Python tensorflow.Graph() Examples

def testFailsOnFixedFeature(self):
    component_spec = spec_pb2.ComponentSpec()
    text_format.Parse("""
        name: "annotate"
        network_unit {
          registered_name: "IdentityNetwork"
        }
        fixed_feature {
          name: "fixed" embedding_dim: 32 size: 1
        }
        """, component_spec)
    with tf.Graph().as_default():
      comp = bulk_component.BulkAnnotatorComponentBuilder(
          self.master, component_spec)

      # Expect feature extraction to generate a runtime error due to the
      # fixed feature.
      with self.assertRaises(RuntimeError):
        comp.build_greedy_training(self.master_state, self.network_states) 

def load_graph(frozen_graph_filename):
    # We load the protobuf file from the disk and parse it to retrieve the
    # unserialized graph_def
    with tf.gfile.GFile(frozen_graph_filename, "rb") as f:
        graph_def = tf.GraphDef()
        graph_def.ParseFromString(f.read())

    # Then, we can use again a convenient built-in function to import a graph_def into the
    # current default Graph
    with tf.Graph().as_default() as graph:
        tf.import_graph_def(
            graph_def,
            input_map=None,
            return_elements=None,
            name="",
            op_dict=None,
            producer_op_list=None
        )
    return graph 

def PathScores(self, iterations, beam_size, max_steps, batch_size):
    with self.test_session(graph=tf.Graph()) as sess:
      t = self.MakeGraph(beam_size=beam_size, max_steps=max_steps,
                         batch_size=batch_size).training
      sess.run(t['inits'])
      all_path_scores = []
      beam_path_scores = []
      for i in range(iterations):
        logging.info('run %d', i)
        tensors = (
            sess.run(
                [t['alive_steps'], t['concat_scores'],
                 t['all_path_scores'], t['beam_path_scores'],
                 t['indices'], t['path_ids']]))

        logging.info('alive for %s, all_path_scores and beam_path_scores, '
                     'indices and path_ids:'
                     '\n%s\n%s\n%s\n%s',
                     tensors[0], tensors[2], tensors[3], tensors[4], tensors[5])
        logging.info('diff:\n%s', tensors[2] - tensors[3])

        all_path_scores.append(tensors[2])
        beam_path_scores.append(tensors[3])
      return all_path_scores, beam_path_scores 

def __init__(self, params_descriptor, MWF=False, stft_backend="auto", multiprocess=True):
        """ Default constructor.

        :param params_descriptor: Descriptor for TF params to be used.
        :param MWF: (Optional) True if MWF should be used, False otherwise.
        """

        self._params = load_configuration(params_descriptor)
        self._sample_rate = self._params['sample_rate']
        self._MWF = MWF
        self._tf_graph = tf.Graph()
        self._predictor = None
        self._input_provider = None
        self._builder = None
        self._features = None
        self._session = None
        self._pool = Pool() if multiprocess else None
        self._tasks = []
        self._params["stft_backend"] = get_backend(stft_backend) 

def test_mnist_tutorial_pytorch(self):
        import tensorflow as tf
        from cleverhans_tutorials import mnist_tutorial_pytorch

        # Run the MNIST tutorial on a dataset of reduced size
        with tf.Graph().as_default():
            np.random.seed(42)
            report = mnist_tutorial_pytorch.mnist_tutorial(
                nb_epochs=2,
                train_end=5000,
                test_end=333,
            )

        # Check accuracy values contained in the AccuracyReport object
        self.assertGreater(report.clean_train_clean_eval, 0.9)
        self.assertLess(report.clean_train_adv_eval, 0.10) 

def testBuildOnlyUptoFinalEndpoint(self):
    batch_size = 5
    height, width = 299, 299
    endpoints = ['Conv2d_1a_3x3', 'Conv2d_2a_3x3', 'Conv2d_2b_3x3',
                 'MaxPool_3a_3x3', 'Conv2d_3b_1x1', 'Conv2d_4a_3x3',
                 'MaxPool_5a_3x3', 'Mixed_5b', 'Mixed_6a',
                 'PreAuxLogits', 'Mixed_7a', 'Conv2d_7b_1x1']
    for index, endpoint in enumerate(endpoints):
      with tf.Graph().as_default():
        inputs = tf.random_uniform((batch_size, height, width, 3))
        out_tensor, end_points = inception.inception_resnet_v2_base(
            inputs, final_endpoint=endpoint)
        if endpoint != 'PreAuxLogits':
          self.assertTrue(out_tensor.op.name.startswith(
              'InceptionResnetV2/' + endpoint))
        self.assertItemsEqual(endpoints[:index+1], end_points) 

