Python utils.GetListOfFeatureNamesAndSizes() Examples

The following are 30 code examples of utils.GetListOfFeatureNamesAndSizes(). You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example. You may also want to check out all available functions/classes of the module utils , or try the search function .
Example #1
Source File: inference_autoencoder.py    From youtube-8m with Apache License 2.0 6 votes vote down vote up 
def main(unused_argv):
  logging.set_verbosity(tf.logging.INFO)

  # convert feature_names and feature_sizes to lists of values
  feature_names, feature_sizes = utils.GetListOfFeatureNamesAndSizes(
      FLAGS.feature_names, FLAGS.feature_sizes)

  if FLAGS.frame_features:
    reader = readers.YT8MFrameFeatureReader(feature_names=feature_names,
                                            feature_sizes=feature_sizes)
  else:
    reader = readers.YT8MAggregatedFeatureReader(feature_names=feature_names,
                                                 feature_sizes=feature_sizes)

  if FLAGS.output_file is "":
    raise ValueError("'output_file' was not specified. "
      "Unable to continue with inference.")

  if FLAGS.input_data_pattern is "":
    raise ValueError("'input_data_pattern' was not specified. "
      "Unable to continue with inference.")

  inference(reader, FLAGS.train_dir, FLAGS.input_data_pattern,
    FLAGS.output_file, FLAGS.batch_size, FLAGS.top_k)
Example #2
Source File: inference.py    From Y8M with Apache License 2.0 6 votes vote down vote up 
def main(unused_argv):
  logging.set_verbosity(tf.logging.INFO)

  # convert feature_names and feature_sizes to lists of values
  feature_names, feature_sizes = utils.GetListOfFeatureNamesAndSizes(
      FLAGS.feature_names, FLAGS.feature_sizes)

  if FLAGS.frame_features:
    reader = readers.YT8MFrameFeatureReader(feature_names=feature_names,
                                            feature_sizes=feature_sizes)
  else:
    reader = readers.YT8MAggregatedFeatureReader(feature_names=feature_names,
                                                 feature_sizes=feature_sizes)

  if FLAGS.output_file is "":
    raise ValueError("'output_file' was not specified. "
      "Unable to continue with inference.")

  if FLAGS.input_data_pattern is "":
    raise ValueError("'input_data_pattern' was not specified. "
      "Unable to continue with inference.")

  inference(reader, FLAGS.checkpoint_file, FLAGS.train_dir, FLAGS.input_data_pattern,
    FLAGS.output_file, FLAGS.batch_size, FLAGS.top_k)
Example #3
Source File: train.py    From Y8M with Apache License 2.0 6 votes vote down vote up 
def get_reader():
  # Convert feature_names and feature_sizes to lists of values.
  feature_names, feature_sizes = utils.GetListOfFeatureNamesAndSizes(
      FLAGS.feature_names, FLAGS.feature_sizes)

  if FLAGS.frame_features:
    reader = readers.YT8MFrameFeatureReader(
        num_classes = FLAGS.truncated_num_classes,
        feature_names=feature_names, feature_sizes=feature_sizes)
  else:
    reader = readers.YT8MAggregatedFeatureReader(
        num_classes = FLAGS.truncated_num_classes,
        decode_zlib = FLAGS.decode_zlib,
        feature_names=feature_names, feature_sizes=feature_sizes, feature_calcs=FLAGS.c_vars, feature_remove=FLAGS.r_vars)

  return reader
Example #4
Source File: inference-sample-error-analysis.py    From youtube-8m with Apache License 2.0 6 votes vote down vote up 
def main(unused_argv):
  logging.set_verbosity(tf.logging.INFO)

  # convert feature_names and feature_sizes to lists of values
  feature_names, feature_sizes = utils.GetListOfFeatureNamesAndSizes(
      FLAGS.feature_names, FLAGS.feature_sizes)

  if FLAGS.frame_features:
    reader = readers.YT8MFrameFeatureReader(feature_names=feature_names,
                                            feature_sizes=feature_sizes)
  else:
    reader = readers.YT8MAggregatedFeatureReader(feature_names=feature_names,
                                                 feature_sizes=feature_sizes)

  if FLAGS.output_file is "":
    raise ValueError("'output_file' was not specified. "
      "Unable to continue with inference.")

  if FLAGS.input_data_pattern is "":
    raise ValueError("'input_data_pattern' was not specified. "
      "Unable to continue with inference.")

  inference(reader, FLAGS.train_dir, FLAGS.input_data_pattern,
    FLAGS.output_file, FLAGS.batch_size, FLAGS.top_k)
Example #5
Source File: inference-layer.py    From youtube-8m with Apache License 2.0 6 votes vote down vote up 
def main(unused_argv):
  logging.set_verbosity(tf.logging.INFO)

  # convert feature_names and feature_sizes to lists of values
  feature_names, feature_sizes = utils.GetListOfFeatureNamesAndSizes(
      FLAGS.feature_names, FLAGS.feature_sizes)

  if FLAGS.frame_features:
    reader = readers.YT8MFrameFeatureReader(feature_names=feature_names,
                                            feature_sizes=feature_sizes)
  else:
    reader = readers.YT8MAggregatedFeatureReader(feature_names=feature_names,
                                                 feature_sizes=feature_sizes)

  if FLAGS.output_file is "":
    raise ValueError("'output_file' was not specified. "
      "Unable to continue with inference.")

