python3下tensorflow练习（三）之tensorboard用法详解

tensorboard用法详解：

使用TensorBoard展示数据，需要在执行Tensorflow就算图的过程中，将各种类型的数据汇总并记录到日志文件中。然后使用TensorBoard读取这些日志文件，解析数据并生产数据可视化的Web页面，让我们可以在浏览器中观察各种汇总数据。

包括标量（scalars），图片（images），音频（Audio）,计算图（graph）,数据分布，直方图（histograms）等

如何在event文件中添加自己想要可视化的数据：
a.定义summary operation:
tf.scaler_summary:用来添加一些标量，比如 lr，loss，accuracy ，etc
tf.image_summary:用来添加一些进入graph的输入图片
tf.histogram_summary:用来统计激活分布，梯度分布，权重分布
tf.audio_summary:
比如：
tf.scalar_summary('标签',想要记录的变量)  
b.定义一个op来将所有的summary operation 合并起来
merged = tf.merge_all_summaries()  
c.使用graph初始化一个summary_writer
train_writer = tf.train.SummaryWriter(FLAGS.summaries_dir + '/train',sess.graph)         
d.每隔n step将summary写入
summary, acc = sess.run([merged, accuracy], feed_dict=feed_dict(False))           
train_writer.add_summary(summary, i)  

基于tensorflow0.11和1.7版本测试，记录下两个版本不同的API，

参考：http://blog.csdn.NET/edwards_june/article/details/65652385

改进：

tf.merge_all_summaries() 改为：summary_op = tf.summary.merge_all()

tf.train.SummaryWriter 改为：tf.summary.FileWriter

tf.scalar_summary 改为：tf.summary.scalar#标量（scalars）

histogram_summary 改为：tf.summary.histogram #直方图（histograms）

 

1.变量则可使用Tensorflow.summary.histogram()方法：

tf.histogram_summary(layer_name+"/weights",Weights) #name命名，Weights赋值 

2.常量则可使用Tensorflow.summary.scalar()方法：

tf.scalar_summary('loss',loss) #命名和赋值

3.最后需要整合和存储FileWriter：

merged = tf.summary.merge_all() 

4.选定可视化存储目录:

writer = tf.summary.FileWriter"/目录",sess.graph)

5.运行

result = sess.run(merged) #merged也是需要run的  
writer.add_summary(result,i)#i---运行的次数

 

测试代码：

 

import tensorflow as tf#1.7版本
from sklearn.datasets import load_digits
from sklearn.cross_validation import train_test_split
from sklearn.preprocessing import LabelBinarizer

# load data
digits = load_digits()
X = digits.data
y = digits.target
y = LabelBinarizer().fit_transform(y)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=.3)


def add_layer(inputs, in_size, out_size, layer_name, activation_function=None, ):
    # add one more layer and return the output of this layer
    Weights = tf.Variable(tf.random_normal([in_size, out_size]))
    biases = tf.Variable(tf.zeros([1, out_size]) + 0.1, )
    Wx_plus_b = tf.matmul(inputs, Weights) + biases
    # here to dropout
    Wx_plus_b = tf.nn.dropout(Wx_plus_b, keep_prob)
    if activation_function is None:
        outputs = Wx_plus_b
    else:
        outputs = activation_function(Wx_plus_b, )
    tf.summary.histogram(layer_name + '/outputs', outputs)
    return outputs


# define placeholder for inputs to network
keep_prob = tf.placeholder(tf.float32)
xs = tf.placeholder(tf.float32, [None, 64])  # 8x8
ys = tf.placeholder(tf.float32, [None, 10])

# add output layer
l1 = add_layer(xs, 64, 50, 'l1', activation_function=tf.nn.tanh)
prediction = add_layer(l1, 50, 10, 'l2', activation_function=tf.nn.softmax)

# the loss between prediction and real data
cross_entropy = tf.reduce_mean(-tf.reduce_sum(ys * tf.log(prediction),
                                              reduction_indices=[1]))  # loss
tf.summary.scalar('loss', cross_entropy)
train_step = tf.train.GradientDescentOptimizer(0.5).minimize(cross_entropy)

sess = tf.Session()
merged  = tf.summary.merge_all()##合并summary
 #summary writer goes in here
train_writer = tf.summary.FileWriter("logs/train", sess.graph)
test_writer = tf.summary.FileWriter("logs/test", sess.graph)

sess.run(tf.initialize_all_variables())

for i in range(500):
    # here to determine the keeping probability
    sess.run(train_step, feed_dict={xs: X_train, ys: y_train, keep_prob: 0.5})#保持50%的概率不被dropout掉
    if i % 50 == 0:
#        # record loss
        train_result = sess.run(merged, feed_dict={xs: X_train, ys: y_train, keep_prob: 1})
        test_result = sess.run(merged, feed_dict={xs: X_test, ys: y_test, keep_prob: 1})
        train_writer.add_summary(train_result, i)
        test_writer.add_summary(test_result, i)

运行后，会在相应的目录里生成一个文件，执行：

windows用户需要使用$activate TensorFlow
$tensorboard --logdir="/目录"（logs）