摘要:本文主要向大家介绍了【云计算】MNIST-Tensorflow基础知识入门,通过具体的内容向大家展现,希望对大家学习云计算有所帮助。
本文主要向大家介绍了【云计算】MNIST-Tensorflow基础知识入门,通过具体的内容向大家展现,希望对大家学习云计算有所帮助。
在TensorFlow中文社区学习的帖子,好久没写博客了,这个教程非常适合新手学习,附上链接如下:
MNIST是一个数字识别的数据集,笔记本一直是win10,就用spyder跑了一下,感觉很好。第一次的代码仿佛helloworld一样拥有新生儿纯洁的面孔,期间也出了很多莫名其妙的bug,话不多说,上code
# -*- coding: utf-8 -*-
"""
Created on Sun Aug 19 10:59:50 2018
@author: Keneyr
"""
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("G:/MINIST_data/", one_hot=True)
#tf.reset_default_graph()
#keep_prob = tf.placeholder(tf.float32)
# Sets a new default graph, and stores it in `g`.
with tf.Graph().as_default() as g:
x = tf.placeholder("float",[None,784])
W = tf.Variable(tf.zeros([784,10]))
b = tf.Variable(tf.zeros([10]))
y = tf.nn.softmax(tf.matmul(x,W)+b)
y_ = tf.placeholder("float",[None,10])
cross_entropy = -tf.reduce_sum(y_*tf.log(y))
train_step = tf.train.GradientDescentOptimizer(0.01).minimize(cross_entropy)
init = tf.initialize_all_variables()
sess = tf.Session()
sess.run(init)
#开始训练模型,循环训练1000次
for i in range(1000):
#随机抓取训练数据中的100个批处理数据点
batch_xs,batch_ys = mnist.train.next_batch(100)
#print(batch_xs)
sess.run(train_step,feed_dict={x:batch_xs,y_:batch_ys})
#tf.argmax(y,1)返回的是模型对于任一输入x预测到的标签值
#tf.argmax(y_,1) 代表正确的标签
correct_prediction = tf.equal(tf.argmax(y,1),tf.argmax(y_,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction,"float"))
print(accuracy)
print (sess.run(accuracy,feed_dict={x: mnist.test.images, y_: mnist.test.labels}))
谁能告诉我为什么我的代码背景升级为黑色了,贼开心,难道这个是博客的等级有关系吗,这个跑出来的结果就是91%,还有另外一段代码也是一样,跑出来的效果也是91%。区别就在于,下面这个代码使用更加方便的InteractiveSession类。通过它,你可以更加灵活地构建你的代码。它能让你在运行图的时候,插入一些计算图,这些计算图是由某些操作(operations)构成的。这对于工作在交互式环境中的人们来说非常便利,比如使用IPython。如果你没有使用InteractiveSession,那么你需要在启动session之前构建整个计算图,然后启动该计算图。code如下:
# -*- coding: utf-8 -*-
"""
Created on Sun Aug 19 14:16:38 2018
@author: Keneyr
"""
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("G:/MINIST_data/",one_hot=True)
#print (mnist)
sess = tf.InteractiveSession()
x = tf.placeholder("float",shape=[None,784])
y_ = tf.placeholder("float",shape=[None,10])
W = tf.Variable(tf.zeros([784,10]))
b = tf.Variable(tf.zeros([10]))
sess.run(tf.initialize_all_variables())
y = tf.nn.softmax(tf.matmul(x,W)+b)
cross_entropy = -tf.reduce_sum(y_*tf.log(y))
train_step = tf.train.GradientDescentOptimizer(0.01).minimize(cross_entropy)
for i in range(1000):
batch = mnist.train.next_batch(50)
train_step.run(feed_dict={x:batch[0],y_:batch[1]})
correct_prediction = tf.equal(tf.argmax(y,1),tf.argmax(y_,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction,"float"))
print (accuracy.eval(feed_dict={x:mnist.test.images,y_:mnist.test.labels}))
