o Qe@svddlmZddlmZmZmZddlmZddlm Z m Z ddl m Z m Z ddgZ d d dZGd ddeZd S))Layer)core_non_static_modein_dygraph_mode) LayerHelper)check_variable_and_dtype check_type)_C_ops _legacy_C_opsviterbi_decodeViterbiDecoderTNc Cstr t||||Strt|||d|St|dddgdt|dddgdt|dddt|d tdtdit }d|i}| |j }| d}|j d|||d ||d |d ||fS)a Decode the highest scoring sequence of tags computed by transitions and potentials and get the viterbi path. Args: potentials (Tensor): The input tensor of unary emission. This is a 3-D tensor with shape of [batch_size, sequence_length, num_tags]. The data type is float32 or float64. transition_params (Tensor): The input tensor of transition matrix. This is a 2-D tensor with shape of [num_tags, num_tags]. The data type is float32 or float64. lengths (Tensor): The input tensor of length of each sequence. This is a 1-D tensor with shape of [batch_size]. The data type is int64. include_bos_eos_tag (`bool`, optional): If set to True, the last row and the last column of transitions will be considered as start tag, the second to last row and the second to last column of transitions will be considered as stop tag. Defaults to ``True``. name (str, optional): The default value is None. Normally there is no need for user to set this property. For more information, please refer to :ref:`api_guide_Name`. Returns: scores(Tensor): The output tensor containing the score for the Viterbi sequence. The shape is [batch_size] and the data type is float32 or float64. paths(Tensor): The output tensor containing the highest scoring tag indices. The shape is [batch_size, sequence_length] and the data type is int64. Example: .. code-block:: python import paddle paddle.seed(102) batch_size, seq_len, num_tags = 2, 4, 3 emission = paddle.rand((batch_size, seq_len, num_tags), dtype='float32') length = paddle.randint(1, seq_len + 1, [batch_size]) tags = paddle.randint(0, num_tags, [batch_size, seq_len]) transition = paddle.rand((num_tags, num_tags), dtype='float32') scores, path = paddle.text.viterbi_decode(emission, transition, length, False) # scores: [3.37089300, 1.56825531], path: [[1, 0, 0], [1, 1, 0]] include_bos_eos_taginputZfloat32Zfloat64r transitionslengthZint64Z include_tag)ZInputZ TransitionZLength)ZScoresPath)typeZinputsZoutputsattrsN)r ) rr r rr rrboolrlocalsZ"create_variable_for_type_inferenceZdtypeZ append_op) potentialsZtransition_paramslengthsrnamehelperrZscorespathrJD:\Projects\ConvertPro\env\Lib\site-packages\paddle/text/viterbi_decode.pyr s@%     cs*eZdZdZdfdd ZddZZS) r a& Decode the highest scoring sequence of tags computed by transitions and potentials and get the viterbi path. Args: transitions (`Tensor`): The transition matrix. Its dtype is float32 and has a shape of `[num_tags, num_tags]`. include_bos_eos_tag (`bool`, optional): If set to True, the last row and the last column of transitions will be considered as start tag, the second to last row and the second to last column of transitions will be considered as stop tag. Defaults to ``True``. name (str, optional): The default value is None. Normally there is no need for user to set this property. For more information, please refer to :ref:`api_guide_Name`. Shape: potentials (Tensor): The input tensor of unary emission. This is a 3-D tensor with shape of [batch_size, sequence_length, num_tags]. The data type is float32 or float64. lengths (Tensor): The input tensor of length of each sequence. This is a 1-D tensor with shape of [batch_size]. The data type is int64. Returns: scores(Tensor): The output tensor containing the score for the Viterbi sequence. The shape is [batch_size] and the data type is float32 or float64. paths(Tensor): The output tensor containing the highest scoring tag indices. The shape is [batch_size, sequence_length] and the data type is int64. Example: .. code-block:: python import paddle paddle.seed(102) batch_size, seq_len, num_tags = 2, 4, 3 emission = paddle.rand((batch_size, seq_len, num_tags), dtype='float32') length = paddle.randint(1, seq_len + 1, [batch_size]) tags = paddle.randint(0, num_tags, [batch_size, seq_len]) transition = paddle.rand((num_tags, num_tags), dtype='float32') decoder = paddle.text.ViterbiDecoder(transition, include_bos_eos_tag=False) scores, path = decoder(emission, length) # scores: [3.37089300, 1.56825531], path: [[1, 0, 0], [1, 1, 0]] TNcs$tt|||_||_||_dSN)superr __init__rrr)selfrrr __class__rrr s zViterbiDecoder.__init__cCst||j||j|jSr)r rrr)r!rrrrrforwards zViterbiDecoder.forwardTN)__name__ __module__ __qualname____doc__r r$ __classcell__rrr"rr ]s$r%)nnrZfluid.frameworkrrrZfluid.layer_helperrZfluid.data_feederrrZpaddler r __all__r r rrrrs   E