Tensorflow 之 TensorBoard可视化Graph和Embeddings

• windows下使用tensorboard
• tensorflow 官网上的例子程序都是针对Linux下的；文件路径需要更改
• tensorflow1.1和1.3的启动方式不一样 ：参考：Running on Google Cloud found : No module named tensorflow.tensorboard

• Could you try using python -m tensorboard --logdir "${MODEL_DIR}" instead? I suspect that this will fix your issue.
• I should have written tensorboard.main instead of TensorBoard: python -m tensorboard.main --logdir "${MODEL_DIR}"

• 但是虽然启动了6006端口，但是加载文件失败，这个问题留到后面解决，继续跟进tensorflow学习

• 更新几个现有的demo

如路径为：E:\MyTensorBoard\logs, logs中又包含train和test。此时，TensorBoard通过读取事件文件来运行，通过在cmd 中键入命令：tensorboard --logdir=log文件路径。按照我们当前目录，若写成：

tensorboard --logdir=E:\MyTensorBoard\logs
显示结果是：No scalar、No image...，然而查了几遍代码也没有问题，事件文件也没有问题。

解决方法：方法一：将cmd的默认路径cd到log文件的上一层，即cd /d E:\MyTensorBoard，之后等号后面直接键入log文件名即可，不需写全路径，即 tensorboard --logdir=logs。方法二：双斜杠，即tensorboard --logdir=E://MyTensorBoard//logs。最后根据得到的网址http://hostIP:6006，在chrome里打开，就可以可视化我们的图表了，幸福来的太突然

Tensor与Graph可视化

• Summary：所有需要在TensorBoard上展示的统计结果。
• tf.name_scope()：为Graph中的Tensor添加层级，TensorBoard会按照代码指定的层级进行展示，初始状态下只绘制最高层级的效果，点击后可展开层级看到下一层的细节。
• tf.summary.scalar()：添加标量统计结果。
• tf.summary.histogram()：添加任意shape的Tensor，统计这个Tensor的取值分布。
• tf.summary.merge_all()：添加一个操作，代表执行所有summary操作，这样可以避免人工执行每一个summary op。
• tf.summary.FileWrite：用于将Summary写入磁盘，需要制定存储路径logdir，如果传递了Graph对象，则在Graph Visualization会显示Tensor Shape Information。执行summary op后，将返回结果传递给add_summary()方法即可。

import gzip
import struct
import numpy as np
from sklearn.linear_model import LogisticRegression
from sklearn import preprocessing
from sklearn.metrics import accuracy_score
import tensorflow as tf

# MNIST data is stored in binary format,
# and we transform them into numpy ndarray objects by the following two utility functions
def read_image(file_name):
    with gzip.open(file_name, 'rb') as f:
        buf = f.read()
        index = 0
        magic, images, rows, columns = struct.unpack_from('>IIII', buf, index)
        index += struct.calcsize('>IIII')

        image_size = '>' + str(images * rows * columns) + 'B'
        ims = struct.unpack_from(image_size, buf, index)

        im_array = np.array(ims).reshape(images, rows, columns)
        return im_array

def read_label(file_name):
    with gzip.open(file_name, 'rb') as f:
        buf = f.read()
        index = 0
        magic, labels = struct.unpack_from('>II', buf, index)
        index += struct.calcsize('>II')

        label_size = '>' + str(labels) + 'B'
        labels = struct.unpack_from(label_size, buf, index)

        label_array = np.array(labels)
        return label_array

print ("Start processing MNIST handwritten digits data...")
train_x_data = read_image("MNIST_data/train-images-idx3-ubyte.gz")
train_x_data = train_x_data.reshape(train_x_data.shape[0], -1).astype(np.float32)
train_y_data = read_label("MNIST_data/train-labels-idx1-ubyte.gz")
test_x_data = read_image("MNIST_data/t10k-images-idx3-ubyte.gz")
test_x_data = test_x_data.reshape(test_x_data.shape[0], -1).astype(np.float32)
test_y_data = read_label("MNIST_data/t10k-labels-idx1-ubyte.gz")

train_x_minmax = train_x_data / 255.0
test_x_minmax = test_x_data / 255.0

# Of course you can also use the utility function to read in MNIST provided by tensorflow
# from tensorflow.examples.tutorials.mnist import input_data
# mnist = input_data.read_data_sets("MNIST_data/", one_hot=False)
# train_x_minmax = mnist.train.images
# train_y_data = mnist.train.labels
# test_x_minmax = mnist.test.images
# test_y_data = mnist.test.labels

