散落的文件组成一个数据集,需要按照指定规则存储成一个文件,并存储,代码如下:
import os import jsonlines def find_txt_files(path): txt_files = [] for root, dirs, files in os.walk(path): for file in files: if file.endswith('.txt'): txt_files.append(os.path.join(root, file)) return txt_files path = 'D:\\OpenAI\\yolov5\\datasets\\\coco128\\labels' # 请替换为实际文件夹路径 txt_files = find_txt_files(path) x=[] for i in txt_files: with open(i, 'r', encoding='utf-8') as file: value={} value['instruction'] = '请根据古诗题目,回复古诗内容,要求对仗工整押韵' value['input'] = i.split('\\')[-1].split('.')[0] value['output'] = file.read().replace('\n', '') x.append(value) with jsonlines.open('outputgus4444.jsonl','w')as file1: file1.write_all(x) # print(txt_files)
import os import jsonlines def find_txt_files(path): txt_files = [] for root, dirs, files in os.walk(path): for file in files: if file.endswith('.txt'): txt_files.append(os.path.join(root, file)) return txt_files path = 'D:\\OpenAI\\yolov5\\datasets\\\coco128\\labels' # 请替换为实际文件夹路径 txt_files = find_txt_files(path) x=[] for i in txt_files: with open(i, 'r', encoding='utf-8') as file: value={} value['instruction'] = '请根据古诗题目,回复古诗内容,要求对仗工整押韵' value['input'] = i.split('\\')[-1].split('.')[0] value['output'] = file.read().replace('\n', '') x.append(value) with jsonlines.open('outputgus4444.jsonl','w')as file1: file1.write_all(x) # print(txt_files)