二、OCR训练时，将txt文件和图片数据转为lmdb文件格式

---

前言

随着人工智能的不断发展，机器学习这门技术也越来越重要，本文就介绍OCR训练前ldmb文件制作的基础内容。

---

提示：以下是本篇文章正文内容，下面案例可供参考

一、背景？

示例：是基于ocr训练而作。

二、直接上内容

1.代码

代码如下（示例）：

# -*- coding:utf-8 -*-

import os
import lmdb  # ?pip install?????
import cv2
import glob  #????????????
import numpy as np


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


def writeCache(env, cache):
    with env.begin(write=True) as txn:
        # for k, v in cache.iteritems(): #python2
        for k, v in cache.items():  #python3
            txn.put(k.encode(), str(v).encode())


def createDataset(outputPath, imagePathList, labelList, lexiconList=None, checkValid=True):
    """
    Create LMDB dataset for CRNN training.
# ARGS:
        outputPath    : LMDB output path
        imagePathList : list of image path
        labelList     : list of corresponding groundtruth texts
        lexiconList   : (optional) list of lexicon lists
        checkValid    : if true, check the validity of every image
    """
    # print (len(imagePathList) , len(labelList))
    assert (len(imagePathList) == len(labelList))
    nSamples = len(imagePathList)
    print('...................')
    env = lmdb.open(outputPath, map_size=8589934592)  # 1099511627776)????????????????1T?????8g???????????????????

    cache = {
    }
    cnt = 1
    for i in range(nSamples):
        imagePath = imagePathList[i]
        label = labelList[i]
        if not os.path.exists(imagePath):
            print('%s does not exist' % imagePath)
            continue
        with open(imagePath, 'r') as f:
            imageBin = f.read()
        if checkValid:
            if not checkImageIsValid(imageBin):
                print('%s is not a valid image' % imagePath)  # ??????linux????f.read??????????????
                continue

        imageKey = 'image-%09d' % cnt
        labelKey = 'label-%09d' % cnt
        cache[imageKey] = imageBin
        cache[labelKey] = label
        if lexiconList:
            lexiconKey = 'lexicon-%09d' % cnt
            cache[lexiconKey] = ' '.join(lexiconList[i])
        if cnt % 1000 == 0:
            writeCache(env, cache)
            cache = {
    }
            print('Written %d / %d' % (cnt, nSamples))
        cnt += 1
    nSamples = cnt - 1
    cache['num-samples'] = str(nSamples)
    writeCache(env, cache)
    print('Created dataset with %d samples' % nSamples)


def read_text(path):
    with open(path) as f:
        text = f.read()
    text = text.strip()

    return text


if __name__ == '__main__':
    # lmdb ????
    outputPath = r'E:\enducate\test_paper\Train_code\train'  # ?????????????????????

    path = r"E:\enducate\test_paper\Train_code\data22222\*.png"  # ?txt?jpg???????????
    imagePathList = glob.glob(path)
    print('------------', len(imagePathList), '------------')

    imgLabelLists = []
    for p in imagePathList:
        try:
            imgLabelLists.append((p, read_text(p.replace('.jpg', '.txt'))))
        except:
            continue

    # imgLabelList = [ (p, read_text(p.replace('.jpg', '.txt'))) for p in imagePathList]
    # sort by labelList
    imgLabelList = sorted(imgLabelLists, key=lambda x: len(x[1]))
    imgPaths = [p[0] for p in imgLabelList]
    txtLists = [p[1] for p in imgLabelList]

    createDataset(outputPath, imgPaths, txtLists, lexiconList=None, checkValid=True)
    

2.文件说明

第一种文件格式
图片路径和txt标签文件共存。（1张图片对应1个txt标签文件）

txt文件和图片是放在一个文件夹的。

---

第二种文件格式如下：
文件有多张图片和1个txt文件组成，其中txt文件是包括所有图片的标签。
格式为：图片路径名+\t+标签。

// A code block
var foo = 'bar';

// An highlighted block

""" 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.begin(write=True) as txn:
        for k, v in cache.items():
            txn.put(k, v)


def createDataset(inputPath, gtFile, outputPath, checkValid=True):
    """
    Create LMDB dataset for training and evaluation.
    ARGS:
        inputPath  : input folder path where starts imagePath
        outputPath : LMDB output path
        gtFile     : list of image path and label
        checkValid : if true, check the validity of every image
    """
    os.makedirs(outputPath, exist_ok=True)
    env = lmdb.open(outputPath, map_size=1099511627776)
    cache = {
    }
    cnt = 1

    with open(gtFile, 'r', encoding='utf-8') as data:
        datalist = data.readlines()

    nSamples = len(datalist)
    for i in range(nSamples):
        imagePath, label = datalist[i].strip('\n').split('\t')
        # imagePath = os.path.join(inputPath, imagePath)

        # # only use alphanumeric data
        # if re.search('[^a-zA-Z0-9]', label):
        #     continue

        if not os.path.exists(imagePath):
            print('%s does not exist' % imagePath)
            continue
        with open(imagePath, 'rb') as f:
            imageBin = f.read()
        if checkValid:
            try:
                if not checkImageIsValid(imageBin):
                    print('%s is not a valid image' % imagePath)
                    continue
            except:
                print('error occured', i)
                with open(outputPath + '/error_image_log.txt', 'a') as log:
                    log.write('%s-th image data occured error\n' % str(i))
                continue

        imageKey = 'image-%09d'.encode() % cnt
        labelKey = 'label-%09d'.encode() % cnt
        cache[imageKey] = imageBin
        cache[labelKey] = label.encode()

        if cnt % 1000 == 0:
            writeCache(env, cache)
            cache = {
    }
            print('Written %d / %d' % (cnt, nSamples))
        cnt += 1
    nSamples = cnt-1
    cache['num-samples'.encode()] = str(nSamples).encode()
    writeCache(env, cache)
    print('Created dataset with %d samples' % nSamples)


if __name__ == '__main__':
    fire.Fire(createDataset)

# python create_lmdb_dataset.py --inputPath /data2/ --gtFile /data2/meterdataset/digital_dataset/otherdataset/1030_data/collect_val.txt --outputPath /data2/meterdataset/digital_dataset/otherdataset/1030_data/2021-0507-result/val

第二个运行说明：
> 输入路径：inputPath 操作的文件夹
txt文件： gtFile
ldmb输出的文件路径： outputPath

// An highlighted block
python create_lmdb_dataset.py --inputPath /data2/ --gtFile /data2/enducation/paper_recog_total/train-paper-recog/Recognization/deep-text-recognition-SHENG/data/text_recog/txt4val/img_gt/gt.txt --outputPath /data2/enducation/paper_recog_total/train-paper-recog/Recognization/deep-text-recognition-SHENG/data/val