上次发现约复杂的网络,拟合能力越强,但是test和train集的准确率差别变大,说明有过拟合的倾向。
下面是代码:
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
#mnist已经作为官方的例子,做好了数据下载,分割,转浮点等一系列工作,源码在tensorflow源码中都可以找到
mnist = input_data.read_data_sets('MNIST_data', one_hot=True)
# 配置每个 GPU 上占用的内存的比例
# 没有GPU直接sess = tf.Session()
gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=0.95)
sess = tf.Session(config=tf.ConfigProto(gpu_options=gpu_options))
#每个批次的大小
batch_size = 200
#定义训练轮数据
train_epoch = 10
#定义每n轮输出一次
test_epoch_n = 1
#计算一共有多少批次
n_batch = mnist.train.num_examples // batch_size
print("batch_size="+str(batch_size)+"n_batch="+str(n_batch))
#占位符,定义了输入,输出
x = tf.placeholder(tf.float32,[None, 784])
y = tf.placeholder(tf.float32,[None, 10])
#权重和偏置,使用0初始化
W1 = tf.Variable(tf.truncated_normal([784,2000],stddev=0.1))
b1 = tf.Variable(tf.zeros([2000])+0.1)
#L1 = tf.nn.tanh(tf.matmul(x,W1)+b1)
#L1 = tf.nn.relu(tf.matmul(x,W1)+b1)
L1 = tf.nn.sigmoid(tf.matmul(x,W1)+b1)
W2 = tf.Variable(tf.truncated_normal([2000,1000],stddev=0.1))
b2 = tf.Variable(tf.zeros([1000])+0.1)
#L2 = tf.nn.tanh(tf.matmul(L1,W2)+b2)
#L2 = tf.nn.relu(tf.matmul(L1,W2)+b2)
L2 = tf.nn.sigmoid(tf.matmul(L1,W2)+b2)
W3 = tf.Variable(tf.truncated_normal([1000,100],stddev=0.1))
b3 = tf.Variable(tf.zeros([100])+0.1)
#L3 = tf.nn.tanh(tf.matmul(L2,W3)+b3)
#L3 = tf.nn.relu(tf.matmul(L2,W3)+b3)
L3 = tf.nn.sigmoid(tf.matmul(L2,W3)+b3)
W4 = tf.Variable(tf.truncated_normal([100,10],stddev=0.1))
b4 = tf.Variable(tf.zeros([10])+0.1)
L4 = tf.nn.sigmoid(tf.matmul(L3,W4)+b4)
#这里定义的网络结构
prediction = tf.nn.softmax(L4)
#损失函数是交叉熵
cross_entropy = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=y,logits=prediction))
#训练方法:
#train_step = tf.train.GradientDescentOptimizer(0.01).minimize(cross_entropy)
train_step = tf.train.AdamOptimizer(1e-2).minimize(cross_entropy)
#初始化sess中所有变量
init = tf.global_variables_initializer()
sess.run(init)
MaxACC = 0#最好的ACC
saver = tf.train.Saver()
#训练n个epoch
for epoch in range(train_epoch):
for batch in range(n_batch):
batch_xs, batch_ys = mnist.train.next_batch(batch_size)
sess.run(train_step, feed_dict = {x: batch_xs, y: batch_ys})
if(0==(epoch%test_epoch_n)):#每若干次预测test一次
#计算test集的准确率
correct_prediction = tf.equal(tf.argmax(prediction,1), tf.argmax(y,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
now_acc=sess.run(accuracy, feed_dict={x:mnist.test.images, y: mnist.test.labels})
print('epoch=',epoch,'ACC=',now_acc,'train acc =',sess.run(accuracy, feed_dict={x:mnist.train.images, y: mnist.train.labels}))
if(now_acc>MaxACC):
MaxACC = now_acc
saver.save(sess, "Model/ModelSoftmax.ckpt")
print('Save model! Now ACC=',MaxACC)
#计算最终test集的准确率
correct_prediction = tf.equal(tf.argmax(prediction,1), tf.argmax(y,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
print('Train OK! epoch=',epoch,'ACC=',sess.run(accuracy, feed_dict={x:mnist.test.images, y: mnist.test.labels}))
#关闭sess
sess.close()
#读取模型
gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=0.95)
with tf.Session(config=tf.ConfigProto(gpu_options=gpu_options)) as sess:
saver.restore(sess, "./Model/ModelSoftmax.ckpt") # 注意此处路径前添加"./"
print('Load Model OK!')
