TensorFlow1.0系统学习（五）————Tensorboard的使用（显示网络结构，各种数据，可视化训练过程）
文章目录
- 一、使用Tensorboard显示网络结构
- 二、使用Tensorboard显示网络运行时的数据
- 三、使用Tensorboard可视化训练过程
一、使用Tensorboard显示网络结构
因为只是为了显示网络结构，故只训练一次就好，不要浪费时间。
首先要定义命名空间
#命名空间
with tf.name_scope('input'):
# 定义两个placeholder
x = tf.placeholder(tf.float32, [None, 784], name='x-input')
y = tf.placeholder(tf.float32, [None, 10], name='y-input')
然后在会话里添加下面代码，为保存的路径。
writer = tf.summary.FileWriter('logs/', sess.graph)
完整代码：
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
# 载入数据集
mnist = input_data.read_data_sets("MNIST_data", one_hot=True)
# 每个批次的大小
batch_size = 100
# 计算一共有多少个批次
n_batch = mnist.train.num_examples // batch_size
#命名空间
with tf.name_scope('input'):
# 定义两个placeholder
x = tf.placeholder(tf.float32, [None, 784], name='x-input')
y = tf.placeholder(tf.float32, [None, 10], name='y-input')
# 创建一个简单的神经网络
W = tf.Variable(tf.zeros([784, 10]))
b = tf.Variable(tf.zeros([10]))
prediction = tf.nn.softmax(tf.matmul(x, W) + b)
#交叉熵代价函数（cross-entropy）和softmax搭配
loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=y, logits=prediction))
# 使用梯度下降法
train_step = tf.train.GradientDescentOptimizer(0.2).minimize(loss)
init = tf.global_variables_initializer()
# 结果存放在一个布尔型列表中
correct_prediction = tf.equal(tf.argmax(y, 1), tf.argmax(prediction, 1)) # argmax返回一维张量中最大的值所在的位置
# 求准确率
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32)) # cast把布尔类型转成浮点型，True为1.0，False为0
with tf.Session() as sess:
sess.run(init)
writer = tf.summary.FileWriter('logs/', sess.graph)
for epoch in range(1): # 训练1个周期
for batch in range(n_batch): # 训练所有的图片一次
batch_xs, batch_ys = mnist.train.next_batch(batch_size) # 获取batch_size大小的图片
sess.run(train_step, feed_dict={x: batch_xs, y: batch_ys})
test_acc = sess.run(accuracy, feed_dict={x: mnist.test.images, y: mnist.test.labels})
train_acc = sess.run(accuracy, feed_dict={x: mnist.train.images, y: mnist.train.labels})
print("epoch： " + str(epoch) + ",Training Accuracy： " + str(train_acc) + ",Testing Accuracy： " + str(test_acc))
训练完得到下面文件：
window下在logs的目录下打开命令行（shift+鼠标右键），输入以下代码
tensorboard --logdir logs --host=127.0.0.1
回车，然后得出
然后在谷歌浏览器上输入：
http://127.0.0.1:6006
此时的网络结构图阅读性不高，因此继续修改。
完整代码：
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
# 载入数据集
mnist = input_data.read_data_sets("MNIST_data", one_hot=True)
# 每个批次的大小
batch_size = 100
# 计算一共有多少个批次
n_batch = mnist.train.num_examples // batch_size
#命名空间
with tf.name_scope('input'):
# 定义两个placeholder
x = tf.placeholder(tf.float32, [None, 784], name='x-input')
y = tf.placeholder(tf.float32, [None, 10], name='y-input')
with tf.name_scope('layer'):
# 创建一个简单的神经网络
with tf.name_scope('wights'):
W = tf.Variable(tf.zeros([784, 10]))
with tf.name_scope('biases'):
b = tf.Variable(tf.zeros([10]))
with tf.name_scope('wx_plus_b'):
wx_plus_b = tf.matmul(x, W) + b
with tf.name_scope('softmax'):
prediction = tf.nn.softmax(wx_plus_b)
with tf.name_scope('loss'):
#交叉熵代价函数（cross-entropy）和softmax搭配
loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=y, logits=prediction))
with tf.name_scope('train'):
# 使用梯度下降法
train_step = tf.train.GradientDescentOptimizer(0.2).minimize(loss)
init = tf.global_variables_initializer()
with tf.name_scope('accuracy'):
with tf.name_scope('correct_prediction'):
# 结果存放在一个布尔型列表中
correct_prediction = tf.equal(tf.argmax(y, 1), tf.argmax(prediction, 1)) # argmax返回一维张量中最大的值所在的位置
with tf.name_scope('accuracy'):
# 求准确率
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32)) # cast把布尔类型转成浮点型，True为1.0，False为0
with tf.Session() as sess:
sess.run(init)
writer = tf.summary.FileWriter('logs/', sess.graph)
for epoch in range(1): # 训练1个周期
for batch in range(n_batch): # 训练所有的图片一次
batch_xs, batch_ys = mnist.train.next_batch(batch_size) # 获取batch_size大小的图片