  if FLAGS.input_data_pattern is "":
    raise ValueError("'input_data_pattern' was not specified. "
      "Unable to continue with inference.")

  inference(reader, FLAGS.train_dir, FLAGS.input_data_pattern,
    FLAGS.output_file, FLAGS.batch_size, FLAGS.top_k)
Example #6
Source File: train.py    From Y8M with Apache License 2.0 6 votes vote down vote up 
def get_reader():
  # Convert feature_names and feature_sizes to lists of values.
  feature_names, feature_sizes = utils.GetListOfFeatureNamesAndSizes(
      FLAGS.feature_names, FLAGS.feature_sizes)

  if FLAGS.frame_features:
    reader = readers.YT8MFrameFeatureReader(
        num_classes = FLAGS.truncated_num_classes,
        decode_zlib = FLAGS.decode_zlib,
        feature_names=feature_names, feature_sizes=feature_sizes)
  else:
    reader = readers.YT8MAggregatedFeatureReader(
        num_classes = FLAGS.truncated_num_classes,
        decode_zlib = FLAGS.decode_zlib,
        feature_names=feature_names, feature_sizes=feature_sizes)

  return reader
Example #7
Source File: inference.py    From Youtube-8M-WILLOW with Apache License 2.0 6 votes vote down vote up 
def main(unused_argv):
  logging.set_verbosity(tf.logging.INFO)

  # convert feature_names and feature_sizes to lists of values
  feature_names, feature_sizes = utils.GetListOfFeatureNamesAndSizes(
      FLAGS.feature_names, FLAGS.feature_sizes)

  if FLAGS.frame_features:
    reader = readers.YT8MFrameFeatureReader(feature_names=feature_names,
                                            feature_sizes=feature_sizes)
  else:
    reader = readers.YT8MAggregatedFeatureReader(feature_names=feature_names,
                                                 feature_sizes=feature_sizes)

  if FLAGS.output_file is "":
    raise ValueError("'output_file' was not specified. "
      "Unable to continue with inference.")

  if FLAGS.input_data_pattern is "":
    raise ValueError("'input_data_pattern' was not specified. "
      "Unable to continue with inference.")

  inference(reader, FLAGS.train_dir, FLAGS.input_data_pattern,
    FLAGS.output_file, FLAGS.batch_size, FLAGS.top_k)
Example #8
Source File: inference.py    From youtube-8m with Apache License 2.0 6 votes vote down vote up 
def main(unused_argv):
  logging.set_verbosity(tf.logging.INFO)

  # convert feature_names and feature_sizes to lists of values
  feature_names, feature_sizes = utils.GetListOfFeatureNamesAndSizes(
      FLAGS.feature_names, FLAGS.feature_sizes)

  if FLAGS.frame_features:
    reader = readers.YT8MFrameFeatureReader(feature_names=feature_names,
                                            feature_sizes=feature_sizes)
  else:
    reader = readers.YT8MAggregatedFeatureReader(feature_names=feature_names,
                                                 feature_sizes=feature_sizes)

  if FLAGS.output_file is "":
    raise ValueError("'output_file' was not specified. "
      "Unable to continue with inference.")

  if FLAGS.input_data_pattern is "":
    raise ValueError("'input_data_pattern' was not specified. "
      "Unable to continue with inference.")

  inference(reader, FLAGS.train_dir, FLAGS.input_data_pattern,
    FLAGS.output_file, FLAGS.batch_size, FLAGS.top_k)
Example #9
Source File: inference.py    From youtube-8m with Apache License 2.0 6 votes vote down vote up 
def main(unused_argv):
  logging.set_verbosity(tf.logging.INFO)

  # convert feature_names and feature_sizes to lists of values
  feature_names, feature_sizes = utils.GetListOfFeatureNamesAndSizes(
      FLAGS.feature_names, FLAGS.feature_sizes)

  if FLAGS.frame_features:
    reader = readers.YT8MFrameFeatureReader(feature_names=feature_names,
                                            feature_sizes=feature_sizes)
  else:
    reader = readers.YT8MAggregatedFeatureReader(feature_names=feature_names,
                                                 feature_sizes=feature_sizes)

  if FLAGS.output_file is "":
    raise ValueError("'output_file' was not specified. "
      "Unable to continue with inference.")

  if FLAGS.input_data_pattern is "":
    raise ValueError("'input_data_pattern' was not specified. "
      "Unable to continue with inference.")

  inference(reader, FLAGS.train_dir, FLAGS.input_data_pattern,
    FLAGS.output_file, FLAGS.batch_size, FLAGS.top_k)
Example #10
Source File: inference_test.py    From youtube-8m with Apache License 2.0 6 votes vote down vote up 
def main(unused_argv):
  logging.set_verbosity(tf.logging.INFO)

