项目场景:
主要完成OCR训练前,dataset需要加载的lmdb格式的文件。
问题描述:
直接上代码,一看就明白:
#@Override
import os
def Combine_txt():
dirpath = r"E:\enducate\test_paper\Train_code\txt1111"
files = os.listdir(dirpath)
res = ""
for file in files:
if file.endswith(".txt"):
name = file[:-3] + "png"
img_path = os.path.join(dirpath, name)
txtpath = os.path.join(dirpath, file)
with open(txtpath, "r", encoding="utf-8") as file:
content = file.read()
text = img_path + "\t" + content
file.close()
input = "%s\n" % (text)
res += input
outpath = r'E:\enducate\test_paper\Train_code\output.txt'
with open(outpath, "a", encoding="utf-8") as outfile:
outfile.write(res)
outfile.close()
print(len(res))
if __name__ == '__main__':
Combine_txt()