Python spec_pb2.TrainTarget方法代碼示例

# 需要導入模塊: from dragnn.protos import spec_pb2 [as 別名]
# 或者: from dragnn.protos.spec_pb2 import TrainTarget [as 別名]
def RunTraining(self, hyperparam_config):
    master_spec = self.LoadSpec('master_spec_link.textproto')

    self.assertTrue(isinstance(hyperparam_config, spec_pb2.GridPoint))
    gold_doc = sentence_pb2.Sentence()
    text_format.Parse(_DUMMY_GOLD_SENTENCE, gold_doc)
    gold_doc_2 = sentence_pb2.Sentence()
    text_format.Parse(_DUMMY_GOLD_SENTENCE_2, gold_doc_2)
    reader_strings = [
        gold_doc.SerializeToString(), gold_doc_2.SerializeToString()
    ]
    tf.logging.info('Generating graph with config: %s', hyperparam_config)
    with tf.Graph().as_default():
      builder = graph_builder.MasterBuilder(master_spec, hyperparam_config)

      target = spec_pb2.TrainTarget()
      target.name = 'testTraining-all'
      train = builder.add_training_from_config(target)
      with self.test_session() as sess:
        logging.info('Initializing')
        sess.run(tf.global_variables_initializer())

        # Run one iteration of training and verify nothing crashes.
        logging.info('Training')
        sess.run(train['run'], feed_dict={train['input_batch']: reader_strings}) 

# 需要導入模塊: from dragnn.protos import spec_pb2 [as 別名]
# 或者: from dragnn.protos.spec_pb2 import TrainTarget [as 別名]
def default_targets_from_spec(spec):
  """Constructs a default set of TrainTarget protos from a DRAGNN spec.

  For each component in the DRAGNN spec, it adds a training target for that
  component's oracle. It also stops unrolling the graph with that component.  It
  skips any 'shift-only' transition systems which have no oracle. E.g.: if there
  are three components, a 'shift-only', a 'tagger', and a 'arc-standard', it
  will construct two training targets, one for the tagger and one for the
  arc-standard parser.

  Arguments:
    spec: DRAGNN spec.

  Returns:
    List of TrainTarget protos.
  """
  component_targets = [
      spec_pb2.TrainTarget(
          name=component.name,
          max_index=idx + 1,
          unroll_using_oracle=[False] * idx + [True])
      for idx, component in enumerate(spec.component)
      if not component.transition_system.registered_name.endswith('shift-only')
  ]
  return component_targets 

# 需要導入模塊: from dragnn.protos import spec_pb2 [as 別名]
# 或者: from dragnn.protos.spec_pb2 import TrainTarget [as 別名]
def getBuilderAndTarget(
      self, test_name, master_spec_path='simple_parser_master_spec.textproto'):
    """Generates a MasterBuilder and TrainTarget based on a simple spec."""
    master_spec = self.LoadSpec(master_spec_path)
    hyperparam_config = spec_pb2.GridPoint()
    target = spec_pb2.TrainTarget()
    target.name = 'test-%s-train' % test_name
    target.component_weights.extend([0] * len(master_spec.component))
    target.component_weights[-1] = 1.0
    target.unroll_using_oracle.extend([False] * len(master_spec.component))
    target.unroll_using_oracle[-1] = True
    builder = graph_builder.MasterBuilder(
        master_spec, hyperparam_config, pool_scope=test_name)
    return builder, target 

# 需要導入模塊: from dragnn.protos import spec_pb2 [as 別名]
# 或者: from dragnn.protos.spec_pb2 import TrainTarget [as 別名]
def RunTraining(self, hyperparam_config):
    master_spec = self.LoadSpec('master_spec_link.textproto')

    self.assertTrue(isinstance(hyperparam_config, spec_pb2.GridPoint))
    gold_doc = sentence_pb2.Sentence()
    text_format.Parse(_DUMMY_GOLD_SENTENCE, gold_doc)
    gold_doc_2 = sentence_pb2.Sentence()
    text_format.Parse(_DUMMY_GOLD_SENTENCE_2, gold_doc_2)
    reader_strings = [
        gold_doc.SerializeToString(),
        gold_doc_2.SerializeToString()
    ]
    tf.logging.info('Generating graph with config: %s', hyperparam_config)
    with tf.Graph().as_default():
      builder = graph_builder.MasterBuilder(master_spec, hyperparam_config)

      target = spec_pb2.TrainTarget()
      target.name = 'testTraining-all'
      train = builder.add_training_from_config(target)
      with self.test_session() as sess:
        logging.info('Initializing')
        sess.run(tf.global_variables_initializer())

        # Run one iteration of training and verify nothing crashes.
        logging.info('Training')
        sess.run(train['run'], feed_dict={train['input_batch']: reader_strings}) 

# 需要導入模塊: from dragnn.protos import spec_pb2 [as 別名]
# 或者: from dragnn.protos.spec_pb2 import TrainTarget [as 別名]
def main(argv):
  del argv  # unused
  # Constructs lexical resources for SyntaxNet in the given resource path, from
  # the training data.
  lexicon.build_lexicon(
      lexicon_dir,
      training_sentence,
      training_corpus_format='sentence-prototext')

  # Construct the ComponentSpec for tagging. This is a simple left-to-right RNN
  # sequence tagger.
  tagger = spec_builder.ComponentSpecBuilder('tagger')
  tagger.set_network_unit(name='FeedForwardNetwork', hidden_layer_sizes='256')
  tagger.set_transition_system(name='tagger')
  tagger.add_fixed_feature(name='words', fml='input.word', embedding_dim=64)
  tagger.add_rnn_link(embedding_dim=-1)
  tagger.fill_from_resources(lexicon_dir)

  master_spec = spec_pb2.MasterSpec()
  master_spec.component.extend([tagger.spec])

  hyperparam_config = spec_pb2.GridPoint()

  # Build the TensorFlow graph.
  graph = tf.Graph()
  with graph.as_default():
    builder = graph_builder.MasterBuilder(master_spec, hyperparam_config)

    target = spec_pb2.TrainTarget()
    target.name = 'all'
    target.unroll_using_oracle.extend([True])
    dry_run = builder.add_training_from_config(target, trace_only=True)

  # Read in serialized protos from training data.
  sentence = sentence_pb2.Sentence()
  text_format.Merge(open(training_sentence).read(), sentence)
  training_set = [sentence.SerializeToString()]

  with tf.Session(graph=graph) as sess:
    # Make sure to re-initialize all underlying state.
    sess.run(tf.initialize_all_variables())
    traces = sess.run(
        dry_run['traces'], feed_dict={dry_run['input_batch']: training_set})

  with open('dragnn_tutorial_1.html', 'w') as f:
    f.write(visualization.trace_html(traces[0], height='300px').encode('utf-8'))