tensorflow之tensorboard

参考https://www.cnblogs.com/felixwang2/p/9184344.html

边学习，边练习

 # https://www.cnblogs.com/felixwang2/p/9184344.html
 # TensorFlow(七)：tensorboard网络执行
 # MNIST数据集 手写数字
 import tensorflow as tf
 from tensorflow.examples.tutorials.mnist import input_data

 # 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

 # 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]),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'):
     # 二次代价函数
     loss=tf.reduce_mean(tf.square(y-prediction))
     tf.summary.scalar('loss',loss) # 一个值就不用调用函数了
 with tf.name_scope('train'):
     # 使用梯度下降法
     train_step=tf.train.GradientDescentOptimizer(0.2).minimize(loss)

 # 初始化变量
 init=tf.global_variables_initializer()

 with tf.name_scope('accuracy'):
     with tf.name_scope('correct_prediction'):
         # 求最大值在哪个位置，结果存放在一个布尔值列表中
         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作用是将布尔值转换为浮点型。
         tf.summary.scalar('accuracy',accuracy) # 一个值就不用调用函数了

 # 合并所有的summary
 merged=tf.summary.merge_all()

 gpu_options = tf.GPUOptions(allow_growth=True)
 with tf.Session(config=tf.ConfigProto(gpu_options=gpu_options)) as sess:
     sess.run(init)
     writer=tf.summary.FileWriter('logs/',sess.graph) # 写入文件

     for epoch in range(10):
         for batch in range(n_batch):
             batch_xs,batch_ys=mnist.train.next_batch(batch_size)
             summary,_=sess.run([merged,train_step],feed_dict={x:batch_xs,y:batch_ys})

         # 添加样本点
         writer.add_summary(summary,epoch)
         #求准确率
         acc=sess.run(accuracy,feed_dict={x:mnist.test.images,y:mnist.test.labels})
         print('Iter:'+str(epoch)+',Testing Accuracy:'+str(acc))

在命令窗口，使用命令 tensorboard --logdir=F:\document\spyder-py3\study_tensor\logs

生成一个地址可以查看训练中间数据

PS F:\document\spyder-py3\study_tensor> tensorboard --logdir=F:\document\spyder-py3\study_tensor\logs
f:\programdata\anaconda3\envs\py35\lib\site-packages\h5py\__init__.py:: FutureWarning: Conversion of the second argument of issubdtype from `float` to `np.floating` is deprecated. In future, it will be treated as `np.float64 == np.dtype(float).type`.
  from ._conv import register_converters as _register_converters
TensorBoard 1.10. at http://KOTIN:6006 (Press CTRL+C to quit)

在网页输入

http://KOTIN:6006
或者输入

http://localhost:6006
就可以看到生成的状态图：