TensorBoard使用

阳光穿透心脏的1/2处 2022-06-18 06:51 247阅读 0赞

## 先跑一个小例程 ##

'''
    Graph and Loss visualization using Tensorboard.
    This example is using the MNIST database of handwritten digits
    (http://yann.lecun.com/exdb/mnist/)
    Author: Aymeric Damien
    Project: https://github.com/aymericdamien/TensorFlow-Examples/
    '''
    
    from __future__ import print_function
    
    import tensorflow as tf
    
    # Import MNIST data
    from tensorflow.examples.tutorials.mnist import input_data
    mnist = input_data.read_data_sets("/tmp/data/", one_hot=True)
    
    # Parameters
    learning_rate = 0.01
    training_epochs = 25
    batch_size = 100
    display_step = 1
    logs_path = '/tmp/tensorflow_logs/example'
    
    # Network Parameters
    n_hidden_1 = 256 # 1st layer number of features
    n_hidden_2 = 256 # 2nd layer number of features
    n_input = 784 # MNIST data input (img shape: 28*28)
    n_classes = 10 # MNIST total classes (0-9 digits)
    
    # tf Graph Input
    # mnist data image of shape 28*28=784
    x = tf.placeholder(tf.float32, [None, 784], name='InputData')
    # 0-9 digits recognition => 10 classes
    y = tf.placeholder(tf.float32, [None, 10], name='LabelData')
    
    
    # Create model
    def multilayer_perceptron(x, weights, biases):
        # Hidden layer with RELU activation
        layer_1 = tf.add(tf.matmul(x, weights['w1']), biases['b1'])
        layer_1 = tf.nn.relu(layer_1)
        # Create a summary to visualize the first layer ReLU activation
        #tf.summary.histogram("relu1", layer_1)
        tf.histogram_summary("relu1", layer_1)
        # Hidden layer with RELU activation
        layer_2 = tf.add(tf.matmul(layer_1, weights['w2']), biases['b2'])
        layer_2 = tf.nn.relu(layer_2)
        # Create another summary to visualize the second layer ReLU activation
        #tf.summary.histogram("relu2", layer_2)
        tf.histogram_summary("relu2", layer_2)
        # Output layer
        out_layer = tf.add(tf.matmul(layer_2, weights['w3']), biases['b3'])
        return out_layer
    
    # Store layers weight & bias
    weights = {
        'w1': tf.Variable(tf.random_normal([n_input, n_hidden_1]), name='W1'),
        'w2': tf.Variable(tf.random_normal([n_hidden_1, n_hidden_2]), name='W2'),
        'w3': tf.Variable(tf.random_normal([n_hidden_2, n_classes]), name='W3')
    }
    biases = {
        'b1': tf.Variable(tf.random_normal([n_hidden_1]), name='b1'),
        'b2': tf.Variable(tf.random_normal([n_hidden_2]), name='b2'),
        'b3': tf.Variable(tf.random_normal([n_classes]), name='b3')
    }
    
    # Encapsulating all ops into scopes, making Tensorboard's Graph
    # Visualization more convenient
    with tf.name_scope('Model'):
        # Build model
        pred = multilayer_perceptron(x, weights, biases)
    
    with tf.name_scope('Loss'):
        # Softmax Cross entropy (cost function)
        loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(pred, y))
    
    with tf.name_scope('SGD'):
        # Gradient Descent
        optimizer = tf.train.GradientDescentOptimizer(learning_rate)
        # Op to calculate every variable gradient
        grads = tf.gradients(loss, tf.trainable_variables())
        grads = list(zip(grads, tf.trainable_variables()))
        # Op to update all variables according to their gradient
        apply_grads = optimizer.apply_gradients(grads_and_vars=grads)
    
    with tf.name_scope('Accuracy'):
        # Accuracy
        acc = tf.equal(tf.argmax(pred, 1), tf.argmax(y, 1))
        acc = tf.reduce_mean(tf.cast(acc, tf.float32))
    
    # Initializing the variables
    init = tf.initialize_all_variables()
    
    # Create a summary to monitor cost tensor
    tf.scalar_summary("loss", loss)
    # Create a summary to monitor accuracy tensor
    tf.scalar_summary("accuracy", acc)
    # Create summaries to visualize weights
    for var in tf.trainable_variables():
        tf.histogram_summary(var.name, var)
    # Summarize all gradients
    for grad, var in grads:
        tf.histogram_summary(var.name + '/gradient', grad)
    # Merge all summaries into a single op
    merged_summary_op = tf.merge_all_summaries()
    
    # Launch the graph
    with tf.Session() as sess:
        sess.run(init)
    
        # op to write logs to Tensorboard
        summary_writer = tf.train.SummaryWriter(logs_path,
                                                graph=tf.get_default_graph())
    
        # Training cycle
        for epoch in range(training_epochs):
            avg_cost = 0.
            total_batch = int(mnist.train.num_examples/batch_size)
            # Loop over all batches
            for i in range(total_batch):
                batch_xs, batch_ys = mnist.train.next_batch(batch_size)
                # Run optimization op (backprop), cost op (to get loss value)
                # and summary nodes
                _, c, summary = sess.run([apply_grads, loss, merged_summary_op],
                                         feed_dict={x: batch_xs, y: batch_ys})
                # Write logs at every iteration
                summary_writer.add_summary(summary, epoch * total_batch + i)
                # Compute average loss
                avg_cost += c / total_batch
            # Display logs per epoch step
            if (epoch+1) % display_step == 0:
                print("Epoch:", '%04d' % (epoch+1), "cost=", "{:.9f}".format(avg_cost))
    
        print("Optimization Finished!")
    
        # Test model
        # Calculate accuracy
        print("Accuracy:", acc.eval({x: mnist.test.images, y: mnist.test.labels}))
    
        print("Run the command line:\n" \
              "--> tensorboard --logdir=/tmp/tensorflow_logs " \
    "\nThen open http://0.0.0.0:6006/ into your web browser")

运行该程序。

运行完了之后，可以在"/tmp/tensorflow\_logs/example"目录下找到事件记录文件"events.out.tfevents.1490276692.inspur.datanode7.com"。

输入"tensorboard --logdir=/tmp/tensorflow\_logs"

这个时候就遇到问题啦~看下面呢：

[root@inspur example]# tensorboard --logdir=/tmp/tensorflow_logs
    ERROR:tensorflow:Tried to connect to port 6006, but address is in use.

6006端口被占用了，把它干掉好啦。

[root@inspur example]# lsof -i:6006
    COMMAND     PID USER   FD   TYPE   DEVICE SIZE/OFF NODE NAME
    tensorboa 28508 root    4u  IPv4 18373697      0t0  TCP *:6006 (LISTEN)
    [root@inspur example]# kill -9 28508
    [root@inspur example]# tensorboard --logdir=/tmp/tensorflow_logs
    Starting TensorBoard b'23' on port 6006
    (You can navigate to http://0.0.0.0:6006)

进程号为28508的进程占用了端口6006，用kill命令干掉。

另外程序是在服务器上跑得，所以在本机上查看的时候，网址要输 ‘’服务器IP:6006"