启动tensorboard
tensorboard --logdir="log path" 一般是在模型跑完了以后，再进行启动，并且log path要和模型中的路径一样。
记录数据和画图
结构图：
直接使用以上代码生成一个带可展开符号的一个域，并且支持嵌套操作：
with tf.name_scope(layer_name): with tf.name_scope(‘weights‘):
节点一般是变量或常量，需要加一个“name=‘’”参数，才会展示和命名，如：
with tf.name_scope(‘weights‘): Weights = tf.Variable(tf.random_normal([in_size,out_size]))
变量：
变量则可使用Tensorflow.histogram_summary()方法：
tf.histogram_summary(layer_name+"/weights",Weights) #name命名，Weights赋值
常量：
常量则可使用Tensorflow.scalar_summary()方法：
tf.scalar_summary(‘loss‘,loss) #命名和赋值
展示：
最后需要整合和存储SummaryWriter：
#合并到Summary中 merged = tf.merge_all_summaries() #选定可视化存储目录 writer = tf.train.SummaryWriter("/目录",sess.graph)
merged也是需要run的，因此还需要：
result = sess.run(merged) #merged也是需要run的 writer.add_summary(result,i)
执行：
运行后，会在相应的目录里生成一个文件，执行：
tensorboard --logdir="/目录"
下面是示例代码：
#encoding=utf-8 import tensorflow as tf from tensorflow.examples.tutorials.mnist import input_data mnist = input_data.read_data_sets(‘MNIST_data/‘, one_hot=True) 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) # scalar用于记录数值，histogram用于记录训练过程中记录的数据的分布图，也可以用scalar来存储 myGraph = tf.Graph() with myGraph.as_default(): with tf.name_scope(‘inputsAndLabels‘): x_raw = tf.placeholder(tf.float32, shape=[None, 784]) y = tf.placeholder(tf.float32, shape=[None, 10]) with tf.name_scope(‘hidden1‘): x = tf.reshape(x_raw, shape=[-1,28,28,1]) W_conv1 = weight_variable([5,5,1,32]) b_conv1 = bias_variable([32]) l_conv1 = tf.nn.relu(tf.nn.conv2d(x,W_conv1, strides=[1,1,1,1],padding=‘SAME‘) + b_conv1) l_pool1 = tf.nn.max_pool(l_conv1, ksize=[1,2,2,1], strides=[1,2,2,1], padding=‘SAME‘) tf.summary.image(‘x_input‘,x,max_outputs=10) tf.summary.histogram(‘W_con1‘,W_conv1) tf.summary.histogram(‘b_con1‘,b_conv1) with tf.name_scope(‘hidden2‘): W_conv2 = weight_variable([5,5,32,64]) b_conv2 = bias_variable([64]) l_conv2 = tf.nn.relu(tf.nn.conv2d(l_pool1, W_conv2, strides=[1,1,1,1], padding=‘SAME‘)+b_conv2) l_pool2 = tf.nn.max_pool(l_conv2, ksize=[1,2,2,1],strides=[1,2,2,1], padding=‘SAME‘) tf.summary.histogram(‘W_con2‘, W_conv2) tf.summary.histogram(‘b_con2‘, b_conv2) with tf.name_scope(‘fc1‘): W_fc1 = weight_variable([64*7*7, 1024]) b_fc1 = bias_variable([1024]) l_pool2_flat = tf.reshape(l_pool2, [-1, 64*7*7]) l_fc1 = tf.nn.relu(tf.matmul(l_pool2_flat, W_fc1) + b_fc1) keep_prob = tf.placeholder(tf.float32) # 增加drop，这里存在1024个节点，如果全连接，会造成网络学习到不必要的信息，这是我们不希望看到的。 l_fc1_drop = tf.nn.dropout(l_fc1, keep_prob) tf.summary.histogram(‘W_fc1‘, W_fc1) tf.summary.histogram(‘b_fc1‘, b_fc1) with tf.name_scope(‘fc2‘): W_fc2 = weight_variable([1024, 10]) b_fc2 = bias_variable([10]) y_conv = tf.matmul(l_fc1_drop, W_fc2) + b_fc2 tf.summary.histogram(‘W_fc1‘, W_fc1) tf.summary.histogram(‘b_fc1‘, b_fc1) with tf.name_scope(‘train‘): cross_entropy = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=y_conv, labels=y)) # 进行梯度下降 train_step = tf.train.AdamOptimizer(learning_rate=1e-4).minimize(cross_entropy) correct_prediction = tf.equal(tf.argmax(y_conv,1), tf.argmax(y, 1)) accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32)) # scalar用于记录数值 tf.summary.scalar(‘loss‘, cross_entropy) tf.summary.scalar(‘accuracy‘, accuracy) with tf.Session(graph=myGraph) as sess: sess.run(tf.global_variables_initializer()) saver = tf.train.Saver() # 收集所有已经画好的graph merged = tf.summary.merge_all() # 定义存储的路径，这个路径必须和tensorboard的启动路径一样(先运行程序，保存图，然后在以相同的logdir启动tensorboard)，并且加上图. summary_writer = tf.summary.FileWriter(‘/Users/maxiong/Workpace/Tensorboard/log‘, graph=sess.graph) for i in range(1000): batch = mnist.train.next_batch(50) sess.run(train_step,feed_dict={x_raw:batch[0],y:batch[1],keep_prob:0.5}) if i%100 == 0: train_accuracy = accuracy.eval(feed_dict={x_raw:batch[0], y:batch[1], keep_prob:1.0}) print(‘step %d training accuracy:%g‘%(i, train_accuracy)) # 获得merged summary = sess.run(merged,feed_dict={x_raw:batch[0], y:batch[1], keep_prob:1.0}) # 利用summary_writer进行存储 summary_writer.add_summary(summary,i) test_accuracy = accuracy.eval(feed_dict={x_raw:mnist.test.images, y:mnist.test.labels, keep_prob:1.0}) print(‘test accuracy:%g‘ %test_accuracy) saver.save(sess,‘/Users/maxiong/Workpace/Tensorboard/model‘,global_step=1)