  # convert feature_names and feature_sizes to lists of values
  feature_names, feature_sizes = utils.GetListOfFeatureNamesAndSizes(
      FLAGS.feature_names, FLAGS.feature_sizes)

  if FLAGS.frame_features:
    reader = readers.YT8MFrameFeatureReader(feature_names=feature_names,
                                            feature_sizes=feature_sizes)
  else:
    reader = readers.YT8MAggregatedFeatureReader(feature_names=feature_names,
                                                 feature_sizes=feature_sizes)

  if FLAGS.output_file is "":
    raise ValueError("'output_file' was not specified. "
      "Unable to continue with inference.")

  if FLAGS.input_data_pattern is "":
    raise ValueError("'input_data_pattern' was not specified. "
      "Unable to continue with inference.")

  inference(reader, FLAGS.train_dir, FLAGS.input_data_pattern,
    FLAGS.output_file, FLAGS.batch_size, FLAGS.top_k)
Example #11
Source File: inference-pre-ensemble.py    From youtube-8m with Apache License 2.0 6 votes vote down vote up 
def main(unused_argv):
  logging.set_verbosity(tf.logging.INFO)

  # convert feature_names and feature_sizes to lists of values
  feature_names, feature_sizes = utils.GetListOfFeatureNamesAndSizes(
      FLAGS.feature_names, FLAGS.feature_sizes)

  if FLAGS.frame_features:
    reader = readers.YT8MFrameFeatureReader(feature_names=feature_names,
                                            feature_sizes=feature_sizes)
  else:
    reader = readers.YT8MAggregatedFeatureReader(feature_names=feature_names,
                                                 feature_sizes=feature_sizes)

  if FLAGS.output_dir is "":
    raise ValueError("'output_dir' was not specified. "
      "Unable to continue with inference.")

  if FLAGS.input_data_pattern is "":
    raise ValueError("'input_data_pattern' was not specified. "
      "Unable to continue with inference.")

  inference(reader, FLAGS.model_checkpoint_path, FLAGS.input_data_pattern,
      FLAGS.output_dir, FLAGS.batch_size, FLAGS.top_k)
Example #12
Source File: train_autoencoder.py    From youtube-8m with Apache License 2.0 5 votes vote down vote up 
def build_model(self):
    """Find the model and build the graph."""

    # Convert feature_names and feature_sizes to lists of values.
    feature_names, feature_sizes = utils.GetListOfFeatureNamesAndSizes(
        FLAGS.feature_names, FLAGS.feature_sizes)

    if FLAGS.frame_features:
      if FLAGS.frame_only:
          reader = readers.YT8MFrameFeatureOnlyReader(
              feature_names=feature_names, feature_sizes=feature_sizes)
      else:
          reader = readers.YT8MFrameFeatureReader(
              feature_names=feature_names, feature_sizes=feature_sizes)
    else:
      reader = readers.YT8MAggregatedFeatureReader(
          feature_names=feature_names, feature_sizes=feature_sizes)

    # Find the model.
    model = find_class_by_name(FLAGS.model,
                               [labels_autoencoder])()
    label_loss_fn = find_class_by_name(FLAGS.label_loss, [losses])()
    optimizer_class = find_class_by_name(FLAGS.optimizer, [tf.train])

    build_graph(reader=reader,
                 model=model,
                 optimizer_class=optimizer_class,
                 clip_gradient_norm=FLAGS.clip_gradient_norm,
                 train_data_pattern=FLAGS.train_data_pattern,
                 label_loss_fn=label_loss_fn,
                 base_learning_rate=FLAGS.base_learning_rate,
                 learning_rate_decay=FLAGS.learning_rate_decay,
                 learning_rate_decay_examples=FLAGS.learning_rate_decay_examples,
                 regularization_penalty=FLAGS.regularization_penalty,
                 num_readers=FLAGS.num_readers,
                 batch_size=FLAGS.batch_size,
                 num_epochs=FLAGS.num_epochs)

    logging.info("%s: Built graph.", task_as_string(self.task))

    return tf.train.Saver(max_to_keep=2, keep_checkpoint_every_n_hours=0.25)
Example #13
Source File: train.py    From youtube8mchallenge with Apache License 2.0 5 votes vote down vote up 
def get_reader():
  # Convert feature_names and feature_sizes to lists of values.
  feature_names, feature_sizes = utils.GetListOfFeatureNamesAndSizes(
      FLAGS.feature_names, FLAGS.feature_sizes)

  if FLAGS.frame_features:
    reader = readers.YT8MFrameFeatureReader(
        feature_names=feature_names, feature_sizes=feature_sizes)
  else:
    reader = readers.YT8MAggregatedFeatureReader(
        feature_names=feature_names, feature_sizes=feature_sizes)

  return reader
Example #14
Source File: inference.py    From youtube8mchallenge with Apache License 2.0 5 votes vote down vote up 
def main(unused_argv):
  logging.set_verbosity(tf.logging.INFO)
  if FLAGS.input_model_tgz:
    if FLAGS.train_dir:
      raise ValueError("You cannot supply --train_dir if supplying "
                       "--input_model_tgz")
    # Untar.
    if not os.path.exists(FLAGS.untar_model_dir):
      os.makedirs(FLAGS.untar_model_dir)
    tarfile.open(FLAGS.input_model_tgz).extractall(FLAGS.untar_model_dir)
    FLAGS.train_dir = FLAGS.untar_model_dir

  flags_dict_file = os.path.join(FLAGS.train_dir, "model_flags.json")
  if not os.path.exists(flags_dict_file):
    raise IOError("Cannot find %s. Did you run eval.py?" % flags_dict_file)
  flags_dict = json.loads(open(flags_dict_file).read())

