Python gen_parser_ops.beam_parser方法代碼示例

本文整理匯總了Python中syntaxnet.ops.gen_parser_ops.beam_parser方法的典型用法代碼示例。如果您正苦於以下問題：Python gen_parser_ops.beam_parser方法的具體用法？Python gen_parser_ops.beam_parser怎麽用？Python gen_parser_ops.beam_parser使用的例子？那麽, 這裏精選的方法代碼示例或許可以為您提供幫助。您也可以進一步了解該方法所在類syntaxnet.ops.gen_parser_ops的用法示例。

在下文中一共展示了gen_parser_ops.beam_parser方法的3個代碼示例，這些例子默認根據受歡迎程度排序。您可以為喜歡或者感覺有用的代碼點讚，您的評價將有助於係統推薦出更棒的Python代碼示例。

示例1: _BuildSequence

# 需要導入模塊: from syntaxnet.ops import gen_parser_ops [as 別名]
# 或者: from syntaxnet.ops.gen_parser_ops import beam_parser [as 別名]
def _BuildSequence(self,
                     batch_size,
                     max_steps,
                     features,
                     state,
                     use_average=False):
    """Adds a sequence of beam parsing steps."""
    def Advance(state, step, scores_array, alive, alive_steps, *features):
      scores = self._BuildNetwork(features,
                                  return_average=use_average)['logits']
      scores_array = scores_array.write(step, scores)
      features, state, alive = (
          gen_parser_ops.beam_parser(state, scores, self._feature_size))
      return [state, step + 1, scores_array, alive, alive_steps + tf.cast(
          alive, tf.int32)] + list(features)

    # args: (state, step, scores_array, alive, alive_steps, *features)
    def KeepGoing(*args):
      return tf.logical_and(args[1] < max_steps, tf.reduce_any(args[3]))

    step = tf.constant(0, tf.int32, [])
    scores_array = tensor_array_ops.TensorArray(dtype=tf.float32,
                                                size=0,
                                                dynamic_size=True)
    alive = tf.constant(True, tf.bool, [batch_size])
    alive_steps = tf.constant(0, tf.int32, [batch_size])
    t = tf.while_loop(
        KeepGoing,
        Advance,
        [state, step, scores_array, alive, alive_steps] + list(features),
        shape_invariants=[tf.TensorShape(None)] * (len(features) + 5),
        parallel_iterations=100)

    # Link to the final nodes/values of ops that have passed through While:
    return {'state': t[0],
            'concat_scores': t[2].concat(),
            'alive': t[3],
            'alive_steps': t[4]}

開發者ID:ringringyi，項目名稱:DOTA_models，代碼行數:40，代碼來源:structured_graph_builder.py

示例2: _BuildSequence

# 需要導入模塊: from syntaxnet.ops import gen_parser_ops [as 別名]
# 或者: from syntaxnet.ops.gen_parser_ops import beam_parser [as 別名]
def _BuildSequence(self,
                     batch_size,
                     max_steps,
                     features,
                     state,
                     use_average=False):
    """Adds a sequence of beam parsing steps."""
    def Advance(state, step, scores_array, alive, alive_steps, *features):
      scores = self._BuildNetwork(features,
                                  return_average=use_average)['logits']
      scores_array = scores_array.write(step, scores)
      features, state, alive = (
          gen_parser_ops.beam_parser(state, scores, self._feature_size))
      return [state, step + 1, scores_array, alive, alive_steps + tf.cast(
          alive, tf.int32)] + list(features)

    # args: (state, step, scores_array, alive, alive_steps, *features)
    def KeepGoing(*args):
      return tf.logical_and(args[1] < max_steps, tf.reduce_any(args[3]))

    step = tf.constant(0, tf.int32, [])
    scores_array = tensor_array_ops.TensorArray(dtype=tf.float32,
                                                size=0,
                                                dynamic_size=True)
    alive = tf.constant(True, tf.bool, [batch_size])
    alive_steps = tf.constant(0, tf.int32, [batch_size])
    t = tf.while_loop(
        KeepGoing,
        Advance,
        [state, step, scores_array, alive, alive_steps] + list(features),
        parallel_iterations=100)

    # Link to the final nodes/values of ops that have passed through While:
    return {'state': t[0],
            'concat_scores': t[2].concat(),
            'alive': t[3],
            'alive_steps': t[4]}

開發者ID:llSourcell，項目名稱:AI_Reader，代碼行數:39，代碼來源:structured_graph_builder.py

示例3: _BuildSequence

# 需要導入模塊: from syntaxnet.ops import gen_parser_ops [as 別名]
# 或者: from syntaxnet.ops.gen_parser_ops import beam_parser [as 別名]
def _BuildSequence(self,
                     batch_size,
                     max_steps,
                     features,
                     state,
                     use_average=False):
    """Adds a sequence of beam parsing steps."""
    def Advance(state, step, scores_array, alive, alive_steps, *features):
      scores = self._BuildNetwork(features,
                                  return_average=use_average)['logits']
      scores_array = scores_array.write(step, scores)
      features, state, alive = (
          gen_parser_ops.beam_parser(state, scores, self._feature_size))
      return [state, step + 1, scores_array, alive, alive_steps + tf.cast(
          alive, tf.int32)] + list(features)

    # args: (state, step, scores_array, alive, alive_steps, *features)
    def KeepGoing(*args):
      return tf.logical_and(args[1] < max_steps, tf.reduce_any(args[3]))

    step = tf.constant(0, tf.int32, [])
    scores_array = tensor_array_ops.TensorArray(
        dtype=tf.float32, size=0, infer_shape=False, dynamic_size=True)
    alive = tf.constant(True, tf.bool, [batch_size])
    alive_steps = tf.constant(0, tf.int32, [batch_size])
    t = tf.while_loop(
        KeepGoing,
        Advance,
        [state, step, scores_array, alive, alive_steps] + list(features),
        shape_invariants=[tf.TensorShape(None)] * (len(features) + 5),
        parallel_iterations=100)

    # Link to the final nodes/values of ops that have passed through While:
    return {'state': t[0],
            'concat_scores': t[2].concat(),
            'alive': t[3],
            'alive_steps': t[4]}

開發者ID:generalized-iou，項目名稱:g-tensorflow-models，代碼行數:39，代碼來源:structured_graph_builder.py

注：本文中的syntaxnet.ops.gen_parser_ops.beam_parser方法示例由純淨天空整理自Github/MSDocs等開源代碼及文檔管理平台，相關代碼片段篩選自各路編程大神貢獻的開源項目，源碼版權歸原作者所有，傳播和使用請參考對應項目的License；未經允許，請勿轉載。