tensorflow-Tensorboard

Tensorboard 是 Tensorflow 官方推出的可视化工具，他可以将模型训练过程中的各种汇总数据展示出来，如标量（Scalars）、图片(image)、音频(Audio)、计算图(Graph)、数据分布(Distributions)、直方图（Histograms）和嵌入向量(Embeddings)。

我们在使用TensorFlow训练大型深度学习神经网络时，中间的计算过程可能非常复杂，因此为了理解、调试和优化网络，可以使用TensorBoard观察训练过程中的各种可视化数据。

下面通过官方MNIST 手写识别例子来认识一下TensorBoard

from __future__ import absolute_import
from __future__ import division
from __future__ import print_function

import argparse
import os
import sys

import tensorflow as tf

from tensorflow.examples.tutorials.mnist import input_data

FLAGS = None


def train():
    # Import data
    mnist = input_data.read_data_sets(FLAGS.data_dir,
                                      fake_data=FLAGS.fake_data)

    sess = tf.InteractiveSession()
    # Create a multilayer model.

    # Input placeholders
    with tf.name_scope('input'):
        x = tf.placeholder(tf.float32, [None, 784], name='x-input')
        y_ = tf.placeholder(tf.int64, [None], name='y-input')

    with tf.name_scope('input_reshape'):
        image_shaped_input = tf.reshape(x, [-1, 28, 28, 1])
        # 保存10张图片
        tf.summary.image('input', image_shaped_input, 10)

    # We can't initialize these variables to 0 - the network will get stuck.
    def weight_variable(shape):
        """Create a weight variable with appropriate initialization."""
        initial = tf.truncated_normal(shape, stddev=0.1)
        return tf.Variable(initial)

    def bias_variable(shape):
        """Create a bias variable with appropriate initialization."""
        initial = tf.constant(0.1, shape=shape)
        return tf.Variable(initial)

    def variable_summaries(var):
        """Attach a lot of summaries to a Tensor (for TensorBoard visualization)."""
        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)

    def nn_layer(input_tensor, input_dim, output_dim, layer_name, act=tf.nn.relu):
        """Reusable code for making a simple neural net layer.
        It does a matrix multiply, bias add, and then uses ReLU to nonlinearize.
        It also sets up name scoping so that the resultant graph is easy to read,
        and adds a number of summary ops.
        """
        # Adding a name scope ensures logical grouping of the layers in the graph.
        with tf.name_scope(layer_name):
            # This Variable will hold the state of the weights for the layer
            with tf.name_scope('weights'):
                weights = weight_variable([input_dim, output_dim])
                variable_summaries(weights)
            with tf.name_scope('biases'):
                biases = bias_variable([output_dim])
                variable_summaries(biases)
            with tf.name_scope('Wx_plus_b'):
                preactivate = tf.matmul(input_tensor, weights) + biases
                tf.summary.histogram('pre_activations', preactivate)
            activations = act(preactivate, name='activation')
            tf.summary.histogram('activations', activations)
            return activations

    hidden1 = nn_layer(x, 784, 500, 'layer1')

    with tf.name_scope('dropout'):
        keep_prob = tf.placeholder(tf.float32)
        tf.summary.scalar('dropout_keep_probability', keep_prob)
        dropped = tf.nn.dropout(hidden1, keep_prob)

    # Do not apply softmax activation yet, see below.
    y = nn_layer(dropped, 500, 10, 'layer2', act=tf.identity)

    with tf.name_scope('cross_entropy'):
        # The raw formulation of cross-entropy,
        #
        # tf.reduce_mean(-tf.reduce_sum(y_ * tf.log(tf.softmax(y)),
        #                               reduction_indices=[1]))
        #
        # can be numerically unstable.
        #
        # So here we use tf.losses.sparse_softmax_cross_entropy on the
        # raw logit outputs of the nn_layer above, and then average across
        # the batch.
        with tf.name_scope('total'):
            cross_entropy = tf.losses.sparse_softmax_cross_entropy(
                labels=y_, logits=y)
    tf.summary.scalar('cross_entropy', cross_entropy)

    with tf.name_scope('train'):
        train_step = tf.train.AdamOptimizer(FLAGS.learning_rate).minimize(
            cross_entropy)

    with tf.name_scope('accuracy'):
        with tf.name_scope('correct_prediction'):
            correct_prediction = tf.equal(tf.argmax(y, 1), y_)
        with tf.name_scope('accuracy'):
            accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
    tf.summary.scalar('accuracy', accuracy)

