Get the vocab file and casing info from the Hub module.

Create `TrainingInstance`s from raw text.

Create `TrainingInstance`s from raw text.

Looks up words embeddings for id tensor. Args: input_ids: int32 Tensor of shape [batch_size, seq_length] containing word ids. vocab_s

Performs various post-processing on a word embedding tensor. Args: input_tensor: float Tensor of shape [batch_size, seq_length, embedding

Flattens (potentially nested) a tuple/dictionary/list to a list.

r"""Compute focal loss for predictions. Multi-labels Focal loss formula: FL = -alpha * (z-p)^gamma * log(p) -(1-alpha) * p^gamma *

Constructs a `BertConfig` from a Python dictionary of parameters.

Gathers the vectors at the specific positions over a minibatch.

Gathers the vectors at the specific positions over a minibatch.

一次性预测所有句子

Maps a string to a Python function, e.g., "relu" => `tf.nn.relu`. Args: activation_string: String name of the activation function. Returns:

Gets a collection of `InputExample`s for the dev set.

Gets output of the embedding lookup (i.e., input to the transformer). Returns: float Tensor of shape [batch_size, seq_length, hidden_size]

Project the tokenized prediction back to the original text.

Gets the list of labels for this data set.

Get loss and log probs for the masked LM.

Get loss and log probs for the masked LM.

Get loss and log probs for the next sentence prediction.

Get loss and log probs for the next sentence prediction.

Gets a collection of `InputExample`s for prediction.

Gets a collection of `InputExample`s for the train set.

Finds all of the tensors in graph that are unreachable from outputs.

Creates an `input_fn` closure to be passed to TPUEstimator.

Runs layer normalization followed by dropout.

Loads a vocabulary file into a dictionary.

Returns `model_fn` closure for TPUEstimator.

Returns `model_fn` closure for TPUEstimator.

Returns `model_fn` closure for TPUEstimator.

Returns `model_fn` closure for TPUEstimator.

Returns `model_fn` closure for TPUEstimator.

Returns `model_fn` closure for TPUEstimator.

Returns `model_fn` closure for TPUEstimator.

Write a InputFeature to the TFRecordWriter as a tf.train.Example.

Read a list of `InputExample`s from an input file.

用划分好的测试集取搜索最优的阈值，精度0.1,再低会过拟合，最好使用交叉验证来做 由于交叉验证bert代价很大，就没做 :param domain: 数据集类别，divorce、labor、loan :param model_pb: pb模型文件 :para

Serializes this instance to a Python dictionary.

Serializes this instance to a JSON string.

Multi-headed, multi-layer Transformer from "Attention is All You Need". This is almost an exact implementation of the original Transformer encoder.

Truncates a pair of sequences to a maximum sequence length.

Truncates a pair of sequences to a maximum sequence length.

Validate the input FLAGS or throw an exception.

Create TF example files from `TrainingInstance`s.

Create TF example files from `TrainingInstance`s.

Write final predictions to the json file and log-odds of null if needed.

Constructs a InputExample. Args: guid: Unique id for the example. text_a: string. The untokenized text of the first seque

:param task: 任务类型，包括divorce，labor，loan :param pb_model: pb模型文件名 :param tagDir: 任务标签tags文件 :param threshold: 多标签分类的阈值列

:param embedding: bert生成的embedding :param context_dim: lstm隐藏层维度 :param hidden_dim:全连接层隐藏层维度 :param dropout_keep_prob

:param embedding: bert生成的embedding :param context_dim: lstm隐藏层维度 :param hidden_dim:全连接层隐藏层维度 :param dropout_keep_prob

Constructs a BasicTokenizer. Args: do_lower_case: Whether to lower case the input.

Constructs a InputExample. Args: guid: Unique id for the example. text_a: string. The untokenized text of the first sequence. For sin

Constructs a AdamWeightDecayOptimizer.

Constructs BertConfig. Args: vocab_size: Vocabulary size of `inputs_ids` in `BertModel`. hidden_size: Size of the encoder layers and

Constructor for BertModel. Args: config: `BertConfig` instance. is_training: bool. true for training model, false for eval model. Con

Convert a set of `InputExample`s to a list of `InputFeatures`.

Convert a set of `InputExample`s to a list of `InputFeatures`.

Creates a classification model.

Creates an optimizer training op.

Gaussian Error Linear Unit. This is a smoother version of the RELU. Original paper: https://arxiv.org/abs/1606.08415 Args: x: float Tensor