# We evaluate the softmax regression model by sklearn first
eval_sklearn = False
if eval_sklearn:
    print ("Start evaluating softmax regression model by sklearn...")
    reg = LogisticRegression(solver="lbfgs", multi_class="multinomial")
    reg.fit(train_x_minmax, train_y_data)
    np.savetxt('coef_softmax_sklearn.txt', reg.coef_, fmt='%.6f')  # Save coefficients to a text file
    test_y_predict = reg.predict(test_x_minmax)
    print ("Accuracy of test set: %f" % accuracy_score(test_y_data, test_y_predict))

eval_tensorflow = True
batch_gradient = False

# Summary：所有需要在TensorBoard上展示的统计结果。
def variable_summaries(var):
    with tf.name_scope('summaries'):
        mean = tf.reduce_mean(var)
        tf.summary.scalar('mean', mean)
        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)

if eval_tensorflow:
    print ("Start evaluating softmax regression model by tensorflow...")
    # reformat y into one-hot encoding style
    lb = preprocessing.LabelBinarizer()
    lb.fit(train_y_data)
    train_y_data_trans = lb.transform(train_y_data)
    test_y_data_trans = lb.transform(test_y_data)

    x = tf.placeholder(tf.float32, [None, 784])
    with tf.name_scope('weights'):
        W = tf.Variable(tf.zeros([784, 10]))
        variable_summaries(W)
    with tf.name_scope('biases'):
        b = tf.Variable(tf.zeros([10]))
        variable_summaries(b)
    with tf.name_scope('Wx_plus_b'):
        V = tf.matmul(x, W) + b
        tf.summary.histogram('pre_activations', V)
    with tf.name_scope('softmax'):
        y = tf.nn.softmax(V)
        tf.summary.histogram('activations', y)

    y_ = tf.placeholder(tf.float32, [None, 10])

    with tf.name_scope('cross_entropy'):
        loss = tf.reduce_mean(-tf.reduce_sum(y_ * tf.log(y), reduction_indices=[1]))
        tf.summary.scalar('cross_entropy', loss)

    with tf.name_scope('train'):
        optimizer = tf.train.GradientDescentOptimizer(0.5)
        train = optimizer.minimize(loss)

    with tf.name_scope('evaluate'):
        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)

    init = tf.global_variables_initializer()

    sess = tf.Session()
    sess.run(init)

    merged = tf.summary.merge_all()
    train_writer = tf.summary.FileWriter('tmp/train', sess.graph)
    test_writer = tf.summary.FileWriter('tmp/test')

    if batch_gradient:
        for step in range(300):
            sess.run(train, feed_dict={x: train_x_minmax, y_: train_y_data_trans})
            if step % 10 == 0:
                print ("Batch Gradient Descent processing step %d" % step)
        print ("Finally we got the estimated results, take such a long time...")
    else:
        for step in range(1000):
            if step % 10 == 0:
                summary, acc = sess.run([merged, accuracy], feed_dict={x: test_x_minmax, y_: test_y_data_trans})
                test_writer.add_summary(summary, step)
                print ("Stochastic Gradient Descent processing step %d accuracy=%.2f" % (step, acc))
            else:
                sample_index = np.random.choice(train_x_minmax.shape[0], 100)
                batch_xs = train_x_minmax[sample_index, :]
                batch_ys = train_y_data_trans[sample_index, :]
                summary, _ = sess.run([merged, train], feed_dict={x: batch_xs, y_: batch_ys})
                train_writer.add_summary(summary, step)

    np.savetxt('coef_softmax_tf.txt', np.transpose(sess.run(W)), fmt='%.6f')  # Save coefficients to a text file
    print ("Accuracy of test set: %f" % sess.run(accuracy, feed_dict={x: test_x_minmax, y_: test_y_data_trans}))