    # Merge all the summaries and write them out to
    # /tmp/tensorflow/mnist/logs/mnist_with_summaries (by default)
    merged = tf.summary.merge_all()
    train_writer = tf.summary.FileWriter(FLAGS.log_dir + '/train', sess.graph)
    test_writer = tf.summary.FileWriter(FLAGS.log_dir + '/test')
    tf.global_variables_initializer().run()

    # Train the model, and also write summaries.
    # Every 10th step, measure test-set accuracy, and write test summaries
    # All other steps, run train_step on training data, & add training summaries

    def feed_dict(train):
        """Make a TensorFlow feed_dict: maps data onto Tensor placeholders."""
        if train or FLAGS.fake_data:
            xs, ys = mnist.train.next_batch(100, fake_data=FLAGS.fake_data)
            k = FLAGS.dropout
        else:
            xs, ys = mnist.test.images, mnist.test.labels
            k = 1.0
        return {x: xs, y_: ys, keep_prob: k}

    for i in range(FLAGS.max_steps):
        if i % 10 == 0:  # Record summaries and test-set accuracy
            summary, acc = sess.run([merged, accuracy], feed_dict=feed_dict(False))
            test_writer.add_summary(summary, i)
            print('Accuracy at step %s: %s' % (i, acc))
        else:  # Record train set summaries, and train
            if i % 100 == 99:  # Record execution stats
                run_options = tf.RunOptions(trace_level=tf.RunOptions.FULL_TRACE)
                run_metadata = tf.RunMetadata()
                summary, _ = sess.run([merged, train_step],
                                      feed_dict=feed_dict(True),
                                      options=run_options,
                                      run_metadata=run_metadata)
                train_writer.add_run_metadata(run_metadata, 'step%03d' % i)
                train_writer.add_summary(summary, i)
                print('Adding run metadata for', i)
            else:  # Record a summary
                summary, _ = sess.run([merged, train_step], feed_dict=feed_dict(True))
                train_writer.add_summary(summary, i)
    train_writer.close()
    test_writer.close()


def main(_):
    if tf.gfile.Exists(FLAGS.log_dir):
        tf.gfile.DeleteRecursively(FLAGS.log_dir)
    tf.gfile.MakeDirs(FLAGS.log_dir)
    train()


if __name__ == '__main__':
    parser = argparse.ArgumentParser()
    parser.add_argument('--fake_data', nargs='?', const=True, type=bool,
                        default=False,
                        help='If true, uses fake data for unit testing.')
    parser.add_argument('--max_steps', type=int, default=1000,
                        help='Number of steps to run trainer.')
    parser.add_argument('--learning_rate', type=float, default=0.001,
                        help='Initial learning rate')
    parser.add_argument('--dropout', type=float, default=0.9,
                        help='Keep probability for training dropout.')
    parser.add_argument(
        '--data_dir',
        type=str,
        default=os.path.join(os.getenv('TEST_TMPDIR', '/tmp'),
                             'tensorflow/mnist/input_data'),
        help='Directory for storing input data')
    parser.add_argument(
        '--log_dir',
        type=str,
        default=os.path.join(os.getenv('TEST_TMPDIR', '/tmp'),
                             'tensorflow/mnist/logs/mnist_with_summaries'),
        help='Summaries log directory')
    FLAGS, unparsed = parser.parse_known_args()

    tf.app.run(main=main, argv=[sys.argv[0]] + unparsed)

训练完成后通过tensorborad来可视化数据了

tensorboard --logdir=mnist_with_summaries

执行命令之后，会出现一条提示信息，复制到浏览器就可以了

TensorBoard 1.7.0 at http://G14002VM-063:6006 (Press CTRL+C to quit)

在SCALARS窗口可以看到一些图标，显示的是之前设置的标量信息

图中两条曲线，分别是train和test中accuray随训练步数变化的趋势，除此之外还可以看到一些其他的统计信息。

在IMAGES窗口，可以看到训练过程中使用的图片情况，可以使原始图片、光学畸变后的图片、或是中间节点的输出

同样是包含train和test两部分，每个部分最多10张图片（在代码中已经设置）

在GRAPHS窗口中可以看到整个Tensorflow计算图的结构