python多进程读图提取特征存npy

本文实例为大家分享了python多进程读图提取特征存npy的具体代码，供大家参考，具体内容如下

import multiprocessing
import os, time, random
import numpy as np
import cv2
import os
import sys
from time import ctime
import tensorflow as tf
 
image_dir = r"d:/sxl/处理图片/汉字分类/train10/"    #图像文件夹路径
data_type = 'test'
save_path = r'e:/sxl_programs/python/cnn/npy/'    #存储路径
data_name = 'img10'                #npy文件名
 
char_set = np.array(os.listdir(image_dir))      #文件夹名称列表
np.save(save_path+'imgshuzi10.npy',char_set)     #文件夹名称列表
char_set_n = len(char_set)              #文件夹列表长度
 
read_process_n = 1  #进程数
repate_n = 4     #随机移动次数
data_size = 1000000  #1个npy大小
 
shuffled = true   #是否打乱
 
#可以读取带中文路径的图
def cv_imread(file_path,type=0):
  cv_img=cv2.imdecode(np.fromfile(file_path,dtype=np.uint8),-1)
  # print(file_path)
  # print(cv_img.shape)
  # print(len(cv_img.shape))
  if(type==0):
    if(len(cv_img.shape)==3):
      cv_img = cv2.cvtcolor(cv_img, cv2.color_bgr2gray)
  return cv_img
 
#多个数组按同一规则打乱数据
def shuffleddata(features,labels):
  '''
  @description:随机打乱数据与标签，但保持数据与标签一一对应
  '''
  permutation = np.random.permutation(features.shape[0])
  shuffled_features = features[permutation,:] #多维
  shuffled_labels = labels[permutation]    #1维
  return shuffled_features,shuffled_labels
 
#函数功能：简单网格
#函数要求：1.无关图像大小；2.输入图像默认为灰度图;3.参数只有输入图像
#返回数据：1x64*64维特征
def getfeature(image):
 
  #图像大小归一化
  image = cv2.resize(image,(64,64))
  img_h = image.shape[0]
  img_w = image.shape[1]
 
  #定义特征向量
  feature = np.zeros(img_h*img_w,dtype=np.int16)
 
  for h in range(img_h):
    for w in range(img_w):
      feature[h*img_h+w] = image[h,w]
 
  return feature
 
# 写数据进程执行的代码:
def read_image_to_queue(queue):
  print('process to write: %s' % os.getpid())
  for j,dirname in enumerate(char_set): # dirname 是文件夹名称
    label = np.where(char_set==dirname)[0][0]   #文件夹名称对应的下标序号
    print('序号：'+str(j),'读 '+dirname+' 文件夹...时间：',ctime() )
    for parent,_,filenames in os.walk(os.path.join(image_dir,dirname)):
      for filename in filenames:
        if(filename[-4:]!='.jpg'):
          continue
        image = cv_imread(os.path.join(parent,filename),0)
 
        # cv2.imshow(dirname,image)
        # cv2.waitkey(0)
        queue.put((image,label))
  
  for i in range(read_process_n):
    queue.put((none,-1))
 
  print('读图结束!')
  return true
    
# 读数据进程执行的代码:
def extract_feature(queue,lock,count):
  '''
  @description:从队列中取出图片进行特征提取
  @queue:先进先出队列
   lock：锁，在计数时上锁，防止冲突
   count:计数
  '''
 
  print('process %s start reading...' % os.getpid())
 
  global data_n
  features = [] #存放提取到的特征
  labels = [] #存放标签
  flag = true #标志着进程是否结束
  while flag:
    image,label = queue.get() #从队列中获取图像和标签
 
    if len(features) >= data_size or label == -1:  #特征数组的长度大于指定长度，则开始存储
 
      array_features = np.array(features) #转换成数组
      array_labels = np.array(labels)
 
      array_features,array_labels = shuffleddata(array_features,array_labels) #打乱数据
      
      lock.acquire()  # 锁开始
 
      # 拆分数据为训练集，测试集
      split_x = int(array_features.shape[0] * 0.8)
      train_data, test_data = np.split(array_features, [split_x], axis=0)   # 拆分特征数据集
      train_labels, test_labels = np.split(array_labels, [split_x], axis=0) # 拆分标签数据集
 
      count.value += 1  #下标计数加1
      str_features_name_train = data_name+'_features_train_'+str(count.value)+'.npy'
      str_labels_name_train = data_name+'_labels_train_'+str(count.value)+'.npy'
      str_features_name_test = data_name+'_features_test_'+str(count.value)+'.npy'
      str_labels_name_test = data_name+'_labels_test_'+str(count.value)+'.npy'
 
      lock.release()  # 锁释放
 
      np.save(save_path+str_features_name_train,train_data)
      np.save(save_path+str_labels_name_train,train_labels)
      np.save(save_path+str_features_name_test,test_data)
      np.save(save_path+str_labels_name_test,test_labels)
      print(os.getpid(),'save:',str_features_name_train)
      print(os.getpid(),'save:',str_labels_name_train)
      print(os.getpid(),'save:',str_features_name_test)
      print(os.getpid(),'save:',str_labels_name_test)
      features.clear()
      labels.clear()
 
    if label == -1:
      break
 
    # 获取特征向量，传入灰度图
    feature = getfeature(image)
    features.append(feature)
    labels.append(label)
 
    # # 随机移动4次
    # for itime in range(repate_n):
    #   rmovedimage = randommoveimage(image)
    #   feature = simplegridfeature(rmovedimage) # 简单网格
    #   features.append(feature)
    #   labels.append(label)
  
  print('process %s is done!' % os.getpid())
 
if __name__=='__main__':
  time_start = time.time() # 开始计时
 
  # 父进程创建queue，并传给各个子进程：
  image_queue = multiprocessing.queue(maxsize=1000) #队列
  lock = multiprocessing.lock()           #锁
  count = multiprocessing.value('i',0)        #计数
 
  #将图写入队列进程
  write_sub_process = multiprocessing.process(target=read_image_to_queue, args=(image_queue,))
 
  read_sub_processes = []              #读图子线程
  for i in range(read_process_n):
    read_sub_processes.append(
      multiprocessing.process(target=extract_feature, args=(image_queue,lock,count))
    )
 
  # 启动子进程pw，写入:
  write_sub_process.start()
 
  # 启动子进程pr，读取:
  for p in read_sub_processes:
    p.start()
 
  # 等待进程结束:
  write_sub_process.join()
  for p in read_sub_processes:
    p.join()
 
  time_end=time.time()
  time_h=(time_end-time_start)/3600
  print('用时：%.6f 小时'% time_h)
  print ("读图提取特征存npy,运行结束！")

以上就是本文的全部内容，希望对大家的学习有所帮助，也希望大家多多支持。