本文主要是介绍TensorBoard数据可视化，希望对大家解决编程问题提供一定的参考价值，需要的开发者们随着小编来一起学习吧！
Tensorboard可以将模型训练的过程中的各种汇总数据展示出来，包括标量（Scalars）、图片（image）、音频（Audio）、计算图（Graphs）、数据分布（Distributions）、直方图（Histograms）和嵌入向量（Embeddings）。
from __future__ import absolute_import
from __future__ import division
from __future__ import print_functionimport argparse
import os
import sysimport tensorflow as tffrom tensorflow.examples.tutorials.mnist import input_data#使用input_data.read_data_sets 下载MNIST数据，并创建Tensorflow的默认Session。FLAGS = Nonedef train():# Import datamnist = input_data.read_data_sets(FLAGS.data_dir,fake_data=FLAGS.fake_data)sess = tf.InteractiveSession()"""为了在tensorboard中展示节点名称，我们设计网络时会经常使用with tf.name_scope 限定命名空间，在这个with下的所有节点都会被自动命名为input/xxx这样的格式。下面定义输入x和y的placeholder，并将输入的一维数据变形为２８x28的图片储存到另一个tensor，这样就可以使用tf.summary.image将图片数据汇总给tensorboard展示了。"""# Create a multilayer model.# Input placeholderswith 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])tf.summary.image('input', image_shaped_input, 10)"""同时，定义神经网络模型参数的初始化方法，权重依然使用我们常用的truncated_normal进行初始化，偏置则赋值为0.1"""# 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)"""再定义对Variable变量的数据汇总函数，我们计算出Variable的mean、stddev、max和min，对这些标量数据使用tf.summary.scalar进行记录和汇总。同时，使用tf.summary.histogram直接记录变量var的直方图数据。"""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)
"""
设计的MLP多层神经网络来训练数据，在每一层中都会对模型参数进行数据汇总。因此，我们定义创建一层神经网络并进行数据汇总的函数nn_layer。这个函数的输入参数有输入数据input_tensor、输入的维度input_dim、输出的维度output_dim和层名layer_name,激活函数act则默认使用ReLU。在函数内，先是初始化这层神经网络的权重和偏置，并使用前面定义的variable_summaries对variable进行数据汇总。然后对输入做矩阵乘法并加偏置，再将未进行激活的结果使用tf.summary.histogram统计直方图。同时，在使用激活函数后，在使用tf.summary.histogram统计一次。
"""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 layerwith 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) + biasestf.summary.histogram('pre_activations', preactivate)activations = act(preactivate, name='activation')tf.summary.histogram('activations', activations)return activationshidden1 = nn_layer(x, 784, 500, 'layer1')"""再创建一个Dropout层，并使用tf.summary.scalar记录keep_prob。"""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)
"""
这里使用tf.losses.sparse_softmax_cross_entropy()对前面输出层的结果进行Sotfmax处理并计算交叉熵损失cross_entropy，并使用tf.summary.scalar进行统计汇总。
"""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)"""
下面使用Adma优化器对损失进行优化，同时统计预测正确的样本数并计算准确率accuray，在使用tf.summary.scalar对accuracy进行统计汇总。
"""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)"""
因为之前定义了非常多的tf.summary的汇总操作，逐一执行这些操作太麻烦，所以这里使用tf.summary.merger_all()直接获取所有汇总操作，以便后面执行。定义两个tf.summary.FileWriter(文件记录器)在不同的子目录，分别用来存放训练和测试的日志数据。同时，将Session的计算图sess.graph加入训练过程的记录器，这样在TensorBoard的GRAPHS窗口中就能展示整个计算图的可视化效果。最后使用tf.global_variables_initializer().run()初始化全部变量。
"""# 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 summariesdef 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.dropoutelse:xs, ys = mnist.test.images, mnist.test.labelsk = 1.0return {x: xs, y_: ys, keep_prob: k}
"""
首先使用tf.train.Saver()创建模型的保存器，然后进入训练的循环中，每隔10步执行一次merged(数据汇总)、accuracy(求测试集上的预测准确率)操作，并使用test_write.add_sumamry将汇总结果summary和循环步数i写入日志文件；同时每隔100步，使用tf.RunOptions定义TensorFlow运行选项，其中设置trace_level为FULL_TRACE,并使用tf.RunMetadata()定义Tensorflow运行的元信息，这样可以记录训练时运算时间和内存占用等方面的信息。再执行merged数据汇总操作和train_step训练操作，将汇总结果summary和训练元信息run_metadata添加到train_writer。平时，则只执行merged操作和train_step操作，并添加summary到train_writer。所有训练全部结束后，关闭train_writer和test_writer。
"""saver = tf.train.Saver()for i in range(FLAGS.max_steps):if i % 10 == 0: # Record summaries and test-set accuracysummary, 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 trainif i % 100 == 99: # Record execution statsrun_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 summarysummary, _ = 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)
之后切换到Linux命令行下，执行TensorBoard程序，并通过–logdir指定TensorFlow日志路径，然后TensorBoard就可以自动生成所有汇总数据可视化的结果了。
tensorboard --logdir=/tmp/tensorflow/mnist/logs/mnist_with_summaries这篇关于TensorBoard数据可视化的文章就介绍到这儿，希望我们推荐的文章对编程师们有所帮助！
