tensorflow学习笔记(1)
来源:互联网 发布:jk js 编辑:程序博客网 时间:2024/05/22 03:52
使用tensorflow实现一个简单的卷积网络,使用数据集MNIST,预测可以达到99.2%的准确率。卷积网络由两个卷积层加一个全连接层构成。 #-*- coding: utf-8 -*-
"""
Spyder Editor
This is a temporary script file.
"""
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data #载入MNIST数据集,并创建默认的Interactive Session
mnist=input_data.read_data_sets("MNIST_data/",one_hot=True)
sess = tf.InteractiveSession()
`#定义初始化函数 给权重加入噪音
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)
#卷积层与池化层
def conv2d(x, W):
#x 是输入 W是卷积的参数 :【5,5,1,32】代表5*5的卷积大小
#1表示chaanel 32表示卷积核数量
#strides表示移动步长【1,1,1,1】表示不遗漏每一个点 padding:same 加上边界
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’)
x = tf.placeholder(tf.float32,[None, 784])
y_ = tf.placeholder(tf.float32,[None, 10])
x_image = tf.reshape(x,[-1,28,28,1])
#定义第一个卷积层
W_conv1 = weight_variable([5,5,1,32])
b_conv1 = bias_variable([32])
h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1)+b_conv1)
h_pool1 = max_pool_2x2(h_conv1)
#定义第二个卷积层
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)
#两次最大池化,28*28变成7*7,7*7*64转化为1d向量
W_fc1 = weight_variable([7*7*64,1024])
b_fc1 = bias_variable([1024])
h_pool2_float = tf.reshape(h_pool2, [-1,7*7*64])
h_fc1 = tf.nn.relu(tf.matmul(h_pool2_float, W_fc1)+b_fc1)
#加入dropout防止过拟合
keep_prob = tf.placeholder(tf.float32)
h_fc1_drop = tf.nn.dropout(h_fc1,keep_prob)
#最后一层输出连接一个softmax 得到概率输出
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)
#定义损失函数 cross entropy 优化器:adam
cross_entropy = tf.reduce_mean(-tf.reduce_sum(y_ *tf.log(y_conv),reduction_indices=[1]))
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)
#定义评估准确率的函数
correct_prediction = tf.equal(tf.argmax(y_conv, 1), tf.argmax(y_,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction,tf.float32))
#开始训练,初始化所有参数,drop=0.5 用50的mini-batch 进行20000次迭代,共100w样本,100次评估一次
tf.global_variables_initializer().run()
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}))
- TensorFlow 学习笔记(1)
- tensorflow学习笔记(1)
- TensorFlow学习笔记(1)
- TensorFlow学习笔记-1
- TensorFlow学习笔记1
- Tensorflow学习笔记(1)
- TensorFlow学习笔记1
- TensorFlow学习笔记1
- tensorflow学习笔记1
- tensorflow 学习笔记 1
- TensorFlow学习笔记(1)--TensorFlow简介,常用基本操作
- Tensorflow——学习笔记(1)
- tensorflow学习笔记(1):基础元素
- tensorflow中文文档学习笔记(1)
- tensorflow学习笔记(1)-sess
- TensorFlow学习笔记(1)--Mac安装TensorFlow
- TensorFlow学习笔记(1)--Mac安装TensorFlow
- TensorFlow学习笔记1:Hello TensorFlow!
- ffplay看直播,简洁是美
- mysql日志
- iOS学习笔记-127.SDWebImage3——缓存的清除和操作的取消
- 我所理解的WSGI(关键词:Python/HTTP/WSGI/web开发)
- JS数组方法
- tensorflow学习笔记(1)
- extern 全局变量2
- BZOJ 1895 & POJ 3580 supermemo (splay)
- hdu 1208 Pascal's Travels
- POJ 2104 K-th Number 静态第K大模板
- Codeforces Round #433(Div.2) C,D,E题目详解
- HDU 4325 Flowers(树状数组+离散化)
- java SE类初始化过程学习记录
- oracle学习之oracle基础