TensorBoard是TensorFlow官方推出的可視化工具尺栖，它可以將模型訓練過程中的各種匯總數(shù)據(jù)展示出來决瞳。我們在使用TensorFlow訓練大型深度學習神經(jīng)網(wǎng)絡時皮胡，中間的計算過程可能非常復雜赏迟，可以使用TensorBoard觀察訓練過程中的各種可視化數(shù)據(jù)锌杀。它的流程是糕再，在執(zhí)行TensorFlow計算圖的過程中突想，將各種類型的數(shù)據(jù)匯總并記錄到日志文件中。然后使用TensorBoard讀取這些日志文件袭灯，解析數(shù)據(jù)并生成數(shù)據(jù)可視化Web頁面稽荧。

用一個MNIST數(shù)據(jù)集的手寫字體識別姨丈，看一下各種類型數(shù)據(jù)的匯總和展示构挤。

先說一下我的環(huán)境筋现，我用的是Cuda9.0+Ubuntu16.04+Tensorflow-gpu1.12+Python3.6矾飞。

訓練過程

import tensorflow as tf

from tensorflow.examples.tutorials.mnist import input_data

max_steps=1000

learning_rate=0.001

dropout=0.9

data_dir='/tmp/tensorflow/mnist/input_data'

#匯總數(shù)據(jù)的日志存放地址

log_dir='/tmp/tensorflow/mnist/logs/mnist_with_summaries'

? # Import data

mnist = input_data.read_data_sets(data_dir,one_hot=True)

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)))

? ? #進行記錄和匯總

? ? tf.summary.scalar('stddev', stddev)

? ? tf.summary.scalar('max', tf.reduce_max(var))

? ? tf.summary.scalar('min', tf.reduce_min(var))

#直接記錄變量var的直方圖數(shù)據(jù)

? ? 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(logits=y, labels=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(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/mnist_logs (by default)

merged = tf.summary.merge_all()

train_writer = tf.summary.FileWriter(log_dir + '/train', sess.graph)

test_writer = tf.summary.FileWriter(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:

? ? xs, ys = mnist.train.next_batch(100)

? ? k = dropout

? else:

? ? xs, ys = mnist.test.images, mnist.test.labels

? ? k = 1.0

? return {x: xs, y_: ys, keep_prob: k}

saver = tf.train.Saver()

for i in range(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)

? ? ? saver.save(sess, log_dir+"/model.ckpt", 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()

可視化效果

切換到Linux命令行下，執(zhí)行TensorBoard程序括尸，并通過--logdir指定TensorFlow日志路徑濒翻，然后就可以自動生成所有匯總數(shù)據(jù)可視化的結果了有送。

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

執(zhí)行上面的命令后雀摘，出現(xiàn)一條提示信息，復制其中的網(wǎng)址到瀏覽器烁落，就能看到數(shù)據(jù)可視化的圖標了。

首先打開標量SCALARS的窗口轧铁，并單擊打開accuracy的圖表旦棉，其中可以看到兩條曲線齿风，分別是train和test中accuracy隨訓練步數(shù)變化的趨勢药薯。可以調整Smoothing參數(shù)救斑，控制對曲線的平滑處理童本。如下圖所示

打開IMAGES窗口，可以看到MNIST數(shù)據(jù)集中的圖片脸候，不只是原始數(shù)據(jù)穷娱，所有在tf.summary.image()中匯總的圖片數(shù)據(jù)都可以在這里看到。

進入GRAPHS窗口运沦，可以看到整個TensorFlow計算圖的結構，這里展示了網(wǎng)絡forward的inference的流程携添，以及backward訓練更新參數(shù)的流程

切換到DISTRIBUTIONS窗口嫁盲，可以看到之前記錄的各個神經(jīng)網(wǎng)絡層輸出的分布，包括在激活函數(shù)前的結果及在激活函數(shù)后的結果烈掠。這樣能觀察到神經(jīng)網(wǎng)絡節(jié)點的輸出是否有效

點擊HISTOGRAMS窗口羞秤，將DISTRIBUTIONS的圖示結構轉換為直方圖的形式，將每一步訓練后的神經(jīng)網(wǎng)絡層的輸出的分布以直方圖的形式展示出來

單擊PROJECTOR左敌，可以看到降維后的嵌入向量的可視化效果