def testBuildOnlyUptoFinalEndpoint(self):
    batch_size = 5
    height, width = 224, 224
    endpoints = ['Conv2d_0',
                 'Conv2d_1_depthwise', 'Conv2d_1_pointwise',
                 'Conv2d_2_depthwise', 'Conv2d_2_pointwise',
                 'Conv2d_3_depthwise', 'Conv2d_3_pointwise',
                 'Conv2d_4_depthwise', 'Conv2d_4_pointwise',
                 'Conv2d_5_depthwise', 'Conv2d_5_pointwise',
                 'Conv2d_6_depthwise', 'Conv2d_6_pointwise',
                 'Conv2d_7_depthwise', 'Conv2d_7_pointwise',
                 'Conv2d_8_depthwise', 'Conv2d_8_pointwise',
                 'Conv2d_9_depthwise', 'Conv2d_9_pointwise',
                 'Conv2d_10_depthwise', 'Conv2d_10_pointwise',
                 'Conv2d_11_depthwise', 'Conv2d_11_pointwise',
                 'Conv2d_12_depthwise', 'Conv2d_12_pointwise',
                 'Conv2d_13_depthwise', 'Conv2d_13_pointwise']
    for index, endpoint in enumerate(endpoints):
      with tf.Graph().as_default():
        inputs = tf.random_uniform((batch_size, height, width, 3))
        out_tensor, end_points = mobilenet_v1.mobilenet_v1_base(
            inputs, final_endpoint=endpoint)
        self.assertTrue(out_tensor.op.name.startswith(
            'MobilenetV1/' + endpoint))
        self.assertItemsEqual(endpoints[:index+1], end_points) 

def testBuildOnlyUpToFinalEndpoint(self):
    batch_size = 5
    height, width = 299, 299
    all_endpoints = [
        'Conv2d_1a_3x3', 'Conv2d_2a_3x3', 'Conv2d_2b_3x3', 'Mixed_3a',
        'Mixed_4a', 'Mixed_5a', 'Mixed_5b', 'Mixed_5c', 'Mixed_5d',
        'Mixed_5e', 'Mixed_6a', 'Mixed_6b', 'Mixed_6c', 'Mixed_6d',
        'Mixed_6e', 'Mixed_6f', 'Mixed_6g', 'Mixed_6h', 'Mixed_7a',
        'Mixed_7b', 'Mixed_7c', 'Mixed_7d']
    for index, endpoint in enumerate(all_endpoints):
      with tf.Graph().as_default():
        inputs = tf.random_uniform((batch_size, height, width, 3))
        out_tensor, end_points = inception.inception_v4_base(
            inputs, final_endpoint=endpoint)
        self.assertTrue(out_tensor.op.name.startswith(
            'InceptionV4/' + endpoint))
        self.assertItemsEqual(all_endpoints[:index+1], end_points) 

def testBuildOnlyUptoFinalEndpoint(self):
    batch_size = 5
    height, width = 224, 224
    endpoints = ['Conv2d_1a_7x7', 'MaxPool_2a_3x3', 'Conv2d_2b_1x1',
                 'Conv2d_2c_3x3', 'MaxPool_3a_3x3', 'Mixed_3b', 'Mixed_3c',
                 'MaxPool_4a_3x3', 'Mixed_4b', 'Mixed_4c', 'Mixed_4d',
                 'Mixed_4e', 'Mixed_4f', 'MaxPool_5a_2x2', 'Mixed_5b',
                 'Mixed_5c']
    for index, endpoint in enumerate(endpoints):
      with tf.Graph().as_default():
        inputs = tf.random_uniform((batch_size, height, width, 3))
        out_tensor, end_points = inception.inception_v1_base(
            inputs, final_endpoint=endpoint)
        self.assertTrue(out_tensor.op.name.startswith(
            'InceptionV1/' + endpoint))
        self.assertItemsEqual(endpoints[:index+1], end_points) 