  # convert feature_names and feature_sizes to lists of values
  feature_names, feature_sizes = utils.GetListOfFeatureNamesAndSizes(
      flags_dict["feature_names"], flags_dict["feature_sizes"])

  if flags_dict["frame_features"]:
    reader = readers.YT8MFrameFeatureReader(feature_names=feature_names,
                                            feature_sizes=feature_sizes)
  else:
    reader = readers.YT8MAggregatedFeatureReader(feature_names=feature_names,
                                                 feature_sizes=feature_sizes)

  if FLAGS.output_file is "":
    raise ValueError("'output_file' was not specified. "
      "Unable to continue with inference.")

  if FLAGS.input_data_pattern is "":
    raise ValueError("'input_data_pattern' was not specified. "
      "Unable to continue with inference.")

  inference(reader, FLAGS.train_dir, FLAGS.input_data_pattern,
    FLAGS.output_file, FLAGS.batch_size, FLAGS.top_k)
Example #15
Source File: inference_gpu.py    From youtube8mchallenge with Apache License 2.0 5 votes vote down vote up 
def main(unused_argv):
  logging.set_verbosity(tf.logging.INFO)
  if FLAGS.input_model_tgz:
    if FLAGS.train_dir:
      raise ValueError("You cannot supply --train_dir if supplying "
                       "--input_model_tgz")
    # Untar.
    if not os.path.exists(FLAGS.untar_model_dir):
      os.makedirs(FLAGS.untar_model_dir)
    tarfile.open(FLAGS.input_model_tgz).extractall(FLAGS.untar_model_dir)
    FLAGS.train_dir = FLAGS.untar_model_dir

  flags_dict_file = os.path.join(FLAGS.train_dir, "model_flags.json")
  if not os.path.exists(flags_dict_file):
    raise IOError("Cannot find %s. Did you run eval.py?" % flags_dict_file)
  flags_dict = json.loads(open(flags_dict_file).read())

  # convert feature_names and feature_sizes to lists of values
  feature_names, feature_sizes = utils.GetListOfFeatureNamesAndSizes(
      flags_dict["feature_names"], flags_dict["feature_sizes"])

  if flags_dict["frame_features"]:
    reader = readers.YT8MFrameFeatureReader(feature_names=feature_names,
                                            feature_sizes=feature_sizes)
  else:
    reader = readers.YT8MAggregatedFeatureReader(feature_names=feature_names,
                                                 feature_sizes=feature_sizes)

  if FLAGS.output_file is "":
    raise ValueError("'output_file' was not specified. "
      "Unable to continue with inference.")

  if FLAGS.input_data_pattern is "":
    raise ValueError("'input_data_pattern' was not specified. "
      "Unable to continue with inference.")

  inference(reader, FLAGS.train_dir, FLAGS.input_data_pattern,
    FLAGS.output_file, FLAGS.batch_size, FLAGS.top_k)
Example #16
Source File: train.py    From youtube-8m with Apache License 2.0 5 votes vote down vote up 
def get_reader():
  # Convert feature_names and feature_sizes to lists of values.
  feature_names, feature_sizes = utils.GetListOfFeatureNamesAndSizes(
      FLAGS.feature_names, FLAGS.feature_sizes)

  if FLAGS.frame_features:
    reader = readers.YT8MFrameFeatureReader(feature_names=feature_names,
                                            feature_sizes=feature_sizes,
                                            segment_labels=FLAGS.segment_labels)
  else:
    reader = readers.YT8MAggregatedFeatureReader(feature_names=feature_names,
                                                 feature_sizes=feature_sizes)

  return reader
Example #17
Source File: inference-sample-error.py    From youtube-8m with Apache License 2.0 5 votes vote down vote up 
def main(unused_argv):
  logging.set_verbosity(tf.logging.INFO)

  # convert feature_names and feature_sizes to lists of values
  feature_names, feature_sizes = utils.GetListOfFeatureNamesAndSizes(
      FLAGS.feature_names, FLAGS.feature_sizes)

  if FLAGS.frame_features:
    reader = readers.YT8MFrameFeatureReader(feature_names=feature_names,
                                            feature_sizes=feature_sizes)
  else:
    reader = readers.YT8MAggregatedFeatureReader(feature_names=feature_names,
                                                 feature_sizes=feature_sizes)

  if FLAGS.output_file is "":
    raise ValueError("'output_file' was not specified. "
      "Unable to continue with inference.")

  if FLAGS.input_data_pattern is "":
    raise ValueError("'input_data_pattern' was not specified. "
      "Unable to continue with inference.")

