TensorBoard:可视化学习

TensorBoard:可视化学习

1. 数据序列化

如何将数据序列化，使之图表可视化？

对于一个简单的神经网络，如下所示：

import tensorflow as tf
import numpy as np 

def add_layer(inputs, in_size, out_size, activation_function=None):
	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
	if activation_function is None:
		outputs = Wx_plus_b
	else:
		outputs = activation_function(Wx_plus_b)
	return outputs

# make up some real data
x_data = np.linspace(-1,1,300)[:, np.newaxis]
noise = np.random.normal(0, 0.05, x_data.shape)
y_data = np.square(x_data) - 0.5 + noise

# define placeholder for inputs to network
xs = tf.placeholder(tf.float32, [None, 1])
ys = tf.placeholder(tf.float32, [None, 1])

# add hidden layer
l1 = add_layer(xs, 1, 10, activation_function=tf.nn.relu)

# add output layer
prediction = add_layer(l1, 10, 1, activation_function=None)

# loss and Optimizer
loss = tf.reduce_mean(tf.reduce_sum(tf.square(ys - prediction), reduction_indices=[1]))
train_step = tf.train.GradientDescentOptimizer(0.1).minimize(loss)

# start
init = tf.global_variables_initializer()
sess = tf.Session()
sess.run(init)

for i in range(1000):
	#train
	sess.run(train_step, feed_dict={xs:x_data, ys:y_data})
	if i % 50 == 0:
		print(sess.run(loss, feed_dict={xs:x_data, ys:y_data}))

---

对W、b、loss、train这些元素进行数据序列化。

比如对于Weights，进行修改：

由

Weights = tf.Variable(tf.random_normal([in_size, out_size]))

修改为：

with tf.name_scope('weights'):

Weights = tf.Variable(tf.random_normal([in_size, out_size]), name='W')

tf.summary.histogram(layer_name + '/weights', Weights)

整体修改的代码如下：

import tensorflow as tf
import numpy as np 

def add_layer(inputs, in_size, out_size, n_layer, activation_function=None):
	layer_name = 'layer%s' % n_layer
	with tf.name_scope(layer_name):
		with tf.name_scope('weights'):
			Weights = tf.Variable(tf.random_normal([in_size, out_size]), name='W')
			tf.summary.histogram(layer_name + '/weights', Weights)
		with tf.name_scope('biases'):
			biases = tf.Variable(tf.zeros([1,out_size]) + 0.1, name='b')
			tf.summary.histogram(layer_name + '/biases', biases)
		with tf.name_scope('Wx_plus_b'):
			Wx_plus_b = tf.matmul(inputs, Weights) + biases
		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

# make up some real data
x_data = np.linspace(-1,1,300)[:, np.newaxis]
noise = np.random.normal(0, 0.05, x_data.shape)
y_data = np.square(x_data) - 0.5 + noise

# define placeholder for inputs to network
with tf.name_scope('inputs'):
	xs = tf.placeholder(tf.float32, [None, 1], name='x_input')
	ys = tf.placeholder(tf.float32, [None, 1], name='y_input')

# add hidden layer
l1 = add_layer(xs, 1, 10, n_layer=1, activation_function=tf.nn.relu)

# add output layer
prediction = add_layer(l1, 10, 1, n_layer=1, activation_function=None)

# loss and Optimizer
with tf.name_scope('loss'):
	loss = tf.reduce_mean(tf.reduce_sum(tf.square(ys - prediction), reduction_indices=[1]))
	tf.summary.scalar('loss', loss)
with tf.name_scope('train'):
	train_step = tf.train.GradientDescentOptimizer(0.1).minimize(loss)

# start
init = tf.global_variables_initializer()
sess = tf.Session()
merged = tf.summary.merge_all()

writer = tf.summary.FileWriter('D:/Projects/TensorBoard/logs/', sess.graph)
sess.run(init)

for i in range(1000):
	#train
	sess.run(train_step, feed_dict={xs:x_data, ys:y_data})
	if i % 50 == 0:
		result = sess.run(merged, feed_dict={xs:x_data, ys:y_data})
		writer.add_summary(result, i)

---

2. 启动TensorBoard

1. 在命令提示符中运行：python ***.py，在文件夹中生成TensorFlow 图

2. 在命令提示符中运行：tensorboard --logdir=/path/to/log-directory。

这里的参数 logdir 指向 SummaryWriter 序列化数据的存储路径。如果logdir目录的子目录中包含另一次运行时的数据，那么 TensorBoard 会展示所有运行的数据。

3. 一旦 TensorBoard 开始运行，你可以通过在浏览器中输入  localhost:6006  来查看 TensorBoard。