Training Data Eval:
Num examples: 55000 Num correct: 52015 Precision @ 1: 0.9457
Validation Data Eval:
Num examples: 5000 Num correct: 4740 Precision @ 1: 0.9480
Test Data Eval:
Num examples: 10000 Num correct: 9456 Precision @ 1: 0.9456

 import tensorflow as tf
import input_data
import math NUM_CLASSES = 10
IMAGE_SIZE = 28
IMAGE_PIXELS = IMAGE_SIZE * IMAGE_SIZE
flags = tf.app.flags
FLAGS = flags.FLAGS
flags.DEFINE_float('learning_rate', 0.01, 'Initial learning rate.')
flags.DEFINE_integer('max_steps', 10000, 'Number of steps to run trainer.')
flags.DEFINE_integer('hidden1', 128, 'Number of units in hidden layer 1.')
flags.DEFINE_integer('hidden2', 32, 'Number of units in hidden layer 2.')
flags.DEFINE_integer('batch_size', 100, 'Batch size. '
'Must divide evenly into the dataset sizes.')
flags.DEFINE_string('train_dir', 'data', 'Directory to put the training data.')
flags.DEFINE_boolean('fake_data', False, 'If true, uses fake data '
'for unit testing.') def inference(images, hidden1_units, hidden2_units):
with tf.name_scope('hidden1'):
weights = tf.Variable(
tf.truncated_normal([IMAGE_PIXELS, hidden1_units],
stddev=1.0 / math.sqrt(float(IMAGE_PIXELS))),
name='weights')
biases = tf.Variable(tf.zeros([hidden1_units]),
name='biases')
hidden1 = tf.nn.relu(tf.matmul(images, weights) + biases)
with tf.name_scope('hidden2'):
weights = tf.Variable(
tf.truncated_normal([hidden1_units, hidden2_units],
stddev=1.0 / math.sqrt(float(hidden1_units))),
name='weights')
biases = tf.Variable(tf.zeros([hidden2_units]),
name='biases')
hidden2 = tf.nn.relu(tf.matmul(hidden1, weights) + biases)
with tf.name_scope('softmax_linear'):
weights = tf.Variable(
tf.truncated_normal([hidden2_units, NUM_CLASSES],
stddev=1.0 / math.sqrt(float(hidden2_units))),
name='weights')
biases = tf.Variable(tf.zeros([NUM_CLASSES]),
name='biases')
logits = tf.matmul(hidden2, weights) + biases
return logits def loss(logits, labels):
labels = tf.to_int64(labels)
cross_entropy = tf.nn.sparse_softmax_cross_entropy_with_logits(
logits, labels, name='xentropy')
loss = tf.reduce_mean(cross_entropy, name='xentropy_mean')
return loss def training(loss, learning_rate):
tf.scalar_summary(loss.op.name, loss)
optimizer = tf.train.GradientDescentOptimizer(learning_rate)
global_step = tf.Variable(0, name='global_step', trainable=False)
train_op = optimizer.minimize(loss, global_step=global_step)
return train_op def evaluation(logits, labels):
correct = tf.nn.in_top_k(logits, labels, 1)
return tf.reduce_sum(tf.cast(correct, tf.int32)) def placeholder_inputs(batch_size):
images_placeholder = tf.placeholder(tf.float32, shape=(batch_size,
IMAGE_PIXELS))
labels_placeholder = tf.placeholder(tf.int32, shape=(batch_size))
return images_placeholder, labels_placeholder def fill_feed_dict(data_set, images_pl, labels_pl):
images_feed, labels_feed = data_set.next_batch(FLAGS.batch_size,
FLAGS.fake_data)
feed_dict = {
images_pl: images_feed,
labels_pl: labels_feed,
}
return feed_dict def do_eval(sess,
eval_correct,
images_placeholder,
labels_placeholder,
data_set):
true_count = 0
steps_per_epoch = data_set.num_examples // FLAGS.batch_size
num_examples = steps_per_epoch * FLAGS.batch_size
for step in range(steps_per_epoch):
feed_dict = fill_feed_dict(data_set,
images_placeholder,
labels_placeholder)
true_count += sess.run(eval_correct, feed_dict=feed_dict)
precision = true_count / num_examples
print(' Num examples: %d Num correct: %d Precision @ 1: %0.04f' %
(num_examples, true_count, precision)) def run_training():
data_sets = input_data.read_data_sets(FLAGS.train_dir, FLAGS.fake_data)
print(FLAGS.train_dir, FLAGS.fake_data)
with tf.Graph().as_default():
images_placeholder, labels_placeholder = placeholder_inputs(
FLAGS.batch_size)
logits = inference(images_placeholder,
FLAGS.hidden1,
FLAGS.hidden2)
loss_minist = loss(logits, labels_placeholder)
train_op = training(loss_minist, FLAGS.learning_rate)
eval_correct = evaluation(logits, labels_placeholder)
summary = tf.merge_all_summaries()
init = tf.initialize_all_variables()
sess = tf.Session()
summary_writer = tf.train.SummaryWriter(FLAGS.train_dir, sess.graph)
sess.run(init)
for step in range(FLAGS.max_steps):
feed_dict = fill_feed_dict(data_sets.train,
images_placeholder,
labels_placeholder)
_, loss_value = sess.run([train_op, loss_minist],
feed_dict=feed_dict) if step % 100 == 0:
print('Step %d: loss = %.2f' % (step, loss_value))
summary_str = sess.run(summary, feed_dict=feed_dict)
summary_writer.add_summary(summary_str, step)
summary_writer.flush()
if (step + 1) % 1000 == 0 or (step + 1) == FLAGS.max_steps:
print('Training Data Eval:')
do_eval(sess,
eval_correct,
images_placeholder,
labels_placeholder,
data_sets.train)
print('Validation Data Eval:')
do_eval(sess,
eval_correct,
images_placeholder,
labels_placeholder,
data_sets.validation)
print('Test Data Eval:')
do_eval(sess,
eval_correct,
images_placeholder,
labels_placeholder,
data_sets.test)
run_training()

Tensorflow ——神经网络的更多相关文章

  1. TensorFlow神经网络集成方案

    TensorFlow神经网络集成方案 创造张力流create_tensorflow_neuropod 将TensorFlow模型打包为neuropod包. create_tensorflow_neur ...

