FLAGS =无意义?

时间:2017-02-26 02:25:06

标签: python tensorflow argparse

我是python&的新手tensorFlow,我在tensorFlow文档中关注this MNIST tutorial

在第一位,我不知道FLAGS = None在这里做什么。我在谷歌搜索,然后回来了。这似乎对其他人来说太明显了?

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

import argparse
import sys

from tensorflow.examples.tutorials.mnist import input_data

import tensorflow as tf

FLAGS = None


def main(_):
  # Import data
  mnist = input_data.read_data_sets(FLAGS.data_dir, one_hot=True)

那么什么是FLAGS以及如何使用它? 例如,FLAGS.data_dir

任何帮助将不胜感激!

2 个答案:

答案 0 :(得分:4)

这是您正在查看的完整代码:我将解释:

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

import argparse
import sys

from tensorflow.examples.tutorials.mnist import input_data

import tensorflow as tf

FLAGS = None   #Adds a default value to FLAGS


def main(_):  #Everything inside the function is not checked until it's called
  mnist = input_data.read_data_sets(FLAGS.data_dir, one_hot=True) #FLAGS is not None anymore because it got changed below

  x = tf.placeholder(tf.float32, [None, 784])
  W = tf.Variable(tf.zeros([784, 10]))
  b = tf.Variable(tf.zeros([10]))
  y = tf.matmul(x, W) + b

  y_ = tf.placeholder(tf.float32, [None, 10])

  cross_entropy = tf.reduce_mean(
      tf.nn.softmax_cross_entropy_with_logits(labels=y_, logits=y))
  train_step = tf.train.GradientDescentOptimizer(0.5).minimize(cross_entropy)

  sess = tf.InteractiveSession()
  tf.global_variables_initializer().run()
  # Train
  for _ in range(1000):
    batch_xs, batch_ys = mnist.train.next_batch(100)
    sess.run(train_step, feed_dict={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(sess.run(accuracy, feed_dict={x: mnist.test.images,
                                      y_: mnist.test.labels}))

if __name__ == '__main__': 
  parser = argparse.ArgumentParser()
  parser.add_argument('--data_dir', type=str, default='/tmp/tensorflow/mnist/input_data',
                      help='Directory for storing input data')

  FLAGS, unparsed = parser.parse_known_args() #Here it changed the value of FLAGS to the first thing returned from parser.parse_known_args()

  tf.app.run(main=main, argv=[sys.argv[0]] + unparsed) #runs the app (calling main)

发生的事情是FLAGS在这里发生了变化: FLAGS, unparsed = parser.parse_known_args()

答案 1 :(得分:3)

初始化FLAGS=None只是初始化全局常量的一种方法。如果保留原样,则会在main中引发错误,因为None没有任何属性。

但如果通过argparse parser设置,如更全面的示例所示,它是一个具有各种属性的简单对象。 main假设其中一个属性称为data_dir

如果在

之后
FLAGS, unparsed = parser.parse_known_args()
print(FLAGS)

您应该看到Namespace(data_dir='a directory', ....),其中data_dir的值是从命令行解析的。