TensorBoard可视化demo--summary/scalar/histogram/FileWriter

本程序基于tensorflow下对MNIST数据集进行识别的程序代码 修改得到.
主要就是为了实现TensorBoard的可视化,加入了summary data到event file中去,有summary.scalar和summary.histogram

还有name_scope的应用,这些都是为了可视化

程序运行完成后,在命令行执行

tensorboard --logdir=/tmp/tensorflow/mnist/logs/mnist_with_summaries

在http://0.0.0.0:6006查看可视化情况

"""A simple MNIST classifier which displays summaries in TensorBoard. This is an unimpressive MNIST model, but it is a good example of usingtf.name_scope to make a graph legible in the TensorBoard graph explorer, and ofnaming summary tags so that they are grouped meaningfully in TensorBoard.It demonstrates the functionality of every TensorBoard dashboard."""from __future__ import absolute_importfrom __future__ import divisionfrom __future__ import print_functionimport argparseimport sysimport tensorflow as tffrom tensorflow.examples.tutorials.mnist import input_dataFLAGS = Nonedef train():  # Import data  mnist = input_data.read_data_sets(FLAGS.data_dir,                                    one_hot=True,                                    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.float32, [None, 10], name='y-input')  with tf.name_scope('input_reshape'):    image_shaped_input = tf.reshape(x, [-1, 28, 28, 1])    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.nn.softmax_cross_entropy_with_logits on the    # raw outputs of the nn_layer above, and then average across    # the batch.    diff = tf.nn.softmax_cross_entropy_with_logits(labels=y_, logits=y)    with tf.name_scope('total'):      cross_entropy = tf.reduce_mean(diff)  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), tf.argmax(y_, 1))    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='/tmp/tensorflow/mnist/input_data',                      help='Directory for storing input data')  parser.add_argument('--log_dir', type=str, default='/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)

运行结果

Accuracy at step 0: 0.1068Accuracy at step 10: 0.7145Accuracy at step 20: 0.82Accuracy at step 30: 0.8618Accuracy at step 40: 0.8786Accuracy at step 50: 0.8895Accuracy at step 60: 0.8944Accuracy at step 70: 0.9003Accuracy at step 80: 0.9091Accuracy at step 90: 0.9114Adding run metadata for 99Accuracy at step 100: 0.9096Accuracy at step 110: 0.9169Accuracy at step 120: 0.9219Accuracy at step 130: 0.923Accuracy at step 140: 0.9223Accuracy at step 150: 0.9253Accuracy at step 160: 0.9261Accuracy at step 170: 0.9317Accuracy at step 180: 0.9335Accuracy at step 190: 0.9344Adding run metadata for 199Accuracy at step 200: 0.9344Accuracy at step 210: 0.9371Accuracy at step 220: 0.9332Accuracy at step 230: 0.9325Accuracy at step 240: 0.9292Accuracy at step 250: 0.9388Accuracy at step 260: 0.9358Accuracy at step 270: 0.9362Accuracy at step 280: 0.9392Accuracy at step 290: 0.94Adding run metadata for 299Accuracy at step 300: 0.9458Accuracy at step 310: 0.9434Accuracy at step 320: 0.9465Accuracy at step 330: 0.9472Accuracy at step 340: 0.9474Accuracy at step 350: 0.9473Accuracy at step 360: 0.9484Accuracy at step 370: 0.9464Accuracy at step 380: 0.9505Accuracy at step 390: 0.9482Adding run metadata for 399Accuracy at step 400: 0.9477Accuracy at step 410: 0.9519Accuracy at step 420: 0.9501Accuracy at step 430: 0.9538Accuracy at step 440: 0.9544Accuracy at step 450: 0.9518Accuracy at step 460: 0.954Accuracy at step 470: 0.9509Accuracy at step 480: 0.9526Accuracy at step 490: 0.9525Adding run metadata for 499Accuracy at step 500: 0.9585Accuracy at step 510: 0.9571Accuracy at step 520: 0.9585Accuracy at step 530: 0.9591Accuracy at step 540: 0.9563Accuracy at step 550: 0.9596Accuracy at step 560: 0.9581Accuracy at step 570: 0.9623Accuracy at step 580: 0.9587Accuracy at step 590: 0.9597Adding run metadata for 599Accuracy at step 600: 0.9622Accuracy at step 610: 0.9617Accuracy at step 620: 0.9622Accuracy at step 630: 0.9617Accuracy at step 640: 0.9582Accuracy at step 650: 0.9603Accuracy at step 660: 0.9612Accuracy at step 670: 0.9634Accuracy at step 680: 0.9609Accuracy at step 690: 0.9641Adding run metadata for 699Accuracy at step 700: 0.9617Accuracy at step 710: 0.9625Accuracy at step 720: 0.9621Accuracy at step 730: 0.963Accuracy at step 740: 0.964Accuracy at step 750: 0.9635Accuracy at step 760: 0.9636Accuracy at step 770: 0.9655Accuracy at step 780: 0.9641Accuracy at step 790: 0.9651Adding run metadata for 799Accuracy at step 800: 0.9649Accuracy at step 810: 0.9651Accuracy at step 820: 0.9653Accuracy at step 830: 0.9668Accuracy at step 840: 0.9664Accuracy at step 850: 0.9643Accuracy at step 860: 0.9651Accuracy at step 870: 0.9663Accuracy at step 880: 0.966Accuracy at step 890: 0.9657Adding run metadata for 899Accuracy at step 900: 0.9657Accuracy at step 910: 0.967Accuracy at step 920: 0.9678Accuracy at step 930: 0.9664Accuracy at step 940: 0.9678Accuracy at step 950: 0.9659Accuracy at step 960: 0.9687Accuracy at step 970: 0.9674Accuracy at step 980: 0.9683Accuracy at step 990: 0.9683Adding run metadata for 999