| 123456789101112131415161718192021 |
- fp = open('materials/ch_dict.txt', 'r', encoding='utf-8')
- fp2 = open('materials/chinese_cht_dict.txt', 'r', encoding='utf-8')
- fp1 = open('materials/tw_idcard_dict.txt', 'a', encoding='utf-8')
- list = []
- for line in fp.readlines():
- # print(line.split('\t')[-1].rstrip('\n'))
- list.extend(line.split('\t')[-1].rstrip('\n'))
- list2 = []
- for line in fp2.readlines():
- # print(line.split('\t')[-1].rstrip('\n'))
- list2.extend(line.split('\t')[-1].rstrip('\n'))
- list.extend(list2)
- for word in set(list):
- fp1.write(word+'\n')
- # python tools/train.py -c configs/rec/PP-OCRv3/ch_PP-OCRv3_rec.yml
- # visualdl --logdir output/tw_idcard/vdl --port 8080
|