  model = find_class_by_name(FLAGS.model,
                             [frame_level_models, video_level_models])()
  transformer_fn = find_class_by_name(FLAGS.feature_transformer, 
                                         [feature_transform])

  build_graph(reader,
              model,
              input_data_pattern=FLAGS.input_data_pattern,
              batch_size=FLAGS.batch_size,
              transformer_class=transformer_fn)

  saver = tf.train.Saver(max_to_keep=3, keep_checkpoint_every_n_hours=10000000000)

  inference(saver, FLAGS.train_dir,
            FLAGS.output_file, FLAGS.batch_size, FLAGS.top_k)
Example #18
Source File: inference.py    From youtube-8m with Apache License 2.0 5 votes vote down vote up 
def main(unused_argv):
  logging.set_verbosity(tf.logging.INFO)
  if FLAGS.input_model_tgz:
    if FLAGS.train_dir:
      raise ValueError("You cannot supply --train_dir if supplying "
                       "--input_model_tgz")
    # Untar.
    if not os.path.exists(FLAGS.untar_model_dir):
      os.makedirs(FLAGS.untar_model_dir)
    tarfile.open(FLAGS.input_model_tgz).extractall(FLAGS.untar_model_dir)
    FLAGS.train_dir = FLAGS.untar_model_dir

  flags_dict_file = os.path.join(FLAGS.train_dir, "model_flags.json")
  if not file_io.file_exists(flags_dict_file):
    raise IOError("Cannot find %s. Did you run eval.py?" % flags_dict_file)
  flags_dict = json.loads(file_io.FileIO(flags_dict_file, "r").read())

  # convert feature_names and feature_sizes to lists of values
  feature_names, feature_sizes = utils.GetListOfFeatureNamesAndSizes(
      flags_dict["feature_names"], flags_dict["feature_sizes"])

  if flags_dict["frame_features"]:
    reader = readers.YT8MFrameFeatureReader(feature_names=feature_names,
                                            feature_sizes=feature_sizes)
  else:
    reader = readers.YT8MAggregatedFeatureReader(feature_names=feature_names,
                                                 feature_sizes=feature_sizes)

  if not FLAGS.output_file:
    raise ValueError("'output_file' was not specified. "
                     "Unable to continue with inference.")

  if not FLAGS.input_data_pattern:
    raise ValueError("'input_data_pattern' was not specified. "
                     "Unable to continue with inference.")

  inference(reader, FLAGS.train_dir, FLAGS.input_data_pattern,
            FLAGS.output_file, FLAGS.batch_size, FLAGS.top_k)
Example #19
Source File: multires_lstm_memory_deep_combine_chain_model.py    From youtube-8m with Apache License 2.0 5 votes vote down vote up 
def lstm(self, model_input, vocab_size, num_frames, sub_scope="", **unused_params):
    number_of_layers = FLAGS.lstm_layers
    lstm_sizes = map(int, FLAGS.lstm_cells.split(","))
    feature_names, feature_sizes = utils.GetListOfFeatureNamesAndSizes(
        FLAGS.feature_names, FLAGS.feature_sizes)
    sub_inputs = [tf.nn.l2_normalize(x, dim=2) for x in tf.split(model_input, feature_sizes, axis = 2)]

    assert len(lstm_sizes) == len(feature_sizes), \
      "length of lstm_sizes (={}) != length of feature_sizes (={})".format( \
      len(lstm_sizes), len(feature_sizes))

    states = []
    for i in xrange(len(feature_sizes)):
      with tf.variable_scope(sub_scope+"RNN%d" % i):
        sub_input = sub_inputs[i]
        lstm_size = lstm_sizes[i]
        ## Batch normalize the input
        stacked_lstm = tf.contrib.rnn.MultiRNNCell(
                [
                    tf.contrib.rnn.BasicLSTMCell(
                        lstm_size, forget_bias=1.0, state_is_tuple=True)
                    for _ in range(number_of_layers)
                    ],
                state_is_tuple=True)
        output, state = tf.nn.dynamic_rnn(stacked_lstm, sub_input,
                                         sequence_length=num_frames,
                                         swap_memory=FLAGS.rnn_swap_memory,
                                         dtype=tf.float32)
        states.extend(map(lambda x: x.c, state))
    final_state = tf.concat(states, axis = 1)
    return final_state
Example #20
Source File: lstm_cnn_deep_combine_chain_model.py    From youtube-8m with Apache License 2.0 5 votes vote down vote up 
def lstmoutput(self, model_input, vocab_size, num_frames):

    number_of_layers = FLAGS.lstm_layers

    lstm_sizes = map(int, FLAGS.lstm_cells.split(","))
    feature_names, feature_sizes = utils.GetListOfFeatureNamesAndSizes(
        FLAGS.feature_names, FLAGS.feature_sizes)
    sub_inputs = [tf.nn.l2_normalize(x, dim=2) for x in tf.split(model_input, feature_sizes, axis = 2)]

    assert len(lstm_sizes) == len(feature_sizes), \
      "length of lstm_sizes (={}) != length of feature_sizes (={})".format( \
      len(lstm_sizes), len(feature_sizes))

    outputs = []
    for i in xrange(len(feature_sizes)):
      with tf.variable_scope("RNN%d" % i):
        sub_input = sub_inputs[i]
        lstm_size = lstm_sizes[i]
        ## Batch normalize the input
        stacked_lstm = tf.contrib.rnn.MultiRNNCell(
                [
                    tf.contrib.rnn.BasicLSTMCell(
                        lstm_size, forget_bias=1.0, state_is_tuple=True)
                    for _ in range(number_of_layers)
                    ],
                state_is_tuple=True)

        output, state = tf.nn.dynamic_rnn(stacked_lstm, sub_input,
                                         sequence_length=num_frames,
                                         swap_memory=FLAGS.rnn_swap_memory,
                                         dtype=tf.float32)
        outputs.append(output)

