tensorflow之tensorboard

tensorflow之tensorboard

前言

tensorboard是TensorFlow中自带的一个数据可视化工具，在安装TensorFlow的同时，系统会自动安装。

在不同的TensorFlow版本中，记录训练过程所需要的API也不一样，

1.3

主要需要

summary

，而之前的版本，则直接封装在了

tf

下面

在使用tensorboard时，必须使用

name_scope

来创建一个域，然后在每个域内定义变量的名称。

tf.summary

中提供了一系列函数，用来帮忙统计。

histogram

用来绘制直方图。

scale

用来统计标量

除此之外，还需要用到

tf.summary.merge_all

用来一次性生成所有摘要

tf.summary.Filewriter

用来生成一个写入的文件夹（训练结果和测试结果可以放在不同的文件夹中）

add_summary

讲新生成的

summer

写入记录器

代码

# -*- coding: utf-8 -*-
"""
Created on Wed Oct 25 11:41:50 2017

@author: Sky_Gao
"""

import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
max_steps = 100
learning_rate = 0.001
dropout = 0.9
data_dir = 'MNIST_data/'
log_dir = 'mnist_with_summaries/'
# 定义一个存储的目录

mnist = input_data.read_data_sets(data_dir, one_hot=True)
sess = tf.InteractiveSession()

def weight_variable(shape):
inital = tf.truncated_normal(shape=shape, stddev=0.1)
return tf.Variable(inital)

def bias_variable(shape):
initial = tf.constant(0.1, shape
4000
=shape)
return tf.Variable(initial)

with tf.name_scope('input'):
x = tf.placeholder(tf.float32, [None, 784], name='x-input')
y_ = tf.placeholder(tf.float32, [None, 10], name='y-input')
# 定义输入域，并在其中利用placeholder实现占位
#
with tf.name_scope('input_reshape'):
image_shaped_input = tf.reshape(x, [-1, 28, 28, 1])
tf.summary.image('input', image_shaped_input, 10)

def Variable_summaries(var):
with tf.name_scope('summaries'):
mean = tf.reduce_mean(var)
tf.summary.scalar('mean', mean)
with tf.name_scope('stddev'):
stddev = tf.sqrt(tf.reduce_mean(tf.square(var - mean)))
tf.summary.scalar('stddev', stddev)
tf.summary.scalar('max', tf.reduce_max(var))
tf.summary.scalar('min', tf.reduce_min(var))
tf.summary.histogram('histogram', var)

def nn_layer(input_tensor, input_dim, output_dim, layer_name, act=tf.nn.relu):
with tf.name_scope(layer_name):
with tf.name_scope('weights'):
weights = weight_variable([input_dim, output_dim])
Variable_summaries(weights)
with tf.name_scope('biases'):
biases = bias_variable([output_dim])
Variable_summaries(biases)

with tf.name_scope('Wx_plus_b'):
preactivate = tf.matmul(input_tensor, weights) + biases
tf.summary.histogram('preactivate', preactivate)

activations = act(preactivate, name='activations')
tf.summary.histogram('activations', activations)

return activations

hidden1 = nn_layer(x, 784, 500, 'layer1')

with tf.name_scope('dropout'):
keep_prob = tf.placeholder(dtype=tf.float32)
tf.summary.scalar('dropout_keep_probability', keep_prob)
dropped = tf.nn.dropout(hidden1, keep_prob)

y = nn_layer(dropped, 500, 10, 'layer2', act=tf.identity)

with tf.name_scope('cross_entropy'):
diff = tf.nn.softmax_cross_entropy_with_logits(logits=y, labels=y_)
with tf.name_scope('total'):
cross_entropy = tf.reduce_mean(diff)

tf.summary.scalar('cross_entropy', cross_entropy)

with tf.name_scope('train'):
train_step = tf.train.AdamOptimizer(learning_rate).minimize(cross_entropy)

with tf.name_scope('accuracy'):
with tf.name_scope('correct_prediction'):
correct_prediction = tf.equal(tf.argmax(y, 1), tf.argmax(y_, 1))

with tf.name_scope('accuracy'):
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))

tf.summary.scalar('accuracy', accuracy)

#merge = tf.summary.merge_all()

with tf.Session() as sess:

merged = tf.summary.merge_all()
#定义合并变量操作，一次性生成所有摘要数据
#    sess.run(merged)
train_writer = tf.summary.FileWriter(log_dir + '/train', sess.graph)
test_writer = tf.summary.FileWriter(log_dir + '/test', sess.graph)
tf.global_variables_initializer().run()

def feed_dict(train):
if train:
xs, ys = mnist.train.next_batch(100)
k = dropout
else:
xs, ys = mnist.test.images, mnist.test.labels
k = 1.0

return {x: xs, y_:ys, keep_prob:k}

saver = tf.train.Saver()

for i in range(max_steps):
if i % 10 == 0:
summary, acc = sess.run([merged, accuracy], feed_dict=feed_dict(False))
test_writer.add_summary(summary, i)
print('accuracy at step %s : %s' % (i, acc))
else:
if i % 100 == 99:
run_options = tf.RunOptions(trace_level=tf.RunOptions.FULL_TRACE)
run_metadata = tf.RunMetadata()
summary, _ = sess.run([merged, train_step], feed_dict=feed_dict(True),
options=run_options, run_metadata=run_metadata)
train_writer.add_run_metadata(run_metadata, 'step%03d' % i)
train_writer.add_summary(summary, i)
saver.save(sess, log_dir+"/model.ckpt", i)
else:
summary, _ = sess.run([merged, train_step], feed_dict=feed_dict(True))
train_writer.add_summary(summary, i)

train_writer.close()
test_writer.close()
#sess.close()