生成 ocr key 字符集 alphabet
import pickle as pkl#----------- 生成 ocr key 字符集 alphabet alphabet_set = set() # 数据集label infofiles_label = ['/home/jlb/下载/rec_data_lesson_demo/train.txt', '/home/jlb/下载/rec_data_lesson_demo/val.txt']# ppocr中文key infofiles = ['/home/jlb/Project/OCR/ocr/recognize/ppocr_keys_v1.txt']for infofile in infofiles:f = open(infofile)content = f.readlines()f.close()for line in content:line = line.replace("\n", "")alphabet_set.add(line)for infofile in infofiles_label:f = open(infofile)content = f.readlines()f.close()for line in content:if len(line.strip())>0:if len(line.strip().split('\t'))!=2:print(line)else:fname,label = line.strip().split('\t')for ch in label:alphabet_set.add(ch)alphabet_list = sorted(list(alphabet_set)) pkl.dump(alphabet_list, open('alphabet.pkl','wb'))
读取字符集 alphabet
#----------- 读取字符集 alphabet
alphabet_list = pkl.load(open('/home/jlb/Project/OCR/ocr/recognize/alphabet.pkl','rb'))
alphabet = [ord(ch) for ch in alphabet_list]
alphabet_v2 = alphabet
print("----------------------- alphabet_v2:", len(alphabet_list), alphabet_list)