但是这两个代码的效率都不高,有一个用CNN训练的, 效果达到了99.2%,还是不错的,到底要选择什么样的梯度下降算法,选择什么样的网络,网络又该怎么设计,真的是谜一般的存在。难道深度学习这个东西就是黑灯瞎火的碰运气吗···
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("G:/MINIST_data/", one_hot=True)
x = tf.placeholder("float",shape=[None,784])
y_ = tf.placeholder("float",shape=[None,10])
sess = tf.InteractiveSession()
'''
initialization functions
'''
def weight_variable(shape):
initial = tf.truncated_normal(shape,stddev=0.1)
return tf.Variable(initial)
def bias_variable(shape):
initial = tf.constant(0.1,shape=shape)
return tf.Variable(initial)
'''
convolution maxpooling functions
'''
def conv2d(x,W):
return tf.nn.conv2d(x,W,strides=[1,1,1,1],padding='SAME')
def max_pool_2x2(x):
return tf.nn.max_pool(x,ksize=[1,2,2,1],strides=[1,2,2,1],padding='SAME')
'''
conv-relu-maxpooling
'''
W_conv1 = weight_variable([5,5,1,32])
b_conv1 = bias_variable([32])
x_image = tf.reshape(x,[-1,28,28,1])
h_conv1 = tf.nn.relu(conv2d(x_image,W_conv1)+b_conv1)
h_pool1 = max_pool_2x2(h_conv1)
'''
conv-relu-maxpooling
'''
W_conv2 = weight_variable([5,5,32,64])
b_conv2 = bias_variable([64])
h_conv2 = tf.nn.relu(conv2d(h_pool1,W_conv2)+b_conv2)
h_pool2 = max_pool_2x2(h_conv2)
'''
fc
'''
W_fc1 = weight_variable([7 * 7 * 64, 1024])
b_fc1 = bias_variable([1024])
h_pool2_flat = tf.reshape(h_pool2, [-1, 7*7*64])
h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)
'''
dropout
'''
keep_prob = tf.placeholder("float")
h_fc1_drop = tf.nn.dropout(h_fc1,keep_prob)
'''
softmax
'''
W_fc2 = weight_variable([1024, 10])
b_fc2 = bias_variable([10])
y_conv=tf.nn.softmax(tf.matmul(h_fc1_drop, W_fc2) + b_fc2)
'''
train-evaluate
'''
cross_entropy = -tf.reduce_sum(y_*tf.log(y_conv))
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)
correct_prediction = tf.equal(tf.argmax(y_conv,1), tf.argmax(y_,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))
sess.run(tf.initialize_all_variables())
for i in range(20000):
batch = mnist.train.next_batch(50)
if i%100 == 0:
train_accuracy = accuracy.eval(feed_dict={
x:batch[0], y_: batch[1], keep_prob: 1.0})
print ("step %d, training accuracy %g"%(i, train_accuracy))
train_step.run(feed_dict={x: batch[0], y_: batch[1], keep_prob: 0.5})
print ("test accuracy %g"%accuracy.eval(feed_dict={
x: mnist.test.images, y_: mnist.test.labels, keep_prob: 1.0}))
sess.close()
本文由职坐标整理并发布,希望对同学们有所帮助。了解更多详情请关注职坐标大数据云计算大数据安全频道!
您输入的评论内容中包含违禁敏感词
我知道了
请输入正确的手机号码
请输入正确的验证码
您今天的短信下发次数太多了,明天再试试吧!
我们会在第一时间安排职业规划师联系您!
您也可以联系我们的职业规划师咨询:
版权所有 职坐标-一站式IT培训就业服务领导者 沪ICP备13042190号-4
上海海同信息科技有限公司 Copyright ©2015 www.zhizuobiao.com,All Rights Reserved.
沪公网安备 31011502005948号