  2. 【Magenta 项目初探】手把手教你用Tensorflow神经网络创造音乐

    原文链接:http://www.cnblogs.com/learn-to-rock/p/5677458.html 偶然在网上看到了一个让我很感兴趣的项目 Magenta,用Tensorflow让神经网 ...

  3. Tensorflow 神经网络

    Tensorflow让神经网络自动创造音乐 前几天看到一个有意思的分享,大意是讲如何用Tensorflow教神经网络自动创造音乐.听起来好好玩有木有!作为一个Coldplay死忠粉,第一想法就是自动生 ...

  4. 学习笔记TF055:TensorFlow神经网络简单实现一元二次函数

    TensorFlow运行方式.加载数据.定义超参数,构建网络,训练模型,评估模型.预测. 构造一个满足一元二次函数y=ax^2+b原始数据,构建最简单神经网络,包含输入层.隐藏层.输出层.Tensor ...

  5. TensorFlow 神经网络相关函数

    TensorFlow 激活函数 激活操作提供用于神经网络的不同类型的非线性.这些包括平滑的非线性(sigmoid,tanh,elu,softplus,和softsign),连续的,但不是到处可微函数( ...

  6. TensorFlow 神经网络教程

    TensorFlow 是一个用于机器学习应用程序的开源库.它是谷歌大脑的第二代系统,在取代了近源的 DistBelief 之后,被谷歌用于研究和生产应用.TensorFlow 提供了很多种语言接口,包 ...

  7. tensorflow神经网络拟合非线性函数与操作指南

    本实验通过建立一个含有两个隐含层的BP神经网络,拟合具有二次函数非线性关系的方程,并通过可视化展现学习到的拟合曲线,同时随机给定输入值,输出预测值,最后给出一些关键的提示. 源代码如下: # -*- ...

  8. TensorFlow神经网络中的激活函数

    激活函数是人工神经网络的一个极其重要的特征.它决定一个神经元是否应该被激活,激活代表神经元接收的信息与给定的信息有关. 激活函数对输入信息进行非线性变换. 然后将变换后的输出信息作为输入信息传给下一层 ...

  9. Tensorflow神经网络进行fiting function

    使用Tensorflow中的神经网络来拟合函数(y = x ^ 3 + 0.7) # -*- coding:utf-8 -*-import tensorflow as tf import numpy ...

  10. 封装TensorFlow神经网络

    为了参加今年的软件杯设计大赛,这几个月学习了很多新知识.现在大赛的第二轮作品优化已经提交,开始对这四个月所学知识做一些总结与记录. 用TensorFlow搭建神经网络.TensorFlow将神经网络的 ...

随机推荐

  1. 2013年7月份第4周51Aspx源码发布详情

    大型企业通用管理ERP源码  2013-7-26 [VS2010]2013.7.4更新内容:1.修复决策模式-客户等级不能保存问题.2.修复企业知识库有报错问题.3.修复运营模式-人力资源分析模块-在 ...

  2. 技术解析:锁屏绕过,三星Galaxy系列手机也能“被”呼出电话

    近期,由两位安全研究人员,Roberto Paleari及Aristide Fattori,发布了关于三星Galaxy手机设备安全漏洞的技术细节.据称,Galaxy手机可在锁屏状态下被未授权的第三方人 ...

  3. NSAttributedString的用法

    标签: 以前看到这种字号和颜色不一样的字符串,想出个讨巧的办法就是“¥150”一个UILable,“元/位”一个UILable.今天翻看以前的工程,command点进UITextField中看到[at ...

  4. simple grammer

    <?phpecho strlen("Hello world!"); // outputs 12?> <?phpecho str_word_count(" ...

  5. 使用免费内测托管平台fir.im测试

    1,使用Xcode先行把项目导成ipa文件.登录http://fir.im/ 2.点击左上角的苹果标志,把准备好的ipa文件拖入即可.4.填写相关材料即可开始上传5,让飞机灰一会即可.6.接着会看见: ...

  6. UI基础:UITableView的编辑和移动

    相对UITableViiew进行编辑,必须设置代理,让代理遵循UITableViewDataSource和UITableViewDelegate协议.因为需要代理实现协议中几个必须的方法. UITab ...

  7. JS实现Tab选项卡

    http://www.jb51.net/article/24694.htm http://www.sunsean.com/idTabs/#t1 http://www.cnblogs.com/sskse ...

  8. Windows Store App, Shaken

    Accelerometer _accelerometer; ; public MainPage() { this.InitializeComponent(); _accelerometer=Accel ...

  9. Ecshop安装过程中的的问题:cls_image::gd_version()和不支持JPEG

    在安装Ecshop的时候,遇到两个问题: 1.Strict Standards: Non-static method cls_image::gd_version() should not be cal ...

  10. 转载: SQL Server中的索引

    http://www.blogjava.net/wangdetian168/archive/2011/03/07/347192.html 1 SQL Server中的索引 索引是与表或视图关联的磁盘上 ...