.
After 2001 training step(s), loss on training batch is 0.676516.
# -*- coding: utf-8 -*-
"""
Created on Wed Jul 26 13:58:24 2017
@author: mnist_eval.py
"""
import time
import tensorflow as tf
import numpy as np
from tensorflow.examples.tutorials.mnist import input_data
#加载mnist_inference.py和mnist_train.py中定义的常量和函数
import mnist_inference
import mnist_train
#每10秒加载一次最新的模型, 并在测试数据上测试最新的正确率
EVAL_INTERVAL_SECS = 10
BATCH_SIZE = 1000
def evaluate(mnist):
with tf.Graph().as_default() as g:
#定义输入输出的格式
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')
xs = mnist.validation.images[:1000]
reshaped_xs = np.reshape(xs, [BATCH_SIZE, mnist_inference.IMAGE_SIZE, mnist_inference.IMAGE_SIZE, mnist_inference.NUM_CHANNELS])
validate_feed = {x:reshaped_xs,
y_:mnist.validation.labels[:1000]}
#前向传播
y = mnist_inference.inference(x,False,None)
#使用前向传播的结果计算正确率
correct_prediction = tf.equal(tf.arg_max(y,1), tf.arg_max(y_,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
#通过变量重命名的方式来加载模型
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)
#每隔EVAL_INTERVAL_SECS秒调用一次计算正确率的过程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=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):
mnist = input_data.read_data_sets(r"F:\Tensor\MNIST_data", one_hot=True)
evaluate(mnist)
if __name__ == '__main__':
tf.app.run()
测试的结果为:
Extracting F:\Tensor\MNIST_data\train-images-idx3-ubyte.gz
Extracting F:\Tensor\MNIST_data\train-labels-idx1-ubyte.gz
Extracting F:\Tensor\MNIST_data\t10k-images-idx3-ubyte.gz
Extracting F:\Tensor\MNIST_data\t10k-labels-idx1-ubyte.gz
INFO:tensorflow:Restoring parameters from C:\Users\alienware\Desktop\mnist3\ckpt\model.ckpt-2001
After 2001 training step(s), validation accuracy = 0.984
INFO:tensorflow:Restoring parameters from C:\Users\alienware\Desktop\mnist3\ckpt\model.ckpt-2001
After 2001 training step(s), validation accuracy = 0.984