print('ACC=',sess.run(accuracy, feed_dict={x:mnist.test.images, y: mnist.test.labels}))
最终输出结果:
epoch= 0 ACC= 0.7969 train acc = 0.799182
Save model! Now ACC= 0.7969
epoch= 1 ACC= 0.9566 train acc = 0.962764
Save model! Now ACC= 0.9566
epoch= 2 ACC= 0.9613 train acc = 0.968036
Save model! Now ACC= 0.9613
epoch= 3 ACC= 0.9677 train acc = 0.975109
Save model! Now ACC= 0.9677
epoch= 4 ACC= 0.9698 train acc = 0.977145
Save model! Now ACC= 0.9698
epoch= 5 ACC= 0.9687 train acc = 0.979345
epoch= 6 ACC= 0.9653 train acc = 0.974636
epoch= 7 ACC= 0.9693 train acc = 0.980545
epoch= 8 ACC= 0.9694 train acc = 0.981091
epoch= 9 ACC= 0.9654 train acc = 0.978727
Train OK! epoch= 9 ACC= 0.9654
加入dropout
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
#mnist已经作为官方的例子,做好了数据下载,分割,转浮点等一系列工作,源码在tensorflow源码中都可以找到
mnist = input_data.read_data_sets('MNIST_data', one_hot=True)
# 配置每个 GPU 上占用的内存的比例
# 没有GPU直接sess = tf.Session()
gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=0.95)
sess = tf.Session(config=tf.ConfigProto(gpu_options=gpu_options))
#每个批次的大小
batch_size = 200
#定义训练轮数据
train_epoch = 10
#定义每n轮输出一次
test_epoch_n = 1
#计算一共有多少批次
n_batch = mnist.train.num_examples // batch_size
print("batch_size="+str(batch_size)+"n_batch="+str(n_batch))
#占位符,定义了输入,输出
x = tf.placeholder(tf.float32,[None, 784])
y = tf.placeholder(tf.float32,[None, 10])
#定义
keep_prob=tf.placeholder(tf.float32)
#权重和偏置,使用0初始化
W1 = tf.Variable(tf.truncated_normal([784,2000],stddev=0.1))
b1 = tf.Variable(tf.zeros([2000])+0.1)
L1 = tf.nn.sigmoid(tf.matmul(x,W1)+b1)
L1_drop = tf.nn.dropout(L1,keep_prob)
W2 = tf.Variable(tf.truncated_normal([2000,1000],stddev=0.1))
b2 = tf.Variable(tf.zeros([1000])+0.1)
L2 = tf.nn.sigmoid(tf.matmul(L1_drop,W2)+b2)
L2_drop = tf.nn.dropout(L2,keep_prob)
W3 = tf.Variable(tf.truncated_normal([1000,100],stddev=0.1))
b3 = tf.Variable(tf.zeros([100])+0.1)
L3 = tf.nn.sigmoid(tf.matmul(L2_drop,W3)+b3)
L3_drop = tf.nn.dropout(L3,keep_prob)
W4 = tf.Variable(tf.truncated_normal([100,10],stddev=0.1))
b4 = tf.Variable(tf.zeros([10])+0.1)
L4 = tf.nn.sigmoid(tf.matmul(L3,W4)+b4)
#这里定义的网络结构
prediction = tf.nn.softmax(L4)
#损失函数是交叉熵
cross_entropy = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=y,logits=prediction))
#训练方法:
#train_step = tf.train.GradientDescentOptimizer(0.01).minimize(cross_entropy)
train_step = tf.train.AdamOptimizer(1e-2).minimize(cross_entropy)
#初始化sess中所有变量
init = tf.global_variables_initializer()
sess.run(init)
MaxACC = 0#最好的ACC
saver = tf.train.Saver()
#训练n个epoch
for epoch in range(train_epoch):
for batch in range(n_batch):
batch_xs, batch_ys = mnist.train.next_batch(batch_size)
sess.run(train_step, feed_dict = {x: batch_xs, y: batch_ys,keep_prob:0.7})
if(0==(epoch%test_epoch_n)):#每若干次预测test一次
#计算test集的准确率
correct_prediction = tf.equal(tf.argmax(prediction,1), tf.argmax(y,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
now_acc=sess.run(accuracy, feed_dict={x:mnist.test.images, y: mnist.test.labels,keep_prob:1.0})
print('epoch=',epoch,'ACC=',now_acc,'train acc =',sess.run(accuracy, feed_dict={x:mnist.train.images, y: mnist.train.labels,keep_prob:1.0}))
if(now_acc>MaxACC):
MaxACC = now_acc
saver.save(sess, "Model/ModelSoftmax.ckpt")
print('Save model! Now ACC=',MaxACC)
#计算最终test集的准确率
correct_prediction = tf.equal(tf.argmax(prediction,1), tf.argmax(y,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
print('Train OK! epoch=',epoch,'ACC=',sess.run(accuracy, feed_dict={x:mnist.test.images, y: mnist.test.labels,keep_prob:1.0}))
#关闭sess
sess.close()
#读取模型
gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=0.95)
with tf.Session(config=tf.ConfigProto(gpu_options=gpu_options)) as sess:
saver.restore(sess, "./Model/ModelSoftmax.ckpt") # 注意此处路径前添加"./"
print('Load Model OK!')
print('ACC=',sess.run(accuracy, feed_dict={x:mnist.test.images, y: mnist.test.labels,keep_prob:1.0}))
最终结果:
epoch= 0 ACC= 0.856 train acc = 0.858455
Save model! Now ACC= 0.856
epoch= 1 ACC= 0.8622 train acc = 0.866527
Save model! Now ACC= 0.8622
epoch= 2 ACC= 0.884 train acc = 0.893582
Save model! Now ACC= 0.884
epoch= 3 ACC= 0.9656 train acc = 0.971473
Save model! Now ACC= 0.9656
epoch= 4 ACC= 0.9663 train acc = 0.972618
Save model! Now ACC= 0.9663
epoch= 5 ACC= 0.969 train acc = 0.977655
Save model! Now ACC= 0.969
epoch= 6 ACC= 0.9661 train acc = 0.975982
epoch= 7 ACC= 0.9648 train acc = 0.9736
epoch= 8 ACC= 0.9698 train acc = 0.979345
Save model! Now ACC= 0.9698
epoch= 9 ACC= 0.9699 train acc = 0.978418
Save model! Now ACC= 0.9699
Train OK! epoch= 9 ACC= 0.9699
好像也没有好太多,还是过拟合情况不够严重。