    # concat
    final_output = tf.concat(outputs, axis=2)
    return final_output
Example #21
Source File: distillchain_lstm_cnn_deep_combine_chain_model.py    From youtube-8m with Apache License 2.0 5 votes vote down vote up 
def lstmoutput(self, model_input, vocab_size, num_frames):

    number_of_layers = FLAGS.lstm_layers

    lstm_sizes = map(int, FLAGS.lstm_cells.split(","))
    feature_names, feature_sizes = utils.GetListOfFeatureNamesAndSizes(
        FLAGS.feature_names, FLAGS.feature_sizes)
    sub_inputs = [tf.nn.l2_normalize(x, dim=2) for x in tf.split(model_input, feature_sizes, axis = 2)]

    assert len(lstm_sizes) == len(feature_sizes), \
      "length of lstm_sizes (={}) != length of feature_sizes (={})".format( \
      len(lstm_sizes), len(feature_sizes))

    outputs = []
    for i in xrange(len(feature_sizes)):
      with tf.variable_scope("RNN%d" % i):
        sub_input = sub_inputs[i]
        lstm_size = lstm_sizes[i]
        ## Batch normalize the input
        stacked_lstm = tf.contrib.rnn.MultiRNNCell(
                [
                    tf.contrib.rnn.BasicLSTMCell(
                        lstm_size, forget_bias=1.0, state_is_tuple=True)
                    for _ in range(number_of_layers)
                    ],
                state_is_tuple=True)

        output, state = tf.nn.dynamic_rnn(stacked_lstm, sub_input,
                                         sequence_length=num_frames,
                                         swap_memory=FLAGS.rnn_swap_memory,
                                         dtype=tf.float32)
        outputs.append(output)

    # concat
    final_output = tf.concat(outputs, axis=2)
    return final_output
Example #22
Source File: train_distill.py    From youtube8mchallenge with Apache License 2.0 5 votes vote down vote up 
def get_reader():
  # Convert feature_names and feature_sizes to lists of values.
  feature_names, feature_sizes = utils.GetListOfFeatureNamesAndSizes(
      FLAGS.feature_names, FLAGS.feature_sizes)

  if FLAGS.frame_features:
    reader = readers.YT8MFrameFeatureReader(
        feature_names=feature_names, feature_sizes=feature_sizes, distill=True)
  else:
    reader = readers.YT8MAggregatedFeatureReader(
        feature_names=feature_names, feature_sizes=feature_sizes)

  return reader
Example #23
Source File: train_embedding.py    From youtube-8m with Apache License 2.0 5 votes vote down vote up 
def build_model(self):
    """Find the model and build the graph."""

    # Convert feature_names and feature_sizes to lists of values.
    feature_names, feature_sizes = utils.GetListOfFeatureNamesAndSizes(
        FLAGS.feature_names, FLAGS.feature_sizes)

    if FLAGS.frame_features:
      if FLAGS.frame_only:
          reader = readers.YT8MFrameFeatureOnlyReader(
              feature_names=feature_names, feature_sizes=feature_sizes)
      else:
          reader = readers.YT8MFrameFeatureReader(
              feature_names=feature_names, feature_sizes=feature_sizes)
    else:
      reader = readers.YT8MAggregatedFeatureReader(
          feature_names=feature_names, feature_sizes=feature_sizes)

    # Find the model.
    model = find_class_by_name(FLAGS.model,
                               [labels_embedding])()
    label_loss_fn = find_class_by_name(FLAGS.label_loss, [losses_embedding])()
    optimizer_class = find_class_by_name(FLAGS.optimizer, [tf.train])

    build_graph(reader=reader,
                 model=model,
                 optimizer_class=optimizer_class,
                 clip_gradient_norm=FLAGS.clip_gradient_norm,
                 train_data_pattern=FLAGS.train_data_pattern,
                 label_loss_fn=label_loss_fn,
                 base_learning_rate=FLAGS.base_learning_rate,
                 learning_rate_decay=FLAGS.learning_rate_decay,
                 learning_rate_decay_examples=FLAGS.learning_rate_decay_examples,
                 regularization_penalty=FLAGS.regularization_penalty,
                 num_readers=FLAGS.num_readers,
                 batch_size=FLAGS.batch_size,
                 num_epochs=FLAGS.num_epochs)

    logging.info("%s: Built graph.", task_as_string(self.task))

