utils.py

import os
import json
import logging
import random
import time
from datetime import timedelta

import numpy as np
import torch
from torch.utils.data import TensorDataset
from transformers import BertForSequenceClassification

def get_time_dif(start_time):
    """获取已使用时间"""
    end_time = time.time()
    time_dif = end_time - start_time
    return timedelta(seconds=int(round(time_dif)))

def set_seed(seed):
    np.random.seed(seed)
    random.seed(seed)
    torch.manual_seed(seed)
    torch.cuda.manual_seed_all(seed)
    # torch.backends.cudnn.deterministic = True

def set_logger(log_path):
    """
    Args:
        log_path: (string) where to log
    """
    logger = logging.getLogger()
    logger.setLevel(logging.INFO)
    if not logger.handlers:
        # Logging to a file
        file_handler = logging.FileHandler(log_path, mode='w', encoding='utf-8')
        file_handler.setFormatter(logging.Formatter('%(asctime)s:%(levelname)s: %(message)s'))
        logger.addHandler(file_handler)

        # Logging to console
        stream_handler = logging.StreamHandler()
        stream_handler.setFormatter(logging.Formatter('%(message)s'))
        logger.addHandler(stream_handler)


# bert4keras snippets
def is_string(s):
    """判断是否是字符串
    """
    return isinstance(s, str)

def convert_to_unicode(text, encoding='utf-8', errors='ignore'):
    """字符串转换为unicode格式（假设输入为utf-8格式）
    """
    if isinstance(text, bytes):
        text = text.decode(encoding, errors=errors)
    return text