sess.run(train_step, feed_dict={x: batch_xs, y: batch_ys})
test_acc = sess.run(accuracy, feed_dict={x: mnist.test.images, y: mnist.test.labels})
train_acc = sess.run(accuracy, feed_dict={x: mnist.train.images, y: mnist.train.labels})
print("epoch： " + str(epoch) + ",Training Accuracy： " + str(train_acc) + ",Testing Accuracy： " + str(test_acc))
这样阅读性更高了。
二、使用Tensorboard显示网络运行时的数据
首先定义一个计算函数，用来计算查看权值W和偏置值b的信息：
def variable_summaries(var):
with tf.name_scope('sumaries'):
mean = tf.reduce_mean(var)
tf.summary.scalar('mean', mean) #平均值
with tf.name_scope('stddev'):
stddev = tf.sqrt(tf.reduce_mean(tf.square(var - mean)))
tf.summary.scalar('stddev', stddev) #标准差
tf.summary.scalar('max', tf.reduce_max(var)) #最大值
tf.summary.scalar('min', tf.reduce_min(var)) #最小值
tf.summary.histogram('histogram', var) #直方图
在W，b 的空间窗口下分别加入：
variable_summaries(W)
variable_summaries(b)
在loss的空间窗口下加入：
tf.summary.scalar('loss', loss)
在accuracy的空间窗口下加入：
tf.summary.scalar('accuracy', accuracy)
然后加入汇总：
#合并所有的summary
merged = tf.summary.merge_all()
然后在会话里修改：
summary,_ = sess.run([merged, train_step], feed_dict={x: batch_xs, y: batch_ys}) #merged 会有返回值，存在summary里面
writer.add_summary(summary, epoch)
完整代码：
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
# 载入数据集
mnist = input_data.read_data_sets("MNIST_data", one_hot=True)
# 每个批次的大小
batch_size = 100
# 计算一共有多少个批次
n_batch = mnist.train.num_examples // batch_size
def variable_summaries(var):
with tf.name_scope('sumaries'):
mean = tf.reduce_mean(var)
tf.summary.scalar('mean', mean) #平均值
with tf.name_scope('stddev'):
stddev = tf.sqrt(tf.reduce_mean(tf.square(var - mean)))
tf.summary.scalar('stddev', stddev) #标准差
tf.summary.scalar('max', tf.reduce_max(var)) #最大值
tf.summary.scalar('min', tf.reduce_min(var)) #最小值
tf.summary.histogram('histogram', var) #直方图
#命名空间
with tf.name_scope('input'):
# 定义两个placeholder
x = tf.placeholder(tf.float32, [None, 784], name='x-input')
y = tf.placeholder(tf.float32, [None, 10], name='y-input')
with tf.name_scope('layer'):
# 创建一个简单的神经网络
with tf.name_scope('wights'):
W = tf.Variable(tf.zeros([784, 10]))
variable_summaries(W)
with tf.name_scope('biases'):
b = tf.Variable(tf.zeros([10]))
variable_summaries(b)
with tf.name_scope('wx_plus_b'):
wx_plus_b = tf.matmul(x, W) + b
with tf.name_scope('softmax'):
prediction = tf.nn.softmax(wx_plus_b)
with tf.name_scope('loss'):
#交叉熵代价函数（cross-entropy）和softmax搭配
loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=y, logits=prediction))
tf.summary.scalar('loss', loss)
with tf.name_scope('train'):
# 使用梯度下降法
train_step = tf.train.GradientDescentOptimizer(0.2).minimize(loss)
init = tf.global_variables_initializer()
with tf.name_scope('accuracy'):
with tf.name_scope('correct_prediction'):
# 结果存放在一个布尔型列表中
correct_prediction = tf.equal(tf.argmax(y, 1), tf.argmax(prediction, 1)) # argmax返回一维张量中最大的值所在的位置
with tf.name_scope('accuracy'):
# 求准确率
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32)) # cast把布尔类型转成浮点型，True为1.0，False为0
tf.summary.scalar('accuracy', accuracy)
#合并所有的summary
merged = tf.summary.merge_all()
with tf.Session() as sess:
sess.run(init)
writer = tf.summary.FileWriter('logs/', sess.graph)
for epoch in range(51): # 训练1个周期
for batch in range(n_batch): # 训练所有的图片一次
batch_xs, batch_ys = mnist.train.next_batch(batch_size) # 获取batch_size大小的图片
summary,_ = sess.run([merged, train_step], feed_dict={x: batch_xs, y: batch_ys}) #merged 会有返回值，存在summary里面
writer.add_summary(summary, epoch)
test_acc = sess.run(accuracy, feed_dict={x: mnist.test.images, y: mnist.test.labels})
train_acc = sess.run(accuracy, feed_dict={x: mnist.train.images, y: mnist.train.labels})
print("epoch： " + str(epoch) + ",Training Accuracy： " + str(train_acc) + ",Testing Accuracy： " + str(test_acc))