    return tf.train.Saver(max_to_keep=2, keep_checkpoint_every_n_hours=0.25)
Example #24
Source File: inference.py    From AttentionCluster with Apache License 2.0 5 votes vote down vote up 
def main(unused_argv):
    logging.set_verbosity(tf.logging.INFO)
    if FLAGS.input_model_tgz:
        if FLAGS.train_dir:
            raise ValueError("You cannot supply --train_dir if supplying "
                             "--input_model_tgz")
        # Untar.
        if not file_io.file_exists(FLAGS.untar_model_dir):
            os.makedirs(FLAGS.untar_model_dir)
        tarfile.open(FLAGS.input_model_tgz).extractall(FLAGS.untar_model_dir)
        FLAGS.train_dir = FLAGS.untar_model_dir

    flags_dict_file = os.path.join(FLAGS.train_dir, "model_flags.json")
    if not file_io.file_exists(flags_dict_file):
        raise IOError("Cannot find %s. Did you run eval.py?" % flags_dict_file)
    flags_dict = json.loads(file_io.FileIO(flags_dict_file, "r").read())

    # convert feature_names and feature_sizes to lists of values
    feature_names, feature_sizes = utils.GetListOfFeatureNamesAndSizes(
        flags_dict["feature_names"], flags_dict["feature_sizes"])

    if flags_dict["frame_features"]:
        reader = readers.YT8MFrameFeatureReader(feature_names=feature_names,
                                                feature_sizes=feature_sizes)
    else:
        reader = readers.YT8MAggregatedFeatureReader(feature_names=feature_names,
                                                     feature_sizes=feature_sizes)

    if FLAGS.output_file is "":
        raise ValueError("'output_file' was not specified. "
                         "Unable to continue with inference.")

    if FLAGS.input_data_pattern is "":
        raise ValueError("'input_data_pattern' was not specified. "
                         "Unable to continue with inference.")

    inference(reader, FLAGS.train_dir, FLAGS.input_data_pattern,
              FLAGS.output_file, FLAGS.batch_size, FLAGS.top_k)
Example #25
Source File: train.py    From AttentionCluster with Apache License 2.0 5 votes vote down vote up 
def get_reader():
    # Convert feature_names and feature_sizes to lists of values.
    feature_names, feature_sizes = utils.GetListOfFeatureNamesAndSizes(
        FLAGS.feature_names, FLAGS.feature_sizes)

    if FLAGS.frame_features:
        reader = readers.YT8MFrameFeatureReader(
            feature_names=feature_names, feature_sizes=feature_sizes)
    else:
        reader = readers.YT8MAggregatedFeatureReader(
            feature_names=feature_names, feature_sizes=feature_sizes)

    return reader
Example #26
Source File: inference.py    From Y8M with Apache License 2.0 5 votes vote down vote up 
def main(unused_argv):
  logging.set_verbosity(tf.logging.INFO)
  print("START FLAGS===========================")
  print("train_dir: " +str(FLAGS.train_dir))
  print("output_file: " +str(FLAGS.output_file))
  print("input_data_pattern: " + str(FLAGS.input_data_pattern))
  print("frame_features: " + str(FLAGS.frame_features))
  print("batch_size: " +str(FLAGS.batch_size))
  print("feature_names: " + str(FLAGS.feature_names))
  print("feature_sizes: " + str(FLAGS.feature_sizes))
  print("c_vars: " + str(FLAGS.c_vars))
  print("num_readers: " + str(FLAGS.num_readers))
  print("top_k: " + str(FLAGS.top_k))
  print("layers_keep_probs: " + str(FLAGS.layers_keep_probs))
  print("gpu_only: " + str(FLAGS.gpu_only))
  print("END FLAGS ============================")
  # convert feature_names and feature_sizes to lists of values
  feature_names, feature_sizes = utils.GetListOfFeatureNamesAndSizes(
      FLAGS.feature_names, FLAGS.feature_sizes)

  if FLAGS.frame_features:
    reader = readers.YT8MFrameFeatureReader(feature_names=feature_names,
                                            feature_sizes=feature_sizes,
                                            num_classes=FLAGS.truncated_num_classes,
                                            decode_zlib=FLAGS.decode_zlib)
  else:
    reader = readers.YT8MAggregatedFeatureReader(
        num_classes = FLAGS.truncated_num_classes,
        decode_zlib = FLAGS.decode_zlib,
        feature_names=feature_names, feature_sizes=feature_sizes)

  if FLAGS.output_file is "":
    raise ValueError("'output_file' was not specified. "
      "Unable to continue with inference.")

  if FLAGS.input_data_pattern is "":
    raise ValueError("'input_data_pattern' was not specified. "
      "Unable to continue with inference.")

  inference(reader, FLAGS.train_dir, FLAGS.input_data_pattern,
    FLAGS.output_file, FLAGS.batch_size, FLAGS.top_k)
Example #27
Source File: check_video_id.py    From youtube-8m with Apache License 2.0 5 votes vote down vote up 
def check_video_id():
  tf.set_random_seed(0)  # for reproducibility
  with tf.Graph().as_default():
    # convert feature_names and feature_sizes to lists of values
    feature_names, feature_sizes = utils.GetListOfFeatureNamesAndSizes(
        FLAGS.feature_names, FLAGS.feature_sizes)

