Tensorflow学习之TensorBoard

TensorBoard是Tensorflow的一个可视化工具，可以看见整个网络结构，以及将模型训练过程中的各种汇总数据展示出来，包括标量、图片、音频、计算图、数据分布、直方图和嵌入向量。

下面利用Mnist数据在MLP多层神经网络上训练得到的日志文件logs转入TensorBoard中进行数据可视化。

import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
max_step = 1000
learning_rate = 0.001
dropout = 0.9
data_dir = '/usr/local/Cellar/anaconda/lib/python3.6/site-packages/tensorflow/examples/tutorials/mnist/input_data'
log_dir = '/usr/local/Cellar/anaconda/lib/python3.6/site-packages/tensorflow/examples/tutorials/mnist/logs/mnist_with_summaries'

mnist = input_data.read_data_sets(data_dir,one_hot=True)
sess = tf.InteractiveSession()
#为了在TensorBoard中展示节点名称，设计网络时经常食用with tf.name scope 限定命名空间，在这个with下的所有节点都会被自动命名为input/xxx这样的格式
#下面定义输入x和y的placeholder，并将输入的一维数据变形为28x28的图片存储到另一个tensor，这样就可以使用tf.summary.image将图片数据汇总给TensorBoard展示了
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')
with tf.name_scope('input_reshape'):
image_shaped_input = tf.reshape(x,[-1,28,28,1]) #-1代表自动计算的数组元素的个数，28代表元素尺寸为28x28，1代表颜色通道数
tf.summary.image('input',image_shaped_input,10)
def weight_variable(shape):
initial = tf.truncated_normal(shape,stddev = 0.1)
return tf.Variable(initial)
def bias_variable(shape):
initial = tf.constant(0.1,shape = shape)
return tf.Variable(initial)
#再定义对Variable变量的数据汇总函数，对这些标量数据使用tf.summary.scalar进行记录和汇总，同时使用tf.summary.histogram直接记录变量的直方图数据
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)
#利用MLP多层神经网络来训练数据，每一层都对模型参数进行数据汇总
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('pre_activations',preactivate)
activations = act(preactivate,name = 'activation')
tf.summary.histogram('activations',activations)
return activations
hidden1 = nn_layer(x,784,500,'layer1')

with tf.name_scope('dropout'):
keep_prob = tf.placeholder(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) #identity表示激活函数用全等映射

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)

#在使用Adma优化器对损失进行优化
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)

#直接获取所有汇总操作，定义两个文件记录器tf.summary.FileWriter在不同的子目录，分别用来存放训练和测试的日志数据，同时将Session的计算图sess.graph加入训练过程的记录器
merged = tf.summary.merge_all()
train_writer = tf.summary.FileWriter(log_dir + '/train',sess.graph)
test_writer = tf.summary.FileWriter(log_dir + '/test')
tf.global_variables_initializer().run()

#定义损失函数
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}
#最后一步，实际执行具体的训练、测试和日志记录的操作
saver = tf.train.Saver() #创建模型的保存器
for i in range(max_step):
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) #定义运行选项
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)
print('Adding run metadata for', 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()

然后再Terminal中运行

tensorboard --logdir=/usr/local/Cellar/anaconda/lib/python3.6/site-packages/tensorflow/examples/tutorials/mnist/logs/mnist_with_summaries

可以看到

WARNING:tensorflow:Found more than one graph event per run, or there was a metagraph containing a graph_def, as well as one or more graph events.  Overwriting the graph with the newest event.
WARNING:tensorflow:Found more than one metagraph event per run. Overwriting the metagraph with the newest event.
Starting TensorBoard b'54' at http://NewMac.local:6006 (Press CTRL+C to quit)

之后复制粘贴最后的网址即可进入TensorBoard观看各种数据形式。