然后打开：http://127.0.0.1:6006
可以看到：
三、使用Tensorboard可视化训练过程
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
from tensorflow.contrib.tensorboard.plugins import projector
#载入数据集
mnist = input_data.read_data_sets("MNIST_data/",one_hot=True)
#运行次数
max_steps = 1001
#图片数量
image_num = 3000
#当前py文件路径
DIR = "D:/Tensorflow/"
#定义会话
sess = tf.Session()
#载入图片
embedding = tf.Variable(tf.stack(mnist.test.images[:image_num]), trainable=False, name='embedding')
#参数概要
def variable_summaries(var):
with tf.name_scope('summaries'):
mean = tf.reduce_mean(var)
tf.summary.scalar('mean', mean)#平均值
with tf.name_scope('stddev'):
stddev = tf.sqrt(tf.reduce_mean(tf.square(var - mean)))
tf.summary.scalar('stddev', stddev)#标准差
tf.summary.scalar('max', tf.reduce_max(var))#最大值
tf.summary.scalar('min', tf.reduce_min(var))#最小值
tf.summary.histogram('histogram', var)#直方图
#命名空间
with tf.name_scope('input'):
#这里的none表示第一个维度可以是任意的长度
x = tf.placeholder(tf.float32,[None,784],name='x-input')
#正确的标签
y = tf.placeholder(tf.float32,[None,10],name='y-input')
#显示图片
with tf.name_scope('input_reshape'):
image_shaped_input = tf.reshape(x, [-1, 28, 28, 1])
tf.summary.image('input', image_shaped_input, 10)
with tf.name_scope('layer'):
#创建一个简单神经网络
with tf.name_scope('weights'):
W = tf.Variable(tf.zeros([784,10]),name='W')
variable_summaries(W)
with tf.name_scope('biases'):
b = tf.Variable(tf.zeros([10]),name='b')
variable_summaries(b)
with tf.name_scope('wx_plus_b'):
wx_plus_b = tf.matmul(x,W) + b
with tf.name_scope('softmax'):
prediction = tf.nn.softmax(wx_plus_b)
with tf.name_scope('loss'):
#交叉熵代价函数
loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=y,logits=prediction))
tf.summary.scalar('loss',loss)
with tf.name_scope('train'):
#使用梯度下降法
train_step = tf.train.GradientDescentOptimizer(0.5).minimize(loss)
#初始化变量
sess.run(tf.global_variables_initializer())
with tf.name_scope('accuracy'):
with tf.name_scope('correct_prediction'):
#结果存放在一个布尔型列表中
correct_prediction = tf.equal(tf.argmax(y,1),tf.argmax(prediction,1))#argmax返回一维张量中最大的值所在的位置
with tf.name_scope('accuracy'):
#求准确率
accuracy = tf.reduce_mean(tf.cast(correct_prediction,tf.float32))#把correct_prediction变为float32类型
tf.summary.scalar('accuracy',accuracy)
#产生metadata文件
if tf.gfile.Exists(DIR + 'projector/projector/metadata.tsv'):
tf.gfile.DeleteRecursively(DIR + 'projector/projector/metadata.tsv')
with open(DIR + 'projector/projector/metadata.tsv', 'w') as f:
labels = sess.run(tf.argmax(mnist.test.labels[:],1))
for i in range(image_num):
f.write(str(labels[i]) + '\n')
#合并所有的summary
merged = tf.summary.merge_all()
projector_writer = tf.summary.FileWriter(DIR + 'projector/projector',sess.graph)
saver = tf.train.Saver()
config = projector.ProjectorConfig()
embed = config.embeddings.add()
embed.tensor_name = embedding.name
embed.metadata_path = DIR + 'projector/projector/metadata.tsv'
embed.sprite.image_path = DIR + 'projector/data/mnist_10k_sprite.png'
embed.sprite.single_image_dim.extend([28,28])
projector.visualize_embeddings(projector_writer,config)
for i in range(max_steps):
#每个批次100个样本
batch_xs,batch_ys = mnist.train.next_batch(100)
run_options = tf.RunOptions(trace_level=tf.RunOptions.FULL_TRACE)
run_metadata = tf.RunMetadata()
summary,_ = sess.run([merged,train_step],feed_dict={x:batch_xs,y:batch_ys},options=run_options,run_metadata=run_metadata)
projector_writer.add_run_metadata(run_metadata, 'step%03d' % i)
projector_writer.add_summary(summary, i)
if i%100 == 0:
acc = sess.run(accuracy,feed_dict={x:mnist.test.images,y:mnist.test.labels})
print ("Iter " + str(i) + ", Testing Accuracy= " + str(acc))
saver.save(sess, DIR + 'projector/projector/a_model.ckpt', global_step=max_steps)
projector_writer.close()
sess.close()
