MNIST数据集下载链接:
http://yann.lecun.com/exdb/mnist/
Tensorflow实现LeNet-5
下面给出一个Tensorflow的程序来实现一个类似LeNet-5模型的卷积神经网络来解决MNIST数字识别问题。
LeNet_inference.py
# _*_ coding: utf-8 _*_
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
# 第一个卷积层的尺寸和深度
CONV1_DEEP = 32
CONV1_SIZE = 5
# 第二个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
# 定义卷积神经网络的前向传播过程。这里添加了一个新的参数train,用于区别训练过程和测试过程。在这个程序中将用到dropout方法
# dropout可以进一步提升模型可靠性并防止过拟合(dropout过程只在训练时使用)
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.name_scope('layer2-pool1'):
pool1 = tf.nn.max_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(pool1,conv2_weights, strides=[1, 1, 1, 1], padding='SAME')
relu2 = tf.nn.relu(tf.nn.bias_add(conv2, conv2_biases))
with tf.name_scope('layer4-pool2'):
pool2 = tf.nn.max_pool(relu2, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME')
pool2_shape = pool2.get_shape().as_list()
nodes = pool2_shape[1] * pool2_shape[2] * pool2_shape[3]
reshaped = tf.reshape(pool2, [pool2_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(0.0))
fc1 = tf.nn.relu(tf.matmul(reshaped, fc1_weights) + fc1_biases)
if train:
fc1 = tf.nn.dropout(fc1, 0.5)
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
LeNet5_train.py
# _*_ coding: utf-8 _*_
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 LeNet_inference
# 配置神经网络的参数
BATCH_SIZE = 100
LEARNING_RATE_BASE = 0.1
LEARNING_RATE_DECAY = 0.99
REGULARAZTION_RATE = 0.0001
TRAIN_STEPS = 30000
MOVING_AVERAGE_DECAY = 0.99
MODEL_SAVE_PATH = "./model/"
MODEL_NAME = "model3.ckpt"
def train(mnist):
x = tf.placeholder(tf.float32, [BATCH_SIZE, LeNet_inference.IMAGE_SIZE,
LeNet_inference.IMAGE_SIZE,
LeNet_inference.NUM_CHANNELS], name='x-input')
y_ = tf.placeholder(tf.float32, [None, LeNet_inference.OUTPUT_NODE], name='y-input')
regularizer = tf.contrib.layers.l2_regularizer(REGULARAZTION_RATE)
y = LeNet_inference.inference(x, train, regularizer)
global_step = tf.Variable(0, trainable=False)
variable_average = tf.train.ExponentialMovingAverage(MOVING_AVERAGE_DECAY, global_step)
variable_average_op = variable_average.apply(
tf.trainable_variables())
cross_entropy = tf.nn.sparse_softmax_cross_entropy_with_logits(labels=tf.argmax(y_, 1), logits=y)
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=global_step, decay_steps=mnist.train.num_examples / BATCH_SIZE,
decay_rate=LEARNING_RATE_DECAY)
train_step = tf.train.GradientDescentOptimizer(learning_rate).minimize(loss, global_step=global_step)
with tf.control_dependencies([train_step, variable_average_op]):
train_op = tf.no_op(name='train')
saver = tf.train.Saver()
with tf.Session() as sess:
tf.global_variables_initializer().run()
for i in range(TRAIN_STEPS):
xs, ys = mnist.train.next_batch(BATCH_SIZE)
xs = np.reshape(xs, [BATCH_SIZE, LeNet_inference.IMAGE_SIZE,
LeNet_inference.IMAGE_SIZE,
LeNet_inference.NUM_CHANNELS])
_, loss_value, step = sess.run([train_op, loss, global_step], feed_dict={x: xs, y_: ys})
if i % 1000 == 0:
print("After %d training steps, 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("E:\科研\TensorFlow教程\MNIST_data", one_hot=True)
train(mnist)
if __name__ == '__main__':
tf.app.run()
LeNet5_Predict.py
import time
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
import numpy as np
import LeNet_inference
import LeNet5_Train
from PIL import Image
EVAL_INTERVAL_SECS=10
BATCH_SIZE=1
def evaluate(mnist):
with tf.Graph().as_default() as g:
x = tf.placeholder(tf.float32, [BATCH_SIZE, LeNet_inference.IMAGE_SIZE, LeNet_inference.IMAGE_SIZE,
LeNet_inference.NUM_CHANNELS], name='x-input')
y_ = tf.placeholder(tf.float32, [BATCH_SIZE, LeNet_inference.OUTPUT_NODE], name='y-input')
img=Image.open('test.bmp')
x_img_array=np.float32(np.asarray(img))/255.0
reshape_img=np.reshape(x_img_array,[1,28,28,1])
xs, ys = mnist.validation.next_batch(BATCH_SIZE)
validate_feed={x:reshape_img}
y=LeNet_inference.inference(x,False,None)
num = tf.argmax(y, 1)
variable_averages=tf.train.ExponentialMovingAverage(LeNet5_Train.MOVING_AVERAGE_DECAY)
variable_to_restore=variable_averages.variables_to_restore()
saver = tf.train.Saver(variable_to_restore)
sess=tf.Session()
with sess.as_default():
ckpt = tf.train.get_checkpoint_state(LeNet5_Train.MODEL_SAVE_PATH)
if ckpt and ckpt.model_checkpoint_path:
saver.restore(sess, ckpt.model_checkpoint_path)
while True:
with sess.as_default():
addr=input('input your image address: ')
img = Image.open(addr)
x_img_array = np.float32(np.asarray(img)) / 255.0
reshape_img = np.reshape(x_img_array, [1, 28, 28, 1])
validate_feed = {x: reshape_img}
y_value, result = sess.run([y, num], feed_dict=validate_feed)
print('the result is ', result[0])
def main (argv=None):
mnist=input_data.read_data_sets("MNIST_data\\",one_hot=True)
evaluate(mnist)
if __name__=='__main__':
tf.app.run()