    # prepare a reader for each single model prediction result
    all_readers = []

    all_patterns = FLAGS.eval_data_patterns
    all_patterns = map(lambda x: x.strip(), all_patterns.strip().strip(",").split(","))
    for i in xrange(len(all_patterns)):
      reader = readers.EnsembleReader(
          feature_names=feature_names, feature_sizes=feature_sizes)
      all_readers.append(reader)

    input_reader = None
    input_data_pattern = None
    if FLAGS.input_data_pattern is not None:
      input_reader = readers.EnsembleReader(
          feature_names=["mean_rgb","mean_audio"], feature_sizes=[1024,128])
      input_data_pattern = FLAGS.input_data_pattern

    if FLAGS.eval_data_patterns is "":
      raise IOError("'eval_data_patterns' was not specified. " +
                     "Nothing to evaluate.")

    build_graph(
        all_readers=all_readers,
        input_reader=input_reader,
        input_data_pattern=input_data_pattern,
        all_eval_data_patterns=all_patterns,
        batch_size=FLAGS.batch_size)

    logging.info("built evaluation graph")
    video_id_equal = tf.get_collection("video_id_equal")[0]
    input_distance = tf.get_collection("input_distance")[0]

    check_loop(video_id_equal, input_distance, all_patterns)
Example #28
Source File: train.py    From Youtube-8M-WILLOW with Apache License 2.0 5 votes vote down vote up 
def get_reader():
  # Convert feature_names and feature_sizes to lists of values.
  feature_names, feature_sizes = utils.GetListOfFeatureNamesAndSizes(
      FLAGS.feature_names, FLAGS.feature_sizes)

  if FLAGS.frame_features:
    reader = readers.YT8MFrameFeatureReader(
        feature_names=feature_names, feature_sizes=feature_sizes)
  else:
    reader = readers.YT8MAggregatedFeatureReader(
        feature_names=feature_names, feature_sizes=feature_sizes)
    
  return reader
Example #29
Source File: train.py    From Y8M with Apache License 2.0 5 votes vote down vote up 
def get_reader():
  # Convert feature_names and feature_sizes to lists of values.
  feature_names, feature_sizes = utils.GetListOfFeatureNamesAndSizes(
      FLAGS.feature_names, FLAGS.feature_sizes)

  if FLAGS.frame_features:
    reader = readers.YT8MFrameFeatureReader(
        feature_names=feature_names, feature_sizes=feature_sizes)
  else:
    reader = readers.YT8MAggregatedFeatureReader(
        feature_names=feature_names, feature_sizes=feature_sizes)

  return reader
Example #30
Source File: eval.py    From youtube-8m with Apache License 2.0 4 votes vote down vote up 
def evaluate():
  tf.set_random_seed(0)  # for reproducibility
  with tf.Graph().as_default():
    # convert feature_names and feature_sizes to lists of values
    feature_names, feature_sizes = utils.GetListOfFeatureNamesAndSizes(
        FLAGS.feature_names, FLAGS.feature_sizes)

    if FLAGS.frame_features:
      reader = readers.YT8MFrameFeatureReader(feature_names=feature_names,
                                              feature_sizes=feature_sizes)
    else:
      reader = readers.YT8MAggregatedFeatureReader(feature_names=feature_names,
                                                   feature_sizes=feature_sizes)

    if FLAGS.distill_data_pattern is not None:
      distill_reader = readers.YT8MAggregatedFeatureReader(feature_names=["predictions"],
                                                   feature_sizes=[4716])
    else:
      distill_reader = None

    model = find_class_by_name(FLAGS.model,
        [frame_level_models, video_level_models])()
    label_loss_fn = find_class_by_name(FLAGS.label_loss, [losses])()
    transformer_class = find_class_by_name(FLAGS.feature_transformer, [feature_transform])

    if FLAGS.eval_data_pattern is "":
      raise IOError("'eval_data_pattern' was not specified. " +
                     "Nothing to evaluate.")

    build_graph(
        reader=reader,
        model=model,
        eval_data_pattern=FLAGS.eval_data_pattern,
        label_loss_fn=label_loss_fn,
        num_readers=FLAGS.num_readers,
        transformer_class=transformer_class,
        distill_reader=distill_reader,
        batch_size=FLAGS.batch_size)

    logging.info("built evaluation graph")
    video_id_batch = tf.get_collection("video_id_batch")[0]
    prediction_batch = tf.get_collection("predictions")[0]
    label_batch = tf.get_collection("labels")[0]
    loss = tf.get_collection("loss")[0]
    summary_op = tf.get_collection("summary_op")[0]

    saver = tf.train.Saver(tf.global_variables())
    summary_writer = tf.summary.FileWriter(
        FLAGS.train_dir, graph=tf.get_default_graph())

    evl_metrics = eval_util.EvaluationMetrics(reader.num_classes, FLAGS.top_k)

    last_global_step_val = -1
    while True:
      last_global_step_val = evaluation_loop(video_id_batch, prediction_batch,
                                             label_batch, loss, summary_op,
                                             saver, summary_writer, evl_metrics,
                                             last_global_step_val)
      if FLAGS.run_once:
        break