mnist_inference.py
# -*- coding: utf-8 -*-
import tensorflow as tf
'''
mnist_inference.py 定义前向传播过程和神经网络参数
'''
# 神经网络结构参数
INPUT_NODE = 784
OUTPUT_NODE = 10
LAYER1_NODE = 500
# 通过tf.get_variable函数获取变量
def get_weight_var(shape, regularizer):
weights = tf.get_variable(
"weights", shape,
initializer=tf.truncated_normal_initializer(stddev=0.1))
# 将正则化损失加入名为losses的集合
if regularizer != None:
tf.add_to_collection('losses', regularizer(weights))
return weights
# 定义前向传播过程
def inference(input_tensor, regularizer):
# 第一层神经网络
with tf.variable_scope('layer1'):
weights = get_weight_var([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)
# 第二层神经网络
with tf.variable_scope('layer2'):
weights = get_weight_var([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
mnist_train.py
# -*- coding: utf-8 -*-
import os
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
import mnist_inference
'''
mnist_train.py 定义神经网络的训练过程
'''
# 配置神经网络参数
BATCH_SIZE = 100
LEARNING_RATE_BASE = 0.8
LEARNING_RATE_DECAY = 0.99
REGULARIZATION_RATE = 0.0001
TRAINING_STEPS = 30000
MOVING_AVG_DECAY = 0.99
# 模型保存的路径和文件名
MODEL_SAVE_PATH = '/content/saved_model/'
MODEL_NAME = 'model.ckpt'
def train(mnist):
# 定义输入输出
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
regularizer = tf.contrib.layers.l2_regularizer(REGULARIZATION_RATE)
y = mnist_inference.inference(x, regularizer)
global_step = tf.Variable(0, trainable=False)
# 滑动平均操作
var_averages = tf.train.ExponentialMovingAverage(
MOVING_AVG_DECAY, global_step)
var_averages_op = var_averages.apply(tf.trainable_variables())
# 定义损失函数
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'))
# 定义学习率
learning_rate = tf.train.exponential_decay(
LEARNING_RATE_BASE,
global_step,
mnist.train.num_examples / BATCH_SIZE,
LEARNING_RATE_DECAY)
# 定义优化算法
train_step = tf.train.GradientDescentOptimizer(learning_rate).minimize(
loss, global_step=global_step)
# 反向传播同时更新神经网络参数及其滑动平均值
with tf.control_dependencies([train_step, var_averages_op]):
train_op = tf.no_op(name='train')
# 初始化tf持久化类
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)
_, loss_value, step = sess.run(
[train_op, loss, global_step], feed_dict={x: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)
def main(argv=None):
mnist = input_data.read_data_sets("/tmp/data", one_hot=True)
train(mnist)
if __name__ == '__main__':
tf.app.run()
mnist_eval.py
# -*- coding: utf-8 -*-
import tensorflow as tf
import time
from tensorflow.examples.tutorials.mnist import input_data
import mnist_inference
import mnist_train
'''
mnist_eval.py 定义模型的测试过程
'''
# 每10s加再一次最新的模型,测试准确率
EVAL_INTERVAL_SECS = 10
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}
# 前向传播,正则化项为None
y = mnist_inference.inference(x, None)
# 计算正确率
correct_prediction = tf.equal(tf.argmax(y, 1), tf.argmax(y_, 1))
accuracy = tf.reduce_mean(
tf.cast(correct_prediction, tf.float32))
# 通过变量重命名来加载模型
var_averages = tf.train.ExponentialMovingAverage(
mnist_train.MOVING_AVG_DECAY)
var_to_restore = var_averages.variables_to_restore()
saver = tf.train.Saver(var_to_restore)
# 每隔一段时间检验一次正确率
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)
# 通过文件名获取模型保存时的训练轮数
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("/tmp/data", one_hot=True)
evaluate(mnist)
if __name__ == '__main__':
tf.app.run()
以上。