def testCreateLogisticClassifier(self):
    g = tf.Graph()
    with g.as_default():
      tf.set_random_seed(0)
      tf_inputs = tf.constant(self._inputs, dtype=tf.float32)
      tf_labels = tf.constant(self._labels, dtype=tf.float32)

      model_fn = LogisticClassifier
      clone_args = (tf_inputs, tf_labels)
      deploy_config = model_deploy.DeploymentConfig(num_clones=1)

      self.assertEqual(slim.get_variables(), [])
      clones = model_deploy.create_clones(deploy_config, model_fn, clone_args)
      clone = clones[0]
      self.assertEqual(len(slim.get_variables()), 2)
      for v in slim.get_variables():
        self.assertDeviceEqual(v.device, 'CPU:0')
        self.assertDeviceEqual(v.value().device, 'CPU:0')
      self.assertEqual(clone.outputs.op.name,
                       'LogisticClassifier/fully_connected/Sigmoid')
      self.assertEqual(clone.scope, '')
      self.assertDeviceEqual(clone.device, 'GPU:0')
      self.assertEqual(len(slim.losses.get_losses()), 1)
      update_ops = tf.get_collection(tf.GraphKeys.UPDATE_OPS)
      self.assertEqual(update_ops, []) 

def testCreateSingleclone(self):
    g = tf.Graph()
    with g.as_default():
      tf.set_random_seed(0)
      tf_inputs = tf.constant(self._inputs, dtype=tf.float32)
      tf_labels = tf.constant(self._labels, dtype=tf.float32)

      model_fn = BatchNormClassifier
      clone_args = (tf_inputs, tf_labels)
      deploy_config = model_deploy.DeploymentConfig(num_clones=1)

      self.assertEqual(slim.get_variables(), [])
      clones = model_deploy.create_clones(deploy_config, model_fn, clone_args)
      clone = clones[0]
      self.assertEqual(len(slim.get_variables()), 5)
      for v in slim.get_variables():
        self.assertDeviceEqual(v.device, 'CPU:0')
        self.assertDeviceEqual(v.value().device, 'CPU:0')
      self.assertEqual(clone.outputs.op.name,
                       'BatchNormClassifier/fully_connected/Sigmoid')
      self.assertEqual(clone.scope, '')
      self.assertDeviceEqual(clone.device, 'GPU:0')
      self.assertEqual(len(slim.losses.get_losses()), 1)
      update_ops = tf.get_collection(tf.GraphKeys.UPDATE_OPS)
      self.assertEqual(len(update_ops), 2) 

def testCreateOnecloneWithPS(self):
    g = tf.Graph()
    with g.as_default():
      tf.set_random_seed(0)
      tf_inputs = tf.constant(self._inputs, dtype=tf.float32)
      tf_labels = tf.constant(self._labels, dtype=tf.float32)

      model_fn = BatchNormClassifier
      clone_args = (tf_inputs, tf_labels)
      deploy_config = model_deploy.DeploymentConfig(num_clones=1,
                                                    num_ps_tasks=1)

      self.assertEqual(slim.get_variables(), [])
      clones = model_deploy.create_clones(deploy_config, model_fn, clone_args)
      self.assertEqual(len(clones), 1)
      clone = clones[0]
      self.assertEqual(clone.outputs.op.name,
                       'BatchNormClassifier/fully_connected/Sigmoid')
      self.assertDeviceEqual(clone.device, '/job:worker/device:GPU:0')
      self.assertEqual(clone.scope, '')
      self.assertEqual(len(slim.get_variables()), 5)
      for v in slim.get_variables():
        self.assertDeviceEqual(v.device, '/job:ps/task:0/CPU:0')
        self.assertDeviceEqual(v.device, v.value().device) 

def testNoSummariesOnGPU(self):
    with tf.Graph().as_default():
      deploy_config = model_deploy.DeploymentConfig(num_clones=2)

