python生成lmdb格式的文件实例

yipeiwu_com6年前Python基础

在crnn训练的时候需要用到lmdb格式的数据集,下面是python生成lmdb个是数据集的代码,注意一定要在linux系统下,否则会读入图像的时候出问题,可能遇到的问题都在代码里面注释了,看代码即可。

#-*- coding:utf-8 -*-
 
import os
import lmdb#先pip install这个模块哦
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():
   txn.put(k, v)
 
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)所需要的磁盘空间的最小值,之前是1T,我改成了8g,否则会报磁盘空间不足,这个数字是字节
 
 cache = {}
 cnt = 1
 for i in xrange(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)#注意一定要在linux下,否则f.read就不可用了,就会输出这个信息
    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 输出目录
 outputPath = 'D:/ruanjianxiazai/tuxiangyangben/fengehou/train'#训练集和验证集要跑两遍这个程序,分两次生成
 
 path = "D:/ruanjianxiazai/tuxiangyangben/fengehou/chenguang/*.jpg"#将txt与jpg的都放在同一个文件里面
 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)
 

以上这篇python生成lmdb格式的文件实例就是小编分享给大家的全部内容了,希望能给大家一个参考,也希望大家多多支持【听图阁-专注于Python设计】。

相关文章

浅谈python中的getattr函数 hasattr函数

hasattr(object, name) 作用:判断对象object是否包含名为name的特性(hasattr是通过调用getattr(ojbect, name)是否抛出异常来实现的...

对Python使用mfcc的两种方式详解

对Python使用mfcc的两种方式详解

1、Librosa import librosa filepath = "/Users/birenjianmo/Desktop/learn/librosa/mp3/in.wav"...

python实现ipsec开权限实例

本文实例讲述了python实现ipsec开权限的方法。分享给大家供大家参考。具体实现方法如下: windows自带的命令行工具netsh ipsec static add filter不...

Python标准库之itertools库的使用方法

前言 因为最近事情不是很多,想写一些技术文章分享给大家,同时也对自己一段时间来碎片化接受的知识进行一下梳理,所谓写清楚才能说清楚,说清楚才能想清楚,就是这个道理了。 很多人都致力于把P...

python3.6使用pickle序列化class的方法

如下所示: from library.connecter.database.mongo import Op_Mongo a = pickle.dumps(Op_Mongo) #序列化...