本文整理汇总了Python中syntaxnet.structured_graph_builder.StructuredGraphBuilder方法的典型用法代码示例。如果您正苦于以下问题：Python structured_graph_builder.StructuredGraphBuilder方法的具体用法？Python structured_graph_builder.StructuredGraphBuilder怎么用？Python structured_graph_builder.StructuredGraphBuilder使用的例子？那么恭喜您, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类syntaxnet.structured_graph_builder的用法示例。
在下文中一共展示了structured_graph_builder.StructuredGraphBuilder方法的1个代码示例，这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞，您的评价将有助于系统推荐出更棒的Python代码示例。
示例1: MakeGraph
# 需要导入模块: from syntaxnet import structured_graph_builder [as 别名]
# 或者: from syntaxnet.structured_graph_builder import StructuredGraphBuilder [as 别名]
def MakeGraph(self,
max_steps=10,
beam_size=2,
batch_size=1,
**kwargs):
"""Constructs a structured learning graph."""
assert max_steps > 0, 'Empty network not supported.'
logging.info('MakeGraph + %s', kwargs)
with self.test_session(graph=tf.Graph()) as sess:
feature_sizes, domain_sizes, embedding_dims, num_actions = sess.run(
gen_parser_ops.feature_size(task_context=self._task_context))
embedding_dims = [8, 8, 8]
hidden_layer_sizes = []
learning_rate = 0.01
builder = structured_graph_builder.StructuredGraphBuilder(
num_actions,
feature_sizes,
domain_sizes,
embedding_dims,
hidden_layer_sizes,
seed=1,
max_steps=max_steps,
beam_size=beam_size,
gate_gradients=True,
use_locking=True,
use_averaging=False,
check_parameters=False,
**kwargs)
builder.AddTraining(self._task_context,
batch_size,
learning_rate=learning_rate,
decay_steps=1000,
momentum=0.9,
corpus_name='training-corpus')
builder.AddEvaluation(self._task_context,
batch_size,
evaluation_max_steps=25,
corpus_name=None)
builder.training['inits'] = tf.group(*builder.inits.values(), name='inits')
return builder