      # clone function creates a fully_connected layer with a regularizer loss.
      def ModelFn():
        inputs = tf.constant(1.0, shape=(10, 20), dtype=tf.float32)
        reg = tf.contrib.layers.l2_regularizer(0.001)
        tf.contrib.layers.fully_connected(inputs, 30, weights_regularizer=reg)

      model = model_deploy.deploy(
          deploy_config, ModelFn,
          optimizer=tf.train.GradientDescentOptimizer(1.0))
      # The model summary op should have a few summary inputs and all of them
      # should be on the CPU.
      self.assertTrue(model.summary_op.op.inputs)
      for inp in  model.summary_op.op.inputs:
        self.assertEqual('/device:CPU:0', inp.device) 

def testCreateSingleclone(self):
    g = tf.Graph()
    with g.as_default():
      tf.set_random_seed(0)
      tf_inputs = tf.constant(self._inputs, dtype=tf.float32)
      tf_labels = tf.constant(self._labels, dtype=tf.float32)

      model_fn = BatchNormClassifier
      clone_args = (tf_inputs, tf_labels)
      deploy_config = model_deploy.DeploymentConfig(num_clones=1)

      self.assertEqual(slim.get_variables(), [])
      clones = model_deploy.create_clones(deploy_config, model_fn, clone_args)
      self.assertEqual(len(slim.get_variables()), 5)
      update_ops = tf.get_collection(tf.GraphKeys.UPDATE_OPS)
      self.assertEqual(len(update_ops), 2)

      optimizer = tf.train.GradientDescentOptimizer(learning_rate=1.0)
      total_loss, grads_and_vars = model_deploy.optimize_clones(clones,
                                                                optimizer)
      self.assertEqual(len(grads_and_vars), len(tf.trainable_variables()))
      self.assertEqual(total_loss.op.name, 'total_loss')
      for g, v in grads_and_vars:
        self.assertDeviceEqual(g.device, 'GPU:0')
        self.assertDeviceEqual(v.device, 'CPU:0') 

def testBulkFeatureIdExtractorFailsOnLinkedFeature(self):
    component_spec = spec_pb2.ComponentSpec()
    text_format.Parse("""
        name: "test"
        network_unit {
          registered_name: "IdentityNetwork"
        }
        fixed_feature {
          name: "fixed" embedding_dim: -1 size: 1
        }
        linked_feature {
          name: "linked" embedding_dim: -1 size: 1
          source_translator: "identity"
          source_component: "mock"
        }
        """, component_spec)
    with tf.Graph().as_default():
      with self.assertRaises(ValueError):
        unused_comp = bulk_component.BulkFeatureIdExtractorComponentBuilder(
            self.master, component_spec) 

def testSetTracingTrue(self):
    """Checks that 'annotations' does call SetTracing if enabled."""
    test_name = 'set-tracing-true'

    with tf.Graph().as_default():
      builder, _ = self.getBuilderAndTarget(test_name)
      anno = builder.add_annotation(test_name, enable_tracing=True)

      # Check SetTracing is called after GetSession but before AttachDataReader.
      self.checkOpOrder('annotations', anno['annotations'], [
          'GetSession', 'SetTracing', 'AttachDataReader', 'ReleaseSession'
      ])

      # Same for the 'traces' output, if that's what you were to call.
      self.checkOpOrder('traces', anno['traces'], [
          'GetSession', 'SetTracing', 'AttachDataReader', 'ReleaseSession'
      ]) 

def testSetTracingFalse(self):
    """Checks that 'annotations' doesn't call SetTracing if disabled."""
    test_name = 'set-tracing-false'

    with tf.Graph().as_default():
      builder, _ = self.getBuilderAndTarget(test_name)

      # Note: "enable_tracing=False" is the default.
      anno = builder.add_annotation(test_name, enable_tracing=False)

      # ReleaseSession should still be there.
      path = _find_input_path_to_type(anno['annotations'], 'ReleaseSession')
      self.assertNotEmpty(path)

      # As should AttachDataReader.
      path = _find_input_path_to_type(path[-1], 'AttachDataReader')
      self.assertNotEmpty(path)

      # But SetTracing should not be called.
      set_tracing_path = _find_input_path_to_type(path[-1], 'SetTracing')
      self.assertEmpty(set_tracing_path)

      # Instead, we should go to GetSession.
      path = _find_input_path_to_type(path[-1], 'GetSession')
      self.assertNotEmpty(path) 

def testAttachDataReader(self):
    """Checks that train['run'] and 'annotations' call AttachDataReader."""
    test_name = 'attach-data-reader'

    with tf.Graph().as_default():
      builder, target = self.getBuilderAndTarget(test_name)
      train = builder.add_training_from_config(target)
      anno = builder.add_annotation(test_name)

