# 【tensorflow 深度学习】4.tensorboard可视化

xiaoxiao2021-02-28  4

1.上篇博客程序优化：主要是将学习率设置为逐渐减小

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 #定义两个placeholder x = tf.placeholder(tf.float32,[None,784]) y = tf.placeholder(tf.float32,[None,10]) keep_prob=tf.placeholder(tf.float32) lr = tf.Variable(0.001, dtype=tf.float32) #创建一个简单的神经网络 W1 = tf.Variable(tf.truncated_normal([784,500],stddev=0.1)) b1 = tf.Variable(tf.zeros([500])+0.1) L1 = tf.nn.tanh(tf.matmul(x,W1)+b1) L1_drop = tf.nn.dropout(L1,keep_prob) W2 = tf.Variable(tf.truncated_normal([500,300],stddev=0.1)) b2 = tf.Variable(tf.zeros([300])+0.1) L2 = tf.nn.tanh(tf.matmul(L1_drop,W2)+b2) L2_drop = tf.nn.dropout(L2,keep_prob) W3 = tf.Variable(tf.truncated_normal([300,10],stddev=0.1)) b3 = tf.Variable(tf.zeros([10])+0.1) prediction = tf.nn.softmax(tf.matmul(L2_drop,W3)+b3) #交叉熵代价函数 loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=y,logits=prediction)) #训练 train_step = tf.train.AdamOptimizer(lr).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) for epoch in range(51): sess.run(tf.assign(lr, 0.001 * (0.95 ** epoch))) 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,keep_prob:1.0}) learning_rate = sess.run(lr) acc = sess.run(accuracy,feed_dict={x:mnist.test.images,y:mnist.test.labels,keep_prob:1.0}) print ("Iter " + str(epoch) + ", Testing Accuracy= " + str(acc) + ", Learning Rate= " + str(learning_rate))

2.tensorboard绘制网络结构

import tensorflow as tf from tensorflow.examples.tutorials.mnist import input_data # In[3]: #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"):     with tf.name_scope("weights"):         W = tf.Variable(tf.zeros([784,10]),name='W')     with tf.name_scope("biases"):         b = tf.Variable(tf.zeros([10]),name='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(tf.matmul(x,W)+b) #二次代价函数 with tf.name_scope("loss"):     loss = tf.reduce_mean(tf.square(y-prediction)) #使用梯度下降法 with tf.name_scope("train"):     train_step = tf.train.GradientDescentOptimizer(0.2).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 with tf.name_scope("accuracy"):     with tf.name_scope("correct_prediction"):         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     with tf.name_scope("accuracy"):         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(1):         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))

3.查看网络运行时的数据

import tensorflow as tf from tensorflow.examples.tutorials.mnist import input_data # In[3]: #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 #参数概要 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) #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"):     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) #二次代价函数 with tf.name_scope("loss"):     loss = tf.reduce_mean(tf.square(y-prediction))     tf.summary.scalar('loss',loss) #使用梯度下降法 with tf.name_scope("train"):     train_step = tf.train.GradientDescentOptimizer(0.2).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 with tf.name_scope("accuracy"):     with tf.name_scope("correct_prediction"):         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     with tf.name_scope("accuracy"):         accuracy = tf.reduce_mean(tf.cast(correct_prediction,tf.float32))         tf.summary.scalar('accuracy',accuracy) #合并所有的summary merge=tf.summary.merge_all() with tf.Session() as sess:     sess.run(init)     writer=tf.summary.FileWriter('logs/',sess.graph)     for epoch in range(51):         for batch in range(n_batch):             batch_xs,batch_ys =  mnist.train.next_batch(batch_size)             summary,_=sess.run([merge,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))

4.tensorflow可视化