Embeddings

• TensorBoard是TensorFlow自带的一个可视化工具，Embeddings是其中的一个功能，用于在二维或三维空间对高维数据进行探索

# -*- coding: utf-8 -*-
# @author: ranjiewen
# @date: 2017-02-08
# @description: hello world program to set up embedding projector in TensorBoard based on MNIST
# @ref: http://yann.lecun.com/exdb/mnist/, https://www.tensorflow.org/images/mnist_10k_sprite.png
#

import numpy as np
import tensorflow as tf
from tensorflow.contrib.tensorboard.plugins import projector
from tensorflow.examples.tutorials.mnist import input_data
import os

PATH_TO_MNIST_DATA = "MNIST_data"
LOG_DIR = "emd"
IMAGE_NUM = 10000

# Read in MNIST data by utility functions provided by TensorFlow
mnist = input_data.read_data_sets(PATH_TO_MNIST_DATA, one_hot=False)

# Extract target MNIST image data
plot_array = mnist.test.images[:IMAGE_NUM]  # shape: (n_observations, n_features)

# Generate meta data
np.savetxt(os.path.join(LOG_DIR, 'metadata.tsv'), mnist.test.labels[:IMAGE_NUM], fmt='%d')

# Download sprite image
# https://www.tensorflow.org/images/mnist_10k_sprite.png, 100x100 thumbnails
PATH_TO_SPRITE_IMAGE = os.path.join(LOG_DIR, 'mnist_10k_sprite.png')

# To visualise your embeddings, there are 3 things you need to do:
# 1) Setup a 2D tensor variable(s) that holds your embedding(s)
session = tf.InteractiveSession()
embedding_var = tf.Variable(plot_array, name='embedding')
tf.global_variables_initializer().run()

# 2) Periodically save your embeddings in a LOG_DIR
# Here we just save the Tensor once, so we set global_step to a fixed number
saver = tf.train.Saver()
saver.save(session, os.path.join(LOG_DIR, "model.ckpt"), global_step=0)

# 3) Associate metadata and sprite image with your embedding
# Use the same LOG_DIR where you stored your checkpoint.
summary_writer = tf.summary.FileWriter(LOG_DIR)

config = projector.ProjectorConfig()
# You can add multiple embeddings. Here we add only one.
embedding = config.embeddings.add()
embedding.tensor_name = embedding_var.name
# Link this tensor to its metadata file (e.g. labels).
embedding.metadata_path = os.path.join(LOG_DIR, 'metadata.tsv')
# Link this tensor to its sprite image.
embedding.sprite.image_path = PATH_TO_SPRITE_IMAGE
embedding.sprite.single_image_dim.extend([28, 28])
# Saves a configuration file that TensorBoard will read during startup.
projector.visualize_embeddings(summary_writer, config)

官网demo

• 注意更改文件路径

"""A simple MNIST classifier which displays summaries in TensorBoard.
This is an unimpressive MNIST model, but it is a good example of using
tf.name_scope to make a graph legible in the TensorBoard graph explorer, and of
naming summary tags so that they are grouped meaningfully in TensorBoard.
It demonstrates the functionality of every TensorBoard dashboard.
"""
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 #"F:\RANJIEWEN\Deep_learning\TensorFlow\log"

def 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)# log/train or log/test
  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')

  parser.add_argument(
      '--data_dir',
      type=str,
      default=os.path.join(os.getenv('TEST_TMPDIR', 'F:\RANJIEWEN\Deep_learning\TensorFlow\MNIST_data')),
      help='Directory for storing input data')
  parser.add_argument(
      '--log_dir',
      type=str,
      default=os.path.join(os.getenv('TEST_TMPDIR', 'F:\RANJIEWEN\Deep_learning\TensorFlow\log')),
      help='Summaries log directory')
  FLAGS, unparsed = parser.parse_known_args()
  tf.app.run(main=main, argv=[sys.argv[0]] + unparsed)