      # AttachDataReader should be called between GetSession and ReleaseSession.
      self.checkOpOrder('train', train['run'],
                        ['GetSession', 'AttachDataReader', 'ReleaseSession'])

      # A similar contract applies to the annotations.
      self.checkOpOrder('annotations', anno['annotations'],
                        ['GetSession', 'AttachDataReader', 'ReleaseSession']) 

def main(_):
  """Train a word2vec model."""
  if not FLAGS.train_data or not FLAGS.eval_data or not FLAGS.save_path:
    print("--train_data --eval_data and --save_path must be specified.")
    sys.exit(1)
  opts = Options()
  with tf.Graph().as_default(), tf.Session() as session:
    with tf.device("/cpu:0"):
      model = Word2Vec(opts, session)
      model.read_analogies() # Read analogy questions
    for _ in xrange(opts.epochs_to_train):
      model.train()  # Process one epoch
      model.eval()  # Eval analogies.
    # Perform a final save.
    model.saver.save(session, os.path.join(opts.save_path, "model.ckpt"),
                     global_step=model.global_step)
    if FLAGS.interactive:
      # E.g.,
      # [0]: model.analogy(b'france', b'paris', b'russia')
      # [1]: model.nearby([b'proton', b'elephant', b'maxwell'])
      _start_shell(locals()) 

def main(_):
  if not FLAGS.output_file:
    raise ValueError('You must supply the path to save to with --output_file')
  tf.logging.set_verbosity(tf.logging.INFO)
  with tf.Graph().as_default() as graph:
    dataset = dataset_factory.get_dataset(FLAGS.dataset_name, 'train',
                                          FLAGS.dataset_dir)
    network_fn = nets_factory.get_network_fn(
        FLAGS.model_name,
        num_classes=(dataset.num_classes - FLAGS.labels_offset),
        is_training=FLAGS.is_training)
    if hasattr(network_fn, 'default_image_size'):
      image_size = network_fn.default_image_size
    else:
      image_size = FLAGS.default_image_size
    placeholder = tf.placeholder(name='input', dtype=tf.float32,
                                 shape=[1, image_size, image_size, 3])
    network_fn(placeholder)
    graph_def = graph.as_graph_def()
    with gfile.GFile(FLAGS.output_file, 'wb') as f:
      f.write(graph_def.SerializeToString()) 

def testNoSummariesOnGPUForEvals(self):
    with tf.Graph().as_default():
      deploy_config = model_deploy.DeploymentConfig(num_clones=2)

      # clone function creates a fully_connected layer with a regularizer loss.
      def ModelFn():
        inputs = tf.constant(1.0, shape=(10, 20), dtype=tf.float32)
        reg = tf.contrib.layers.l2_regularizer(0.001)
        tf.contrib.layers.fully_connected(inputs, 30, weights_regularizer=reg)

      # No optimizer here, it's an eval.
      model = model_deploy.deploy(deploy_config, ModelFn)
      # The model summary op should have a few summary inputs and all of them
      # should be on the CPU.
      self.assertTrue(model.summary_op.op.inputs)
      for inp in  model.summary_op.op.inputs:
        self.assertEqual('/device:CPU:0', inp.device) 

def testCreateLogisticClassifier(self):
    g = tf.Graph()
    with g.as_default():
      tf.set_random_seed(0)
      tf_inputs = tf.constant(self._inputs, dtype=tf.float32)
      tf_labels = tf.constant(self._labels, dtype=tf.float32)

      model_fn = LogisticClassifier
      clone_args = (tf_inputs, tf_labels)
      deploy_config = model_deploy.DeploymentConfig(num_clones=1)

      self.assertEqual(slim.get_variables(), [])
      clones = model_deploy.create_clones(deploy_config, model_fn, clone_args)
      self.assertEqual(len(slim.get_variables()), 2)
      update_ops = tf.get_collection(tf.GraphKeys.UPDATE_OPS)
      self.assertEqual(update_ops, [])

      optimizer = tf.train.GradientDescentOptimizer(learning_rate=1.0)
      total_loss, grads_and_vars = model_deploy.optimize_clones(clones,
                                                                optimizer)
      self.assertEqual(len(grads_and_vars), len(tf.trainable_variables()))
      self.assertEqual(total_loss.op.name, 'total_loss')
      for g, v in grads_and_vars:
        self.assertDeviceEqual(g.device, 'GPU:0')
        self.assertDeviceEqual(v.device, 'CPU:0') 

def main(unused_argv):
  if not FLAGS.input_file_pattern:
    raise ValueError("--input_file_pattern is required.")
  if not FLAGS.train_dir:
    raise ValueError("--train_dir is required.")

