# 输入数据
import input_data
mnist = input_data.read_data_sets("/tmp/data/", one_hot=True) import tensorflow as tf # 定义网络超参数
learning_rate = 0.001
training_iters = 200000
batch_size = 64
display_step = 20 # 定义网络参数
n_input = 784 # 输入的维度
n_classes = 10 # 标签的维度
dropout = 0.8 # Dropout 的概率 # 占位符输入
x = tf.placeholder(tf.types.float32, [None, n_input])
y = tf.placeholder(tf.types.float32, [None, n_classes])
keep_prob = tf.placeholder(tf.types.float32) # 卷积操作
def conv2d(name, l_input, w, b):
return tf.nn.relu(tf.nn.bias_add(tf.nn.conv2d(l_input, w, strides=[1, 1, 1, 1], padding='SAME'),b), name=name) # 最大下采样操作
def max_pool(name, l_input, k):
return tf.nn.max_pool(l_input, ksize=[1, k, k, 1], strides=[1, k, k, 1], padding='SAME', name=name) # 归一化操作
def norm(name, l_input, lsize=4):
return tf.nn.lrn(l_input, lsize, bias=1.0, alpha=0.001 / 9.0, beta=0.75, name=name) # 定义整个网络
def alex_net(_X, _weights, _biases, _dropout):
# 向量转为矩阵
_X = tf.reshape(_X, shape=[-1, 28, 28, 1]) # 卷积层
conv1 = conv2d('conv1', _X, _weights['wc1'], _biases['bc1'])
# 下采样层
pool1 = max_pool('pool1', conv1, k=2)
# 归一化层
norm1 = norm('norm1', pool1, lsize=4)
# Dropout
norm1 = tf.nn.dropout(norm1, _dropout) # 卷积
conv2 = conv2d('conv2', norm1, _weights['wc2'], _biases['bc2'])
# 下采样
pool2 = max_pool('pool2', conv2, k=2)
# 归一化
norm2 = norm('norm2', pool2, lsize=4)
# Dropout
norm2 = tf.nn.dropout(norm2, _dropout) # 卷积
conv3 = conv2d('conv3', norm2, _weights['wc3'], _biases['bc3'])
# 下采样
pool3 = max_pool('pool3', conv3, k=2)
# 归一化
norm3 = norm('norm3', pool3, lsize=4)
# Dropout
norm3 = tf.nn.dropout(norm3, _dropout) # 全连接层,先把特征图转为向量
dense1 = tf.reshape(norm3, [-1, _weights['wd1'].get_shape().as_list()[0]])
dense1 = tf.nn.relu(tf.matmul(dense1, _weights['wd1']) + _biases['bd1'], name='fc1')
# 全连接层
dense2 = tf.nn.relu(tf.matmul(dense1, _weights['wd2']) + _biases['bd2'], name='fc2') # Relu activation # 网络输出层
out = tf.matmul(dense2, _weights['out']) + _biases['out']
return out # 存储所有的网络参数
weights = {
'wc1': tf.Variable(tf.random_normal([3, 3, 1, 64])),
'wc2': tf.Variable(tf.random_normal([3, 3, 64, 128])),
'wc3': tf.Variable(tf.random_normal([3, 3, 128, 256])),
'wd1': tf.Variable(tf.random_normal([4\*4\*256, 1024])),
'wd2': tf.Variable(tf.random_normal([1024, 1024])),
'out': tf.Variable(tf.random_normal([1024, 10]))
}
biases = {
'bc1': tf.Variable(tf.random_normal([64])),
'bc2': tf.Variable(tf.random_normal([128])),
'bc3': tf.Variable(tf.random_normal([256])),
'bd1': tf.Variable(tf.random_normal([1024])),
'bd2': tf.Variable(tf.random_normal([1024])),
'out': tf.Variable(tf.random_normal([n_classes]))
} # 构建模型
pred = alex_net(x, weights, biases, keep_prob) # 定义损失函数和学习步骤
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(pred, y))
optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(cost) # 测试网络
correct_pred = tf.equal(tf.argmax(pred,1), tf.argmax(y,1))
accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32)) # 初始化所有的共享变量
init = tf.initialize_all_variables() # 开启一个训练
with tf.Session() as sess:
sess.run(init)
step = 1
# Keep training until reach max iterations
while step \* batch_size < training_iters:
batch_xs, batch_ys = mnist.train.next_batch(batch_size)
# 获取批数据
sess.run(optimizer, feed_dict={x: batch_xs, y: batch_ys, keep_prob: dropout})
if step % display_step == 0:
# 计算精度
acc = sess.run(accuracy, feed_dict={x: batch_xs, y: batch_ys, keep_prob: 1.})
# 计算损失值
loss = sess.run(cost, feed_dict={x: batch_xs, y: batch_ys, keep_prob: 1.})
print "Iter " + str(step\*batch_size) + ", Minibatch Loss= " + "{:.6f}".format(loss) + ", Training Accuracy= " + "{:.5f}".format(acc)
step += 1
print "Optimization Finished!"
# 计算测试精度
print "Testing Accuracy:", sess.run(accuracy, feed_dict={x: mnist.test.images[:256], y: mnist.test.labels[:256], keep_prob: 1.})

  

tensorflow 是强大的分布式跨平台深度学习框架

keras,TensorLayer,Tflearn 都是基于tensorflow 开发的库(提供傻瓜式编程)

知识点:

from __future__ import print_function   : 为了老版本的python 兼顾新特性 (from __future import *)

tensorflow---alexnet training (tflearn)的更多相关文章

  1. 神经网络 (2)- Alexnet Training on MNIST

    文章目录 Win10 Anaconda下配置tensorflow+jupyter notebook环境 AlexNet 识别MNIST Win10 Anaconda下配置tensorflow+jupy ...

