Tensorflow训练MNIST手写数字识别模型

本文实例为大家分享了Tensorflow训练MNIST手写数字识别模型的具体代码，供大家参考，具体内容如下

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

INPUT_NODE = 784  # 输入层节点=图片像素=28x28=784
OUTPUT_NODE = 10  # 输出层节点数=图片类别数目

LAYER1_NODE = 500  # 隐藏层节点数，只有一个隐藏层
BATCH_SIZE = 100  # 一个训练包中的数据个数，数字越小
# 越接近随机梯度下降，越大越接近梯度下降

LEARNING_RATE_BASE = 0.8   # 基础学习率
LEARNING_RATE_DECAY = 0.99  # 学习率衰减率

REGULARIZATION_RATE = 0.0001  # 正则化项系数
TRAINING_STEPS = 30000     # 训练轮数
MOVING_AVG_DECAY = 0.99    # 滑动平均衰减率

# 定义一个辅助函数，给定神经网络的输入和所有参数，计算神经网络的前向传播结果
def inference(input_tensor, avg_class, weights1, biases1,
weights2, biases2):

# 当没有提供滑动平均类时，直接使用参数当前取值
if avg_class == None:
# 计算隐藏层前向传播结果
layer1 = tf.nn.relu(tf.matmul(input_tensor, weights1) + biases1)
# 计算输出层前向传播结果
return tf.matmul(layer1, weights2) + biases2
else:
# 首先计算变量的滑动平均值，然后计算前向传播结果
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)

# 训练模型的过程
def train(mnist):
x = tf.placeholder(tf.float32, [None, INPUT_NODE], name='x-input')
y_ = tf.placeholder(tf.float32, [None, OUTPUT_NODE], name='y-input')

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

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

# 计算前向传播结果，不使用参数滑动平均值 avg_class=None
y = inference(x, None, weights1, biases1, weights2, biases2)

# 定义训练轮数变量，指定为不可训练
global_step = tf.Variable(0, trainable=False)

# 给定滑动平均衰减率和训练轮数的变量，初始化滑动平均类
variable_avgs = tf.train.ExponentialMovingAverage(
MOVING_AVG_DECAY, global_step)

# 在所有代表神经网络参数的可训练变量上使用滑动平均
variables_avgs_op = variable_avgs.apply(tf.trainable_variables())

# 计算使用滑动平均值后的前向传播结果
avg_y = inference(x, variable_avgs, weights1, biases1, weights2, biases2)

# 计算交叉熵作为损失函数
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)

# 计算L2正则化损失函数
regularizer = tf.contrib.layers.l2_regularizer(REGULARIZATION_RATE)
regularization = regularizer(weights1) + regularizer(weights2)

loss = cross_entropy_mean + regularization

# 设置指数衰减的学习率
learning_rate = tf.train.exponential_decay(
LEARNING_RATE_BASE,
global_step,              # 当前迭代轮数
mnist.train.num_examples / BATCH_SIZE, # 过完所有训练数据的迭代次数
LEARNING_RATE_DECAY)

# 优化损失函数
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, variables_avgs_op]):
train_op = tf.no_op(name='train')

# 检验使用了滑动平均模型的神经网络前向传播结果是否正确
correct_prediction = tf.equal(tf.argmax(avg_y, 1), tf.argmax(y_, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))

# 初始化会话并开始训练
with tf.Session() as sess:
tf.global_variables_initializer().run()

# 准备验证数据，用于判断停止条件和训练效果
validate_feed = {x: mnist.validation.images,
y_: mnist.validation.labels}

# 准备测试数据，用于模型优劣的最后评价标准
test_feed = {x: mnist.test.images, y_: mnist.test.labels}

# 迭代训练神经网络
for i in range(TRAINING_STEPS):
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})

# 训练结束后在测试集上检测模型的最终正确率
test_acc = sess.run(accuracy, feed_dict=test_feed)
print("After %d training steps, test accuracy using average model "
"is %g " % (TRAINING_STEPS, test_acc))

# 主程序入口
def main(argv=None):
mnist = input_data.read_data_sets("/tmp/data", one_hot=True)
train(mnist)

# Tensorflow主程序入口
if __name__ == '__main__':
tf.app.run()

输出结果如下：

Extracting /tmp/data/train-images-idx3-ubyte.gz
Extracting /tmp/data/train-labels-idx1-ubyte.gz
Extracting /tmp/data/t10k-images-idx3-ubyte.gz
Extracting /tmp/data/t10k-labels-idx1-ubyte.gz
After 0 training step(s), validation accuracy using average model is 0.0462
After 1000 training step(s), validation accuracy using average model is 0.9784
After 2000 training step(s), validation accuracy using average model is 0.9806
After 3000 training step(s), validation accuracy using average model is 0.9798
After 4000 training step(s), validation accuracy using average model is 0.9814
After 5000 training step(s), validation accuracy using average model is 0.9826
After 6000 training step(s), validation accuracy using average model is 0.9828
After 7000 training step(s), validation accuracy using average model is 0.9832
After 8000 training step(s), validation accuracy using average model is 0.9838
After 9000 training step(s), validation accuracy using average model is 0.983
After 10000 training step(s), validation accuracy using average model is 0.9836
After 11000 training step(s), validation accuracy using average model is 0.9822
After 12000 training step(s), validation accuracy using average model is 0.983
After 13000 training step(s), validation accuracy using average model is 0.983
After 14000 training step(s), validation accuracy using average model is 0.9844
After 15000 training step(s), validation accuracy using average model is 0.9832
After 16000 training step(s), validation accuracy using average model is 0.9844
After 17000 training step(s), validation accuracy using average model is 0.9842
After 18000 training step(s), validation accuracy using average model is 0.9842
After 19000 training step(s), validation accuracy using average model is 0.9838
After 20000 training step(s), validation accuracy using average model is 0.9834
After 21000 training step(s), validation accuracy using average model is 0.9828
After 22000 training step(s), validation accuracy using average model is 0.9834
After 23000 training step(s), validation accuracy using average model is 0.9844
After 24000 training step(s), validation accuracy using average model is 0.9838
After 25000 training step(s), validation accuracy using average model is 0.9834
After 26000 training step(s), validation accuracy using average model is 0.984
After 27000 training step(s), validation accuracy using average model is 0.984
After 28000 training step(s), validation accuracy using average model is 0.9836
After 29000 training step(s), validation accuracy using average model is 0.9842
After 30000 training steps, test accuracy using average model is 0.9839

以上就是本文的全部内容，希望对大家的学习有所帮助

您可能感兴趣的文章:

• tensorflow实现训练变量checkpoint的保存与读取
• Tensorflow训练模型越来越慢的2种解决方案
• TensorFlow实现保存训练模型为pd文件并恢复
• 解决TensorFlow训练内存不断增长,进程被杀死问题
• tensorflow获取预训练模型某层参数并赋值到当前网络指定层方式
• tensorflow模型继续训练 fineturn实例
• tensorflow如何继续训练之前保存的模型实例
• Tensorflow实现在训练好的模型上进行测试
• tensorflow保持每次训练结果一致的简单实现