TensorFlow学习（七）

TensorFlow学习（七）tensorboard可视化神经网络结构查看网络运行的数据

TensorFlow学习（七）

tensorboard

可视化神经网络结构

变化的地方有两处（详情见代码，代码仍然用之前识别手写数字的代码）： （1）定义一个命名空间：tf.name_scope() （2）将生成的图，存储： writer = tf.summary.FileWriter('logs/',sess.graph)

其中’logs/'为当前文件夹下，创建一个名为logs的文件夹，图存放在其中。

打开cmd,进入图存放的盘中 本例图存放地址为：E:\anaconda\test1\logs 所以命令为： C:\Users\Z6000>e: 然后输入命令： E:\>tensorboard --logdir=E:\anaconda\test1\logs 得到网址，例如：

然后在网页（建议用谷歌浏览器）中输入网址，就可以看到可视化结果。 如果输入上述命令，出现如下错误：

TensorBoard 1.14.0 at http://LAPTOP-K843PQKN:6006/ (Press CTRL+C to quit)

则需要指定路径：

E:\>tensorboard --logdir=E:\anaconda\test1\logs --host=127.0.0.1

得到的可视化结果如下： 鼠标左键可以移动图片，滚轮可以放大缩小图片。 3. 具体代码如下：

import tensorflow as tf import numpy as np from tensorflow.examples.tutorials.mnist import input_data#载入数据集 mnist = input_data.read_data_sets("MNIST_data",one_hot=True) batch_size = 100 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 W1 = tf.Variable(tf.random_normal([784,500])) b1 = tf.Variable(tf.random_normal([1,500])) L1 = tf.matmul(x,W1)+b1 LL1 = tf.nn.tanh(L1) #LL1 = tf.nn.sigmoid(L1) W2 = tf.Variable(tf.zeros([500,10])) b2 = tf.Variable(tf.zeros([10])) L2 = tf.matmul(LL1,W2)+b2 prediction = tf.nn.softmax(L2) loss = tf.reduce_mean(tf.square(y-prediction)) train_step = tf.train.GradientDescentOptimizer(0.3).minimize(loss) #初始化变量 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)) with tf.Session() as sess: sess.run(init) writer = tf.summary.FileWriter('logs/',sess.graph) for epoch in range(2): for batch in range(n_batch): batch_xs,batch_ys = mnist.train.next_batch(batch_size) sess.run(train_step,feed_dict={x:batch_xs,y:batch_ys}) acc = sess.run(accuracy,feed_dict={x:mnist.test.images,y:mnist.test.labels}) print("Iter " + str(epoch) + ",Testing Accuracy " + str(acc))

查看网络运行的数据

在上述代码中添加： # 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

之后再添加要查看的值：

variable_summaries(W2)

然后合并所有的summary

merged = tf.summary.merge_all()

最后更改：

with tf.Session() as sess: sess.run(init) writer = tf.summary.FileWriter('logs/',sess.graph) 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}) writer.add_summary(summary,epoch) acc = sess.run(accuracy,feed_dict={x:mnist.test.images,y:mnist.test.labels}) print("Iter " + str(epoch) + ",Testing Accuracy " + str(acc))

运行后得到结果再网页中查看：

完整代码如下： import tensorflow as tf import numpy as np from tensorflow.examples.tutorials.mnist import input_data#载入数据集``` mnist = input_data.read_data_sets("MNIST_data",one_hot=True) batch_size = 100 n_batch = mnist.train.num_examples // batch_size 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'): #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('W1'): W1 = tf.Variable(tf.random_normal([784,500]),name='W1') variable_summaries(W1) with tf.name_scope('b1'): b1 = tf.Variable(tf.random_normal([1,500]),name='b1') variable_summaries(b1) with tf.name_scope('wx_plus_b1'): L1 = tf.matmul(x,W1)+b1 LL1 = tf.nn.tanh(L1) #LL1 = tf.nn.sigmoid(L1) with tf.name_scope('W2'): W2 = tf.Variable(tf.zeros([500,10]),name='W2') variable_summaries(W2) with tf.name_scope('b2'): b2 = tf.Variable(tf.zeros([10]),name='b2') variable_summaries(b2) with tf.name_scope('wx_plus_b2'): L2 = tf.matmul(LL1,W2)+b2 prediction = tf.nn.softmax(L2) with tf.name_scope('loss'): loss = tf.reduce_mean(tf.square(y-prediction)) tf.summary.scalar('loss',loss) with tf.name_scope('train'): train_step = tf.train.GradientDescentOptimizer(0.3).minimize(loss) #初始化变量 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)) 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(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}) writer.add_summary(summary,epoch) acc = sess.run(accuracy,feed_dict={x:mnist.test.images,y:mnist.test.labels}) print("Iter " + str(epoch) + ",Testing Accuracy " + str(acc))