tf.app.flags

tf.app.flags

tf.app.flags defines some parameter. A simple example:

import tensorflow as tf
FLAGS = tf.app.flags.FLAGS

tf.app.flags.DEFINE_float('learning_rate', 0.01, 'Initial learning rate.')
tf.app.flags.DEFINE_string('train_dir', 'tmp/train/', 'Directory where to write event logs and checkpoint.')
tf.app.flags.DEFINE_integer('max_steps', 700, 'Number of batches to run.')
tf.app.flags.DEFINE_boolean('log_device_placement', False, 'Whether to log device placement.')

print(FLAGS.max_steps)  

or

from tensorflow import flags
flags.DEFINE_float('threshold', 0.1, 'detection threshold')
flags.DEFINE_string('model', 'cnn', 'configuration of choice')
flags.DEFINE_string('trainer', 'rmsprop', 'training algorithm')
FLAGS = flags.FLAGS

print(FLAGS.threshold)   

[root@...]# python test.py --threshold 10e-2 --model mlp