网络结构代码
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
#载入数据集
mnist = input_data.read_data_sets("MNIST_data",one_hot=True)
#每个批次的大小(每次训练的图片数)
batch_size = 100
#计算一共有多少个批次
n_batch = mnist.train.num_examples
#命名空间
with tf.name_scope('input'):
x = tf.placeholder(tf.float32, [None, 784], name='x_input')
y = tf.placeholder(tf.float32, [None, 10], name='y_input')
with tf.name_scope('layer'):
# 创建一个简单的神经网络 输入层784个神经元输出层10个神经元
with tf.name_scope('weights'):
W = tf.Variable(tf.zeros([784,10]),name='W')
with tf.name_scope('biases'):
b = tf.Variable(tf.zeros([10]),name='b')
with tf.name_scope('wx_plus_b'):
wx_plus_b = tf.matmul(x, W) + b
with tf.name_scope('softmax'):
prediction = tf.nn.softmax(wx_plus_b)
#二次代价函数
#loss = tf.reduce_mean(tf.square(y - prediction))
#交叉熵
with tf.name_scope('loss'):
loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits_v2(labels=y,logits=prediction))
#梯度下降法
with tf.name_scope('train'):
train_step = tf.train.GradientDescentOptimizer(0.2).minimize(loss)
#初始化变量
init = tf.global_variables_initializer()
#结果存放在一个布尔型列表中
#argmax返回一维张量中最大的值所在的位置
#其中argmax(y,1)表示返回每行最大值位置,即哪一个标签,其中1表示每行
#equal表示比较其中两个参数大小是否一样,返回true或false
with tf.name_scope('accuracy'):
with tf.name_scope('correct_prediction'):
correct_prediction = tf.equal(tf.argmax(y,1),tf.argmax(prediction,1)) #其中y是表示标签的位置,例如0010000000,则表示标签在2的位置上
#求准确率
with tf.name_scope('accuracy'):
accuracy = tf.reduce_mean(tf.cast(correct_prediction,tf.float32)) #cast将布尔型转换为浮点型
with tf.Session() as sess:
sess.run(init)
writer = tf.summary.FileWriter('logs/',sess.graph)
for epoch in range(1): #所有图片训练1次
for batch in range(n_batch):#所有图片都循环了一次,每个批次100
batch_xs,batch_ys = mnist.train.next_batch(batch_size)
sess.run(train_step,feed_dict={x:batch_xs,y:batch_ys})
acc = sess.run(accuracy,feed_dict={x:mnist.test.images,y:mnist.test.labels})
print("Iter" + str(epoch) + ",Testing Accuracy" + str(acc))
结果
网络运行代码
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
#载入数据集
mnist = input_data.read_data_sets("MNIST_data",one_hot=True)
#每个批次的大小(每次训练的图片数)
batch_size = 100
#计算一共有多少个批次
n_batch = mnist.train.num_examples
#参数概要
def variable_summaries(var):
with tf.name_scope('summaries'):
mean =tf.reduce_mean(var)
tf.summary.scalar('mean',mean)#平均值
with tf.name_scope('stddev'):
stddev = tf.sqrt(tf.reduce_mean(tf.square(var - mean)))
tf.summary.scalar('stddev',stddev)#标准差
tf.summary.scalar('max',tf.reduce_max(var))#最大值
tf.summary.scalar('min',tf.reduce_min(var))#最小值
tf.summary.histogram('histogarm',var)#直方图
#命名空间
with tf.name_scope('input'):
x = tf.placeholder(tf.float32, [None, 784], name='x_input')
y = tf.placeholder(tf.float32, [None, 10], name='y_input')
with tf.name_scope('layer'):
# 创建一个简单的神经网络 输入层784个神经元输出层10个神经元
with tf.name_scope('weights'):
W = tf.Variable(tf.zeros([784,10]),name='W')
variable_summaries(W)
with tf.name_scope('biases'):
b = tf.Variable(tf.zeros([10]),name='b')
variable_summaries(b)
with tf.name_scope('wx_plus_b'):
wx_plus_b = tf.matmul(x, W) + b
with tf.name_scope('softmax'):
prediction = tf.nn.softmax(wx_plus_b)
#二次代价函数
#loss = tf.reduce_mean(tf.square(y - prediction))
#交叉熵
with tf.name_scope('loss'):
loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits_v2(labels=y,logits=prediction))
tf.summary.scalar('loss',loss)
#梯度下降法
with tf.name_scope('train'):
train_step = tf.train.GradientDescentOptimizer(0.2).minimize(loss)
#初始化变量
init = tf.global_variables_initializer()
#结果存放在一个布尔型列表中
#argmax返回一维张量中最大的值所在的位置
#其中argmax(y,1)表示返回每行最大值位置,即哪一个标签,其中1表示每行
#equal表示比较其中两个参数大小是否一样,返回true或false
with tf.name_scope('accuracy'):
with tf.name_scope('correct_prediction'):
correct_prediction = tf.equal(tf.argmax(y,1),tf.argmax(prediction,1)) #其中y是表示标签的位置,例如0010000000,则表示标签在2的位置上
#求准确率
with tf.name_scope('accuracy'):
accuracy = tf.reduce_mean(tf.cast(correct_prediction,tf.float32)) #cast将布尔型转换为浮点型
tf.summary.scalar('accuracy',accuracy)
#合并所有的summary
merged = tf.summary.merge_all()
with tf.Session() as sess:
sess.run(init)
writer = tf.summary.FileWriter('logs/',sess.graph)
for epoch in range(1): #所有图片训练1次,epoch为运行的周期,这里应该把1改成更大的数就会得到相应的各种曲线
for batch in range(n_batch):#所有图片都循环了一次,每个批次100
batch_xs,batch_ys = mnist.train.next_batch(batch_size)
summary,_ = sess.run([merged,train_step],feed_dict={x:batch_xs,y:batch_ys})
writer.add_summary(summary,epoch)
acc = sess.run(accuracy,feed_dict={x:mnist.test.images,y:mnist.test.labels})
print("Iter" + str(epoch) + ",Testing Accuracy" + str(acc))
结果
由于电脑原因,我只出了八个点