美文网首页我爱编程
Tensorflow.TensorBoard.2.MNIST

Tensorflow.TensorBoard.2.MNIST

作者: 小异_Summer | 来源:发表于2018-03-15 19:53 被阅读0次

    参考内容:
    非常详细的TensorBoard基本解释及使用简介
    TensorFlow学习笔记(6):TensorBoard之Embeddings
    【Python | TensorBoard】用 PCA 可视化 MNIST 手写数字识别数据集
    ** TensorFlow-7-TensorBoard Embedding可视化**
    在线示例


    在查看Embedding时,遇到如下问题:
    Error: Your browser or device does not have WebGL enabled. Please enable hardware acceleration, or use a browser that supports WebGL.

    error
    1. 首先尝试设置firefox:
      在地址栏输入about:config
      找到webgl.disable设置为false
      找到webgl.force-enable设置为True
      但设置完后刷新页面,仍提示相同错误,因此尝试方法2。
    2. 通过主机Chrome浏览器访问VB虚拟机提供的Web页面:
      首先设置VB网络如下所示,访问方式为NAT,点击端口转发添加一条规则。其中 主机IP 169.254.155.25是在主机系统中通过查看网络连接详细信息得到的VB IP地址,主机端口 定义为想要通过浏览器访问的端口; 子系统IP 是在VB的Ubuntu中显示的IP地址, 子系统端口 是tensorboard中设置的访问端口。确认后,允许防火墙所提示的信息即可。
      VB网络设置

    在主机Chrome浏览器中输入http://169.254.155.25:8081/#embeddings,即可查看embeddings信息。



    PLUS:一些参数的Embedding

    from __future__ import absolute_import
    from __future__ import division
    from __future__ import print_function
    
    import argparse
    import sys
    import os
    import tensorflow as tf
    from tensorflow.examples.tutorials.mnist import input_data
    from tensorflow.contrib.tensorboard.plugins import projector
    import numpy as np
    
    FLAGS = None
    
    def train():
        # Import data
        mnist = input_data.read_data_sets(FLAGS.data_dir, one_hot=True, fake_data=FLAGS.fake_data)
        sess = tf.InteractiveSession()
    
    
        # 1)
        # # Create randomly initialized embedding weights which will be trained.
        # D = 200  # Dimensionality of the embedding.
        # embedding_var = tf.Variable(tf.random_normal([N, D]), name='word_embedding')
        N = 10000  # Number of items (vocab size).
        plot_array = mnist.test.images[:N]  # shape: (n_observations, n_features)
        np.savetxt(os.path.join(FLAGS.log_dir, 'metadata.tsv'), mnist.test.labels[:N], fmt='%d')
        embedding_var = tf.Variable(plot_array, name='word_embedding')
    
        # Create a multilayer model
    
        # Input placeholders
        with tf.name_scope('input'):
            y_ = tf.placeholder(tf.float32, [None, 10], name='y-input')
    
            x = tf.placeholder(tf.float32, [None, 784], name='x-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 yo 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 ensure logical grouping of grouping of the layers in the graph.
            with tf.name_scope(layer_name):
                # This Variable will hold the state of the weights for 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_ativations', 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_probalility', 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))    # Attention: There is y_, not y
            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()
    
        # 2) Periodically save your embeddings in a LOG_DIR
        saver = tf.train.Saver()
        saver.save(sess, os.path.join(FLAGS.log_dir, "model.ckpt"), global_step=0)
    
        # 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,
    
        def feed_dict(train):
            """Make a Tensorflow deed_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}    # Attention: There is y_, not y
    
        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 summariess, 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()
    
    
    
        # 3) Associate metadata and sprite image with your embedding
        # Format: tensorflow/tensorboard/plugins/projector/projector_config.proto
        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(FLAGS.log_dir, 'metadata.tsv')
    
        # Use the same LOG_DIR where you stored your checkpoint.
        summary_writer = tf.summary.FileWriter(FLAGS.log_dir)
    
        embedding.sprite.image_path = os.path.join(FLAGS.log_dir, 'mnist_10k_sprite.png')
        embedding.sprite.single_image_dim.extend([28, 28])
        # The next line writes a projector_config.pbtxt in the LOG_DIR. TensorBoard will
        # read this file during startup.
        projector.visualize_embeddings(summary_writer, config)
    
        # Download img from: https://www.tensorflow.org/images/mnist_10k_sprite.png
        # and put it into FLAGS.log_dir
    
    
    def main(_):    # Attention: There is a _ arg
        if tf.gfile.Exists(FLAGS.log_dir):
            tf.gfile.DeleteRecursively(FLAGS.log_dir)
        tf.gfile.MakeDirs(FLAGS.log_dir)
        train()
    
    
    if __name__ == '__main__':
    
        parse = argparse.ArgumentParser()
        parse.add_argument('--fake_data', nargs='?', const=True, type=bool, default=False,
                           help='If true, uses fake data for ubit testing.')
        parse.add_argument('--max_steps', type=int, default=300,    #default=1000
                           help='Number of steps to run trainer.')
        parse.add_argument('--learning_rate', type=float, default=0.01,
                           help='Initial learning rate')
        parse.add_argument('--dropout', type=float, default=0.9,
                           help='Keep probability for training dropout.')
        parse.add_argument(
            '--data_dir',
            type=str,
            #default='/tmp/tensorflow/mnist/input_data',
            default='MNIST_data',
            help='Directory for storing input data')
        parse.add_argument(
            '--log_dir',
            type=str,
            default='/tmp/tensorflow/mnist/logs/mnist_with_summaries',
            help='Summaries log directory')
        FLAGS, unparsed = parse.parse_known_args()
        tf.app.run(main=main, argv=[sys.argv[0]] + unparsed)
    
    # cd --your_log_dir
    # tensorboard --log_dir=yourLogDir
    
    

    相关文章

      网友评论

        本文标题:Tensorflow.TensorBoard.2.MNIST

        本文链接:https://www.haomeiwen.com/subject/uokrcxtx.html