How to use the cleverhans.compat.flags.DEFINE_float function in cleverhans

def main(_=None):
  from cleverhans_tutorials import check_installation
  check_installation(__file__)

  mnist_tutorial(nb_epochs=FLAGS.nb_epochs,
                 batch_size=FLAGS.batch_size,
                 learning_rate=FLAGS.learning_rate)


if __name__ == '__main__':
  flags.DEFINE_integer('nb_epochs', NB_EPOCHS,
                       'Number of epochs to train model')
  flags.DEFINE_integer('batch_size', BATCH_SIZE,
                       'Size of training batches')
  flags.DEFINE_float('learning_rate', LEARNING_RATE,
                     'Learning rate for training')

  tf.app.run()

check_installation(__file__)

  mnist_tutorial(
      nb_epochs=FLAGS.nb_epochs, batch_size=FLAGS.batch_size,
      learning_rate=FLAGS.learning_rate, clean_train=FLAGS.clean_train,
      backprop_through_attack=FLAGS.backprop_through_attack,
      nb_filters=FLAGS.nb_filters, attack_string=FLAGS.attack)


if __name__ == '__main__':
  flags.DEFINE_integer('nb_filters', NB_FILTERS,
                       'Model size multiplier')
  flags.DEFINE_integer('nb_epochs', NB_EPOCHS,
                       'Number of epochs to train model')
  flags.DEFINE_integer('batch_size', BATCH_SIZE, 'Size of training batches')
  flags.DEFINE_float('learning_rate', LEARNING_RATE,
                     'Learning rate for training')
  flags.DEFINE_bool('clean_train', True, 'Train on clean examples')
  flags.DEFINE_bool('backprop_through_attack', False,
                    ('If True, backprop through adversarial example '
                     'construction process during adversarial training'))
  flags.DEFINE_string('attack', 'fgsm',
                      'Adversarial attack crafted and used for training')
  tf.app.run()

mnist_blackbox(nb_classes=FLAGS.nb_classes, batch_size=FLAGS.batch_size,
                 learning_rate=FLAGS.learning_rate,
                 nb_epochs=FLAGS.nb_epochs, holdout=FLAGS.holdout,
                 data_aug=FLAGS.data_aug, nb_epochs_s=FLAGS.nb_epochs_s,
                 lmbda=FLAGS.lmbda, aug_batch_size=FLAGS.data_aug_batch_size)


if __name__ == '__main__':

  # General flags
  flags.DEFINE_integer('nb_classes', NB_CLASSES,
                       'Number of classes in problem')
  flags.DEFINE_integer('batch_size', BATCH_SIZE,
                       'Size of training batches')
  flags.DEFINE_float('learning_rate', LEARNING_RATE,
                     'Learning rate for training')

  # Flags related to oracle
  flags.DEFINE_integer('nb_epochs', NB_EPOCHS,
                       'Number of epochs to train model')

  # Flags related to substitute
  flags.DEFINE_integer('holdout', HOLDOUT,
                       'Test set holdout for adversary')
  flags.DEFINE_integer('data_aug', DATA_AUG,
                       'Number of substitute data augmentations')
  flags.DEFINE_integer('nb_epochs_s', NB_EPOCHS_S,
                       'Training epochs for substitute')
  flags.DEFINE_float('lmbda', LMBDA, 'Lambda from arxiv.org/abs/1602.02697')
  flags.DEFINE_integer('data_aug_batch_size', AUG_BATCH_SIZE,
                       'Batch size for augmentation')

learning_rate=FLAGS.learning_rate,
               nb_filters=FLAGS.nb_filters,
               SNNL_factor=FLAGS.SNNL_factor,
               output_dir=FLAGS.output_dir)


if __name__ == '__main__':
  flags.DEFINE_integer('nb_filters', NB_FILTERS,
                       'Model size multiplier')
  flags.DEFINE_integer('nb_epochs', NB_EPOCHS,
                       'Number of epochs to train model')
  flags.DEFINE_integer('batch_size', BATCH_SIZE,
                       'Size of training batches')
  flags.DEFINE_float('SNNL_factor', SNNL_FACTOR,
                     'Multiplier for Soft Nearest Neighbor Loss')
  flags.DEFINE_float('learning_rate', LEARNING_RATE,
                     'Learning rate for training')
  flags.DEFINE_string('output_dir', OUTPUT_DIR,
                      'output directory for saving figures')

  tf.app.run()

mnist_tutorial_jsma(viz_enabled=FLAGS.viz_enabled,
                      nb_epochs=FLAGS.nb_epochs,
                      batch_size=FLAGS.batch_size,
                      source_samples=FLAGS.source_samples,
                      learning_rate=FLAGS.learning_rate)


if __name__ == '__main__':
  flags.DEFINE_boolean('viz_enabled', VIZ_ENABLED,
                       'Visualize adversarial ex.')
  flags.DEFINE_integer('nb_epochs', NB_EPOCHS,
                       'Number of epochs to train model')
  flags.DEFINE_integer('batch_size', BATCH_SIZE, 'Size of training batches')
  flags.DEFINE_integer('source_samples', SOURCE_SAMPLES,
                       'Nb of test inputs to attack')
  flags.DEFINE_float('learning_rate', LEARNING_RATE,
                     'Learning rate for training')

  tf.app.run()