  2. TensorFlow alexnet在华为Mate10上运行方法

    我使用的caffe模型:https://github.com/BVLC/caffe/tree/ea455eb29393ebe6de9f14e88bfce9eae74edf6d/models/bvlc_ ...

  3. caffe to tensorflow alexnet model

    from kaffe.tensorflow import Network class AlexNet(Network): def setup(self): (self.feed('data') .co ...

  4. tflearn Training Step每次 We will run it for 10 epochs (the network will see all data 10 times) with a batch size of 16. n_epoch=10, batch_size=16

    Training TFLearn provides a model wrapper 'DNN' that can automatically performs a neural network cla ...

  5. 资源 | 数十种TensorFlow实现案例汇集:代码+笔记

    选自 Github 机器之心编译 参与:吴攀.李亚洲 这是使用 TensorFlow 实现流行的机器学习算法的教程汇集.本汇集的目标是让读者可以轻松通过案例深入 TensorFlow. 这些案例适合那 ...

  6. 数十种TensorFlow实现案例汇集:代码+笔记(转)

    转:https://www.jiqizhixin.com/articles/30dc6dd9-39cd-406b-9f9e-041f5cbf1d14 这是使用 TensorFlow 实现流行的机器学习 ...

  7. tensorflow 经典教程及案例

    导语:本文是TensorFlow实现流行机器学习算法的教程汇集,目标是让读者可以轻松通过清晰简明的案例深入了解 TensorFlow.这些案例适合那些想要实现一些 TensorFlow 案例的初学者. ...

  8. (zhuan) 资源|TensorFlow初学者必须了解的55个经典案例

    资源|TensorFlow初学者必须了解的55个经典案例 2017-05-27 全球人工智能 >>>>>>欢迎投稿:news@top25.cn<<< ...

  9. 数十种TensorFlow实现案例汇集:代码+笔记

    这是使用 TensorFlow 实现流行的机器学习算法的教程汇集.本汇集的目标是让读者可以轻松通过案例深入 TensorFlow. 这些案例适合那些想要清晰简明的 TensorFlow 实现案例的初学 ...

随机推荐

  1. postgreSQL学习(一):在Linux下安装postgreSQL

    1. 安装源: $ sudo yum install https://download.postgresql.org/pub/repos/yum/10/redhat/rhel-7-x86_64/pgd ...

  2. jpa 原生查询createNativeQuery里面有冒号保留字关键字的问题

    用\\:替换. 比如: String sql = "select location.ToString() a,version,location.STDistance(geometry\\:\ ...

  3. 【模板】ac自动机

    本来是真的特别不想写这个的 但是有段时间洛谷天天智推这个可能是我太菜了 然后觉得这个也不难 乘着今早没事写下 来这保存下 方便下次食用 #include <bits/stdc++.h> u ...

  4. linux:awk修改输出分隔符

    file1的内容如下: a b c d e f g h 现在想要修改成 a b c:d e f g:h 则需要用到如下命令: awk -F " " '{print $1,$2,$3 ...

  5. GUI 设计

    GUI(图形化界面编程) Graphical  User  Interface (java.Awt    javax.Swing) CLI(命令行操作接口) Command  line  User   ...

  6. Idea2017.3.5+SpringBoot--热部署

    首先建立工程的时候要选择DevTools: 然后File----Settings 然后 点击OK,然后Ctrl+Alt+Shift+/ 当当当当!!出来下面这个,点击Registry 找到这一项,勾选 ...

  7. python基础-格式化时间

    module datatime用strftime格式化时间import datetimedatetime.datetime.now() 返回microsecond,要修改datetime.dateti ...

  8. 【清北学堂2018-刷题冲刺】Contest 3

     比较数学的一场,难度稍大. Task 1:数数 [问题描述]  fadbec 很善于数数,⽐如他会数将a 个红球,b 个黄球,c 个蓝球,d个绿球排成⼀列,求出任意相邻不同⾊的方案数⽬.  现在R ...

  9. linux ------ 使用 screen 后 SSH 断开后程序依旧能在后台运行

    为什么ssh断开后你运行的进程会退出呢? 因为所有进程都得有个父进程.当你ssh到一个服务器上时,打开的shell就是你所有执行命令的父进程. 当你断开ssh连接时,你的命令的父进程就没了.如果处理不 ...

  10. TRAFFIC ANALYSIS EXERCISE - Ransomer

    catalogue . SCENARIO . QUESTIONS . Analysis:10.3.14.134 . Analysis:10.3.14.131 1. SCENARIO The pcap ...