TensorFlow学习笔记（6）----TensorBoard_1

以一个曲线拟合的小例子说明要使用TensorBoard，需要对程序添加那些额外的东西。程序：

import tensorflow as tf
import numpy as np

# Create 100 phony x, y data points in NumPy, y = x * 0.1 + 0.3
x_data = np.random.rand(1000,1).astype(np.float32)
y_data = tf.sin(x_data)*tf.cos(x_data)+tf.random_uniform([1000,1], -0.1, 0.1)


#graph
X = tf.placeholder(tf.float32,[None,1],name = 'X-input')
Y = tf.placeholder(tf.float32,[None,1],name = 'Y-input')

W1 = tf.Variable(tf.random_uniform([1,5], -1.0, 1.0),name = 'weight1')
W2 = tf.Variable(tf.random_uniform([5,2], -1.0, 1.0),name = 'weight2')
W3 = tf.Variable(tf.random_uniform([2,1], -1.0, 1.0),name = 'weight3')

b1 = tf.Variable(tf.zeros([5]), name = 'bias1')
b2 = tf.Variable(tf.zeros([2]), name = 'bias2')
b3 = tf.Variable(tf.zeros([1]), name = 'bias3')

with tf.name_scope('layer2') as scope:
	L2 = tf.sigmoid(tf.matmul(X,W1)+b1)

with tf.name_scope('layer3') as scope:
	L3 = tf.sigmoid(tf.matmul(L2,W2)+b2)

with tf.name_scope('layer4') as scope:
	hypothesis = tf.sigmoid(tf.matmul(L3,W3)+b3)

with tf.name_scope('cost') as scope:
	cost = -tf.reduce_mean(Y*tf.log(hypothesis))
	cost_summery = tf.scalar_summary("cost",cost)

with tf.name_scope('train') as scope:
	optimizer = tf.train.GradientDescentOptimizer(0.01)
	train = optimizer.minimize(cost)

#the summery
w1_hist = tf.histogram_summary("weight1",W1)
w2_hist = tf.histogram_summary("weight2",W2)
b1_hist = tf.histogram_summary("bisa1",b1)
b2_hist = tf.histogram_summary("bisa2",b2)
y_hist = tf.histogram_summary("y",Y)

init = tf.initialize_all_variables()

#run
with tf.Session() as sess:

	sess.run(init)
	#the workers who translate data to TensorBoard
	merged = tf.merge_all_summaries() #collect the tf.xxxxx_summary
	writer = tf.train.SummaryWriter('keep',sess.graph) 
        # maybe many writers to show different curvs in the same figure
	for step in range(20000):
		summary, _ = sess.run([merged, train], feed_dict={X:x_data,Y:y_data.eval()})
		writer.add_summary(summary, step)
		if step%10 ==0:
			print('step %s' % (step))

显然，需要给程序的每一部分添加命名空间，名字分类越清楚，最后的图越好看，

scalar_summary和histogram_summary

分别记录单个变量和一组变量

tf.merge_all_summaries()

类似个收集节点，执行这个节点就表示这个图里面的变量都要收集一遍等待传递给显示文件。

tf.train.SummaryWriter和add_summary

与上面的函数是配合的，可以把刚才收集的变量正式写进去硬盘文件中（这个文件是网页显示Figure的数据），每次add添加进去数据

然后是启动TensorBoard:

tensorboard --logdir=/home/ xxxxxxxxx /keep

就是告诉tensorboard从哪里读取数据，和writed的目录一样，打开网址：http://0.0.0.0:6006，就可以看到生成的图表