Restore the variables.

init the logger file

inner_func

is_finished

Desc: 判断dist是否符合friend的条件 Args: self : self dist : (dist_x, dist_y) Return: True, if friend dist, False, if not

target spo是否在golden_spo_list中

:param s: :return:

knowledge seq2seq

knowledge seq2seq

Desc: 将seg转换为spgeo.LineString Args: self : self Return: spgeo.LineString Raise:

load tsv files

load tsv files

load tables from json files

Loads a vocabulary file into a dictionary.

Loads a vocabulary file into a dictionary.

Loads a vocabulary file into a dictionary.

Loads a vocabulary file into a dictionary.

Loads a vocabulary file into a dictionary.

Loads a vocabulary file into a dictionary.

Loads a vocabulary file into a dictionary.

copy data from 'src' to 'dst' in bytes

This function calculates and returns the precision, recall and f1-score Args: metric_fn: metric function pointer which calculates sco

Multi-Head Attention. Note that attn_bias is added to the logit before computing softmax activiation to mask certain selected positions so th

Multi-Head Attention. Note that attn_bias is added to the logit before computing softmax activiation to mask certain selected positions so th

Multi-Head Attention. Note that attn_bias is added to the logit before computing softmax activiation to mask certain selected positions so th

Multi-Head Attention. Note that attn_bias is added to the logit before computing softmax activiation to mask certain selected positions so th

Multi-Head Attention. Note that attn_bias is added to the logit before computing softmax activiation to mask certain selected positions so th

_list is a list or nested list, example turns/r/single turn c cut_type is head or tail, if _list len > length is used return a list len=

get owner

Pad the instances to the max sequence length in batch, and generate the corresponding position data and attention bias.

Pad the instances to the max sequence length in batch, and generate the corresponding position data and attention bias.

Pad the instances to the max sequence length in batch, and generate the corresponding position data and input mask.

Pad the instances to the max sequence length in batch, and generate the corresponding position data and input mask.

Pad the instances to the max sequence length in batch, and generate the corresponding position data and attention bias.

Pad the instances to the max sequence length in batch, and generate the corresponding position data and input mask.

Pad the instances to the max sequence length in batch, and generate the corresponding position data and input mask.

Pad the instances to the max sequence length in batch, and generate the corresponding position data and input mask.

padding ids

return all args

Args: Returns:

Args: Returns:

Load a config file into AttrDict

Args: Returns:

Args: Returns:

Args: Returns:

Args: Returns:

Args: Returns:

Args: Returns:

Peek the non-interpolated average precision at n. Returns: The non-interpolated average precision at n (default 0). If n is larger th

read pseudo-color label

Generate the initial values for the sinusoid position encoding table.

TBD

Prepares data for calculation of bleu and rouge scores.

Data generator wrapper for DataReader. If use py_reader, set the data provider for py_reader

Data generator wrapper for DataReader. If use py_reader, set the data provider for py_reader

:param sents_vec: # (batch_size, n_blocks, emb_dim) :param src_sents_slf_attn_bias: (batch_size, n_head, n_block, n_block) :param graph

Print arguments

Print para info for debug purpose

Args: patt (TYPE): NULL text (TYPE): NULL Returns: TODO Raises: NULL

read the data by line

read_data

read_data

Read a MRQA json file into a list of MRQAExample.

Read a MRQA json file into a list of MRQAExample.

reader_generater