  model_config = configuration.model_config(
      input_file_pattern=FLAGS.input_file_pattern)
  training_config = configuration.training_config()

  tf.logging.info("Building training graph.")
  g = tf.Graph()
  with g.as_default():
    model = skip_thoughts_model.SkipThoughtsModel(model_config, mode="train")
    model.build()

    learning_rate = _setup_learning_rate(training_config, model.global_step)
    optimizer = tf.train.AdamOptimizer(learning_rate)

    train_tensor = tf.contrib.slim.learning.create_train_op(
        total_loss=model.total_loss,
        optimizer=optimizer,
        global_step=model.global_step,
        clip_gradient_norm=training_config.clip_gradient_norm)

    saver = tf.train.Saver()

  tf.contrib.slim.learning.train(
      train_op=train_tensor,
      logdir=FLAGS.train_dir,
      graph=g,
      global_step=model.global_step,
      number_of_steps=training_config.number_of_steps,
      save_summaries_secs=training_config.save_summaries_secs,
      saver=saver,
      save_interval_secs=training_config.save_model_secs) 

def evaluate():
  """Eval CIFAR-10 for a number of steps."""
  with tf.Graph().as_default() as g:
    # Get images and labels for CIFAR-10.
    eval_data = FLAGS.eval_data == 'test'
    images, labels = cifar10.inputs(eval_data=eval_data)

    # Build a Graph that computes the logits predictions from the
    # inference model.
    logits = cifar10.inference(images)

    # Calculate predictions.
    top_k_op = tf.nn.in_top_k(logits, labels, 1)

    # Restore the moving average version of the learned variables for eval.
    variable_averages = tf.train.ExponentialMovingAverage(
        cifar10.MOVING_AVERAGE_DECAY)
    variables_to_restore = variable_averages.variables_to_restore()
    saver = tf.train.Saver(variables_to_restore)

    # Build the summary operation based on the TF collection of Summaries.
    summary_op = tf.summary.merge_all()

    summary_writer = tf.summary.FileWriter(FLAGS.eval_dir, g)

    while True:
      eval_once(saver, summary_writer, top_k_op, summary_op)
      if FLAGS.run_once:
        break
      time.sleep(FLAGS.eval_interval_secs) 

def run_benchmark():
  """Run the benchmark on AlexNet."""
  with tf.Graph().as_default():
    # Generate some dummy images.
    image_size = 224
    # Note that our padding definition is slightly different the cuda-convnet.
    # In order to force the model to start with the same activations sizes,
    # we add 3 to the image_size and employ VALID padding above.
    images = tf.Variable(tf.random_normal([FLAGS.batch_size,
                                           image_size,
                                           image_size, 3],
                                          dtype=tf.float32,
                                          stddev=1e-1))

    # Build a Graph that computes the logits predictions from the
    # inference model.
    pool5, parameters = inference(images)

    # Build an initialization operation.
    init = tf.global_variables_initializer()

    # Start running operations on the Graph.
    config = tf.ConfigProto()
    config.gpu_options.allocator_type = 'BFC'
    sess = tf.Session(config=config)
    sess.run(init)

    # Run the forward benchmark.
    time_tensorflow_run(sess, pool5, "Forward")

    # Add a simple objective so we can calculate the backward pass.
    objective = tf.nn.l2_loss(pool5)
    # Compute the gradient with respect to all the parameters.
    grad = tf.gradients(objective, parameters)
    # Run the backward benchmark.
    time_tensorflow_run(sess, grad, "Forward-backward") 

def testBidirClassifier(self):
    at_methods = [None, 'rp', 'at', 'vat', 'atvat']
    for method in at_methods:
      FLAGS.adv_training_method = method
      with tf.Graph().as_default():
        graphs.VatxtBidirModel().classifier_graph()

