您好,登錄后才能下訂單哦!
這篇文章將為大家詳細講解有關python中多進程讀圖提取特征存npy的示例分析,小編覺得挺實用的,因此分享給大家做個參考,希望大家閱讀完這篇文章后可以有所收獲。
具體內容如下
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/處理圖片/漢字分類/train10/" #圖像文件夾路徑 data_type = 'test' save_path = r'E:/sxl_Programs/Python/CNN/npy/' #存儲路徑 data_name = 'Img10' #npy文件名 char_set = np.array(os.listdir(image_dir)) #文件夾名稱列表 np.save(save_path+'ImgShuZi10.npy',char_set) #文件夾名稱列表 char_set_n = len(char_set) #文件夾列表長度 read_process_n = 1 #進程數 repate_n = 4 #隨機移動次數 data_size = 1000000 #1個npy大小 shuffled = True #是否打亂 #可以讀取帶中文路徑的圖 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 #多個數組按同一規則打亂數據 def ShuffledData(features,labels): ''' @description:隨機打亂數據與標簽,但保持數據與標簽一一對應 ''' permutation = np.random.permutation(features.shape[0]) shuffled_features = features[permutation,:] #多維 shuffled_labels = labels[permutation] #1維 return shuffled_features,shuffled_labels #函數功能:簡單網格 #函數要求:1.無關圖像大小;2.輸入圖像默認為灰度圖;3.參數只有輸入圖像 #返回數據:1x64*64維特征 def GetFeature(image): #圖像大小歸一化 image = cv2.resize(image,(64,64)) img_h = image.shape[0] img_w = image.shape[1] #定義特征向量 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 # 寫數據進程執行的代碼: def read_image_to_queue(queue): print('Process to write: %s' % os.getpid()) for j,dirname in enumerate(char_set): # dirname 是文件夾名稱 label = np.where(char_set==dirname)[0][0] #文件夾名稱對應的下標序號 print('序號:'+str(j),'讀 '+dirname+' 文件夾...時間:',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('讀圖結束!') return True # 讀數據進程執行的代碼: def extract_feature(queue,lock,count): ''' @description:從隊列中取出圖片進行特征提取 @queue:先進先出隊列 lock:鎖,在計數時上鎖,防止沖突 count:計數 ''' print('Process %s start reading...' % os.getpid()) global data_n features = [] #存放提取到的特征 labels = [] #存放標簽 flag = True #標志著進程是否結束 while flag: image,label = queue.get() #從隊列中獲取圖像和標簽 if len(features) >= data_size or label == -1: #特征數組的長度大于指定長度,則開始存儲 array_features = np.array(features) #轉換成數組 array_labels = np.array(labels) array_features,array_labels = ShuffledData(array_features,array_labels) #打亂數據 lock.acquire() # 鎖開始 # 拆分數據為訓練集,測試集 split_x = int(array_features.shape[0] * 0.8) train_data, test_data = np.split(array_features, [split_x], axis=0) # 拆分特征數據集 train_labels, test_labels = np.split(array_labels, [split_x], axis=0) # 拆分標簽數據集 count.value += 1 #下標計數加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() # 鎖釋放 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 # 獲取特征向量,傳入灰度圖 feature = GetFeature(image) features.append(feature) labels.append(label) # # 隨機移動4次 # for itime in range(repate_n): # rMovedImage = randomMoveImage(image) # feature = SimpleGridFeature(rMovedImage) # 簡單網格 # features.append(feature) # labels.append(label) print('Process %s is done!' % os.getpid()) if __name__=='__main__': time_start = time.time() # 開始計時 # 父進程創建Queue,并傳給各個子進程: image_queue = multiprocessing.Queue(maxsize=1000) #隊列 lock = multiprocessing.Lock() #鎖 count = multiprocessing.Value('i',0) #計數 #將圖寫入隊列進程 write_sub_process = multiprocessing.Process(target=read_image_to_queue, args=(image_queue,)) read_sub_processes = [] #讀圖子線程 for i in range(read_process_n): read_sub_processes.append( multiprocessing.Process(target=extract_feature, args=(image_queue,lock,count)) ) # 啟動子進程pw,寫入: write_sub_process.start() # 啟動子進程pr,讀取: for p in read_sub_processes: p.start() # 等待進程結束: write_sub_process.join() for p in read_sub_processes: p.join() time_end=time.time() time_h=(time_end-time_start)/3600 print('用時:%.6f 小時'% time_h) print ("讀圖提取特征存npy,運行結束!")
關于“python中多進程讀圖提取特征存npy的示例分析”這篇文章就分享到這里了,希望以上內容可以對大家有一定的幫助,使各位可以學到更多知識,如果覺得文章不錯,請把它分享出去讓更多的人看到。
免責聲明:本站發布的內容(圖片、視頻和文字)以原創、轉載和分享為主,文章觀點不代表本網站立場,如果涉及侵權請聯系站長郵箱:is@yisu.com進行舉報,并提供相關證據,一經查實,將立刻刪除涉嫌侵權內容。