如何在tensorflow中使用Softmax分类器中的验证监视器

时间:2016-09-01 18:03:51

标签: machine-learning tensorflow computer-vision deep-learning softmax

我只是编辑https://github.com/tensorflow/tensorflow/blob/r0.10/tensorflow/examples/tutorials/mnist/mnist_softmax.py以使用验证监视器启用日志记录

from __future__ import absolute_import
    from __future__ import division
    from __future__ import print_function

    # Import data
    from tensorflow.examples.tutorials.mnist import input_data

    import tensorflow as tf

    flags = tf.app.flags
    FLAGS = flags.FLAGS
    flags.DEFINE_string('data_dir', '/tmp/data/', 'Directory for storing data')

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

    sess = tf.InteractiveSession()

    # Create the model
    x = tf.placeholder(tf.float32, [None, 784])
    W = tf.Variable(tf.zeros([784, 10]))
    b = tf.Variable(tf.zeros([10]))
    y = tf.nn.softmax(tf.matmul(x, W) + b)

    validation_metrics = {"accuracy": tf.contrib.metrics.streaming_accuracy,
                          "precision": tf.contrib.metrics.streaming_precision,
                          "recall": tf.contrib.metrics.streaming_recall}
    validation_monitor = tf.contrib.learn.monitors.ValidationMonitor(
        mnist.test.images,
        mnist.test.labels,
        every_n_steps=50, metrics=validation_metrics,
        early_stopping_metric="loss",
        early_stopping_metric_minimize=True,
        early_stopping_rounds=200)
    # Define loss and optimizer
    y_ = tf.placeholder(tf.float32, [None, 10])
    cross_entropy = tf.reduce_mean(-tf.reduce_sum(y_ * tf.log(y), reduction_indices=[1]))
    train_step = tf.train.GradientDescentOptimizer(0.5).minimize(cross_entropy)

    # Train
    tf.initialize_all_variables().run()
    for i in range(1000):
      batch_xs, batch_ys = mnist.train.next_batch(100)
      train_step.run({x: batch_xs, y_: batch_ys})

    # Test trained model
    correct_prediction = tf.equal(tf.argmax(y, 1), tf.argmax(y_, 1))
    accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
    print(accuracy.eval({x: mnist.test.images, y_: mnist.test.labels}))

但我很困惑如何在此程序中设置 validation_monitor 。我在 DNNClassfier 中学到了,validation_monitor以flowwing方式使用

# Fit model.
classifier.fit(x=training_set.data,
               y=training_set.target,
               steps=2000, monitors=[validation_monitor])

那么,我如何在softmax_classifer中使用validation_monitor?

1 个答案:

答案 0 :(得分:1)

我认为没有一种简单的方法可以做到这一点,因为ValidationMonitortf.contrib的一部分,例如TensorFlow团队不支持的贡献代码。因此,除非您使用tf.contrib中的某些更高级别的API(例如DNNClassfier),否则您可能无法将ValidationMonitor实例简单地传递给优化程序的minimize方法。

我相信您的选择是:

  • 检查DNNClassfier fit方法的实施方式,并通过在图表和会话中手动处理ValidationMonitor实例来使用相同的方法。
  • 为日志记录和/或提前停止实施您自己的验证例程,或者您打算使用ValidationMonitor的任何内容。