        # Ensure variables have been reused
        # Embedding + 2 LSTM layers + hidden layers + logits layer
        expected_num_vars = 1 + 2 * 2 * FLAGS.rnn_num_layers + 2 * (
            FLAGS.cl_num_layers) + 2
        self.assertEqual(len(tf.trainable_variables()), expected_num_vars) 

def testATMethods(self):
    at_methods = [None, 'rp', 'at', 'vat', 'atvat']
    for method in at_methods:
      FLAGS.adv_training_method = method
      with tf.Graph().as_default():
        graphs.VatxtModel().classifier_graph()

        # Ensure variables have been reused
        # Embedding + LSTM layers + hidden layers + logits layer
        expected_num_vars = 1 + 2 * FLAGS.rnn_num_layers + 2 * (
            FLAGS.cl_num_layers) + 2
        self.assertEqual(len(tf.trainable_variables()), expected_num_vars) 

def main(_):
  # Images for inception classifier are normalized to be in [-1, 1] interval,
  # eps is a difference between pixels so it should be in [0, 2] interval.
  # Renormalizing epsilon from [0, 255] to [0, 2].
  eps = 2.0 * FLAGS.max_epsilon / 255.0
  batch_shape = [FLAGS.batch_size, FLAGS.image_height, FLAGS.image_width, 3]
  num_classes = 1001

  tf.logging.set_verbosity(tf.logging.INFO)

  with tf.Graph().as_default():
    # Prepare graph
    x_input = tf.placeholder(tf.float32, shape=batch_shape)

    model = InceptionModel(num_classes)

    fgsm = FastGradientMethod(model)
    x_adv = fgsm.generate(x_input, eps=eps, clip_min=-1., clip_max=1.)

    # Run computation
    saver = tf.train.Saver(slim.get_model_variables())
    session_creator = tf.train.ChiefSessionCreator(
        scaffold=tf.train.Scaffold(saver=saver),
        checkpoint_filename_with_path=FLAGS.checkpoint_path,
        master=FLAGS.master)

    with tf.train.MonitoredSession(session_creator=session_creator) as sess:
      for filenames, images in load_images(FLAGS.input_dir, batch_shape):
        adv_images = sess.run(x_adv, feed_dict={x_input: images})
        save_images(adv_images, filenames, FLAGS.output_dir) 

def evaluate(mnist):
    with tf.Graph().as_default() as g:
        x = tf.placeholder(tf.float32, [None, mnist_inference.INPUT_NODE], name='x-input')
        y_ = tf.placeholder(tf.float32, [None, mnist_inference.OUTPUT_NODE], name='y-input')
        validate_feed = {
            x: mnist.validation.images,
            y_: mnist.validation.labels}

        y = mnist_inference.inference(x, None)

        correct_prediction = tf.equal(tf.argmax(y, 1), tf.argmax(y_, 1))
        accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))

        variable_averages = tf.train.ExponentialMovingAverage(mnist_train.MOVING_AVERAGE_DECAY)
        variables_to_restore = variable_averages.variables_to_restore()
        saver = tf.train.Saver(variables_to_restore)

        while True:
            with tf.Session() as sess:
                ckpt = tf.train.get_checkpoint_state(mnist_train.MODEL_SAVE_PATH)
                if ckpt and ckpt.model_checkpoint_path:
                    saver.restore(sess, ckpt.model_checkpoint_path)
                    global_step = ckpt.model_checkpoint_path.split('/')[-1].split('-')[-1]
                    accuracy_score = sess.run(accuracy, feed_dict=validate_feed)
                    print("After %s training step(s), validation accuracy = %g" % (global_step, accuracy_score))
                else:
                    print("No Checkpoint file found")
                    return
            time.sleep(EVAL_INTERVAL_SECS) 

def main(_):
  eps = FLAGS.max_epsilon / 255.0
  batch_shape = [FLAGS.batch_size, FLAGS.image_height, FLAGS.image_width, 3]

  with tf.Graph().as_default():
    x_input = tf.placeholder(tf.float32, shape=batch_shape)
    noisy_images = x_input + eps * tf.sign(tf.random_normal(batch_shape))
    x_output = tf.clip_by_value(noisy_images, 0.0, 1.0)

    with tf.Session(FLAGS.master) as sess:
      for filenames, images in load_images(FLAGS.input_dir, batch_shape):
        out_images = sess.run(x_output, feed_dict={x_input: images})
        save_images(out_images, filenames, FLAGS.output_dir)