OCR训练时，将txt文件和图片数据转为lmdb格式

create_lmdb_dataset.py

""" a modified version of CRNN torch repository https://github.com/bgshih/crnn/blob/master/tool/create_dataset.py """

import fire
import os
import lmdb
import cv2

import numpy as np


def checkImageIsValid(imageBin):
    if imageBin is None:
        return False
    imageBuf = np.frombuffer(imageBin, dtype=np.uint8)
    img = cv2.imdecode(imageBuf, cv2.IMREAD_GRAYSCALE)
    imgH, imgW = img.shape[0], img.shape[1]
    if imgH * imgW == 0:
        return False
    return True


def writeCache(env, cache):
    with env.