TensorFlow基础笔记(9) Tensorboard可视化显示

参考: http://blog.csdn.net/l18930738887/article/details/55000008

http://www.jianshu.com/p/19bb60b52dad

http://blog.csdn.net/sinat_33761963/article/details/62433234

import tensorflow as tf
import numpy as np
def add_layer(inputs, in_size, out_size, n_layer, activation_function=None):
# add one more layer and return the output of this layer
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.add(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='input_x')
ys = tf.placeholder(tf.float32, [None, 1],name='input_y')

# 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=2, activation_function=None)

# the error between prediciton and real data
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)

sess = tf.Session()
merged = tf.summary.merge_all()
# save the logs
writer = tf.summary.FileWriter("logs/", sess.graph)
sess.run(tf.global_variables_initializer())
for i in range(1000):
# training
sess.run(train_step, feed_dict={xs: x_data, ys: y_data})
if i % 50 == 0:
# to see the step improvement
result = sess.run(merged,
feed_dict={xs: x_data, ys: y_data})
writer.add_summary(result, i)

到运行python的所在目录下，打一下命令：

$ tensorboard --logdir="logs/"

再在网页中输入链接：127.0.1.1:6006 即可获得展示： 推荐使用friefox浏览器，我电脑上chrom浏览器打不开

比如，从他人处获得一个Graph，想看看它的结构，怎么弄？

Google提供了一个工具，TensorBoard，它能以图表的方式分析你在训练过程中汇总的各种数据，其中包括Graph结构。

所以我们可以简单的写几行Pyhton，加载Graph，只在logdir里，输出Graph结构数据，并可以查看其图结构。

可参考：http://www.tensorfly.cn/tfdoc/how_tos/summaries_and_tensorboard.html

https://www.tensorflow.org/get_started/summaries_and_tensorboard

你可以在jupyter里操作，代码如下：

import tensorflow as tf
from tensorflow.python.platform import gfile

# 这是从二进制格式的pb文件加载模型
graph = tf.get_default_graph()
graphdef = graph.as_graph_def()
graphdef.ParseFromString(gfile.FastGFile("/data/TensorFlowAndroidMNIST/app/src/main/expert-graph.pb", "rb").read())
_ = tf.import_graph_def(graphdef, name="")

#这是从文件格式的meta文件加载模型

_ = tf.train.import_meta_graph("model.ckpt.meta")

summary_write = tf.summary.FileWriter("/data/TensorFlowAndroidMNIST/logdir" , graph)

然后再启动tensorboard：

tensorboard --logdir /data/TensorFlowAndroidMNIST/logdir --host 你的ip --port 你端口(默认6006)