使用TensorBoard可视化学习

in TensorFlow笔记 | 4 comments | 阅读量: 880

当使用TensorFlow进行大网络计算时调试和优化都比较复杂,使用可视化的工具是很有必要的

API参考链接

序列化数据

开始使用TensorBoard之前,我们需要在运行TensorFlow程序的时候生成相应的数据供其使用.

首先需要创建图,然后再决定那些节点需要使用`summary`操作,具体操作如下:

上面依然只是定义了TensorFlow中的基本节点,仅仅只是加到了图中,还需要运行才能在最后获得summary数据.
使用tf.summary.merge_all来汇总这些节点作为一个单独的节点生成所有的数据.当然还可以使用tf.summary.merge来手动的汇总需要的节点,输入要求是一个list类型的数组,数组内就是上述summary节点返回的数据.

最后我们需要存储生成是数据,tf.summary.FileWriter接受一个logdir为输入,这个目录将存储所有的事件数据.同时还可以接收一个Graph作为输入,这样生成的数据中将包含我们所定义的图,另外这个函数返回的类型还支持一些其他的操作:

使用范例:

import tensorflow as tf
import argparse
import sys
from tensorflow.examples.tutorials.mnist import input_data


FLAGS =None


def train():
    # 使用自带的数据集
    mnist = input_data.read_data_sets(FLAGS.data_dir, one_hot=True, fake_data=FLAGS.fake_data)
    # 限制gpu使用 自动增长
    sess = tf.Session(config=tf.ConfigProto(gpu_options=tf.GPUOptions(allow_growth=True)))
    # 使用命名空间来确定节点
    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)

    def weight_variable(shape):
        initial = tf.truncated_normal(shape, stddev=0.1)
        return tf.Variable(initial)

    def bias_variable(shape):
        initial = tf.constant(0.1, shape=shape)
        return tf.Variable(initial)

    # 保存事件信息
    def variable_summaries(var):
        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)

    # 构建网络
    def nn_layer(input_tensor, input_dim, output_dim, layer_name, act=tf.nn.relu):
        with tf.name_scope(layer_name):
            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)

    y = nn_layer(dropped, 500, 10, 'layer2', act=tf.identity)

    with tf.name_scope('cross_entropy'):
        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)

    # 汇总summary操作
    merged = tf.summary.merge_all()
    # 存入磁盘
    train_writer = tf.summary.FileWriter(FLAGS.log_dir + '/train', sess.graph)
    test_writer = tf.summary.FileWriter(FLAGS.log_dir + '/test')
    sess.run(tf.global_variables_initializer())

    def feed_dict(train):
        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:
            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:

            if i % 100 == 99:
                summary, _ = sess.run([merged, train_step],
                                      feed_dict=feed_dict(True))
                train_writer.add_summary(summary, i)

                print('Adding run metadata for', i)
            else:
                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='./MNIST_data',
       help='Directory for storing input data')
    parser.add_argument(
       '--log_dir',
       type=str,
       default='./log',
       help='Summaries log directory')
    FLAGS, unparsed = parser.parse_known_args()
    tf.app.run(main=main, argv=[sys.argv[0]] + unparsed)

启动tensorboard

Screenshot_2017-07-30_12-56-05.png

记录的数据

Screenshot_2017-07-30_12-58-02.png

图的可视化

Screenshot_2017-07-30_12-57-42.png

Responses
  1. write a good cover letter cover letters for employment amazing cover letters make a good cover letter

    Reply
  2. cover letters cover letters help with writing a cover letter cover letters

    Reply
  3. cover letter for employment cover letters a good cover letter cover letters

    Reply
  4. application cover letter cover letters cover letters write cover letter

    Reply