flags.DEFINE_string('attack_type_train', 'MadryEtAl_y_multigpu',
                      'Attack type for adversarial training:\
                        FGSM|MadryEtAl{,_y}{,_multigpu}.')
  flags.DEFINE_string('attack_type_test', 'FGSM',
                      'Attack type for test: FGSM|MadryEtAl{,_y}.')
  flags.DEFINE_string('dataset', 'mnist', 'Dataset mnist|cifar10.')
  flags.DEFINE_boolean('only_adv_train', False,
                       'Do not train with clean examples when adv training.')
  flags.DEFINE_integer('save_steps', 50, 'Save model per X steps.')
  flags.DEFINE_integer('attack_nb_iter_train', None,
                       'Number of iterations of training attack.')
  flags.DEFINE_integer('eval_iters', 1, 'Evaluate every X steps.')
  flags.DEFINE_integer('lrn_step', 30000, 'Step to decrease learning rate'
                       'for ResNet.')
  flags.DEFINE_float('adam_lrn', 0.001, 'Learning rate for Adam Optimizer.')
  flags.DEFINE_float('mom_lrn', 0.1,
                     'Learning rate for Momentum Optimizer.')
  flags.DEFINE_integer('ngpu', 1, 'Number of gpus.')
  flags.DEFINE_integer('sync_step', 1, 'Sync params frequency.')
  flags.DEFINE_boolean('fast_tests', False, 'Fast tests against attacks.')
  flags.DEFINE_string('data_path', './datasets/', 'Path to datasets.'
                      'Each dataset should be in a subdirectory.')

  app.run()

from cleverhans_tutorials import check_installation
  check_installation(__file__)

  mnist_tutorial(nb_epochs=FLAGS.nb_epochs, batch_size=FLAGS.batch_size,
                 learning_rate=FLAGS.learning_rate,
                 clean_train=FLAGS.clean_train,
                 backprop_through_attack=FLAGS.backprop_through_attack,
                 nb_filters=FLAGS.nb_filters)


if __name__ == '__main__':
  flags.DEFINE_integer('nb_filters', NB_FILTERS, 'Model size multiplier')
  flags.DEFINE_integer('nb_epochs', NB_EPOCHS,
                       'Number of epochs to train model')
  flags.DEFINE_integer('batch_size', BATCH_SIZE, 'Size of training batches')
  flags.DEFINE_float('learning_rate', LEARNING_RATE,
                     'Learning rate for training')
  flags.DEFINE_bool('clean_train', CLEAN_TRAIN, 'Train on clean examples')
  flags.DEFINE_bool('backprop_through_attack', BACKPROP_THROUGH_ATTACK,
                    ('If True, backprop through adversarial example '
                     'construction process during adversarial training'))

  tf.app.run()

cifar10_tutorial(nb_epochs=FLAGS.nb_epochs, batch_size=FLAGS.batch_size,
                   learning_rate=FLAGS.learning_rate,
                   clean_train=FLAGS.clean_train,
                   backprop_through_attack=FLAGS.backprop_through_attack,
                   nb_filters=FLAGS.nb_filters)


if __name__ == '__main__':
  flags.DEFINE_integer('nb_filters', NB_FILTERS,
                       'Model size multiplier')
  flags.DEFINE_integer('nb_epochs', NB_EPOCHS,
                       'Number of epochs to train model')
  flags.DEFINE_integer('batch_size', BATCH_SIZE,
                       'Size of training batches')
  flags.DEFINE_float('learning_rate', LEARNING_RATE,
                     'Learning rate for training')
  flags.DEFINE_bool('clean_train', CLEAN_TRAIN, 'Train on clean examples')
  flags.DEFINE_bool('backprop_through_attack', BACKPROP_THROUGH_ATTACK,
                    ('If True, backprop through adversarial example '
                     'construction process during adversarial training'))

  tf.app.run()

if __name__ == '__main__':
  flags.DEFINE_integer('train_start', TRAIN_START, 'Starting point (inclusive)'
                       'of range of train examples to use')
  flags.DEFINE_integer('train_end', TRAIN_END, 'Ending point (non-inclusive) '
                       'of range of train examples to use')
  flags.DEFINE_integer('test_start', TEST_START, 'Starting point (inclusive) '
                       'of range of test examples to use')
  flags.DEFINE_integer('test_end', TEST_END, 'End point (non-inclusive) of '
                       'range of test examples to use')
  flags.DEFINE_integer('nb_iter', NB_ITER, 'Number of iterations of PGD')
  flags.DEFINE_string('which_set', WHICH_SET, '"train" or "test"')
  flags.DEFINE_integer('batch_size', BATCH_SIZE,
                       'Batch size for most jobs')
  flags.DEFINE_float('base_eps_iter', BASE_EPS_ITER,
                     'epsilon per iteration, if data were in [0, 1]')
  tf.app.run()

source_samples=FLAGS.source_samples,
                    learning_rate=FLAGS.learning_rate,
                    attack_iterations=FLAGS.attack_iterations,
                    model_path=FLAGS.model_path,
                    targeted=FLAGS.targeted)


if __name__ == '__main__':
  flags.DEFINE_boolean('viz_enabled', VIZ_ENABLED,
                       'Visualize adversarial ex.')
  flags.DEFINE_integer('nb_epochs', NB_EPOCHS,
                       'Number of epochs to train model')
  flags.DEFINE_integer('batch_size', BATCH_SIZE, 'Size of training batches')
  flags.DEFINE_integer('source_samples', SOURCE_SAMPLES,
                       'Number of test inputs to attack')
  flags.DEFINE_float('learning_rate', LEARNING_RATE,
                     'Learning rate for training')
  flags.DEFINE_string('model_path', MODEL_PATH,
                      'Path to save or load the model file')
  flags.DEFINE_integer('attack_iterations', ATTACK_ITERATIONS,
                       'Number of iterations to run attack; 1000 is good')
  flags.DEFINE_boolean('targeted', TARGETED,
                       'Run the tutorial in targeted mode?')

  tf.app.run()