标签:std stdevs img means python print path os mean
首先先把数据集的图片路径保存在一个txt文件夹里面
- import os
- def generate(dir, label):
- listText = open( 'list.txt', 'a')
- for file in dir:
- fileType = os.path.split(file)
- if fileType[ 1] == '.txt':
- continue
- name = file + ' ' + str(int(label)) + '\n'
- listText.write(name)
- listText.close()
- outer_path = 'E:/lly/data/' # 这里是你的图片的目录
- if __name__ == '__main__':
- i = 1
- num = 0
- personlist = os.listdir(outer_path) # 列举文件夹
- personlist.sort()
- for person in personlist:
- personPath = outer_path+person + "/"
- fingerlist = os.listdir(personPath)
- fingerlist.sort()
- for finger in fingerlist:
- finallPATH=os.path.join(outer_path, person,finger)
- finallPATH=finallPATH.replace( '\\', '/')
- listText = open( 'image_list.txt', 'a')
- fileType = os.path.split(finallPATH)
- name = finallPATH+ '\n'
- listText.write(name)
- listText.close()
- i += 1
计算自己数据集的均值和方差:
- # -*- coding: utf-8 -*-**
- import numpy as np
- import cv2
- import random
- import os
- # calculate means and std 注意换行\n符号**
- # train.txt中每一行是图像的位置信息**
- path = 'C:/Users/lenovo/PycharmProjects/my/image_list.txt'
- means = [ 0, 0, 0]
- stdevs = [ 0, 0, 0]
- index = 1
- num_imgs = 0
- with open(path, 'r') as f:
- lines = f.readlines()
- # random.shuffle(lines)
- for line in lines:
- print(line)
- print( '{}/{}'.format(index, len(lines)))
- index += 1
- a = os.path.join(line)
- # print(a[:-1])
- num_imgs += 1
- img = cv2.imread(a[: -1])
- print(img, 22)
- img = np.asarray(img)
- img = img.astype(np.float32) / 255.
- for i in range( 3):
- means[i] += img[:, :, i].mean()
- stdevs[i] += img[:, :, i].std()
- print(num_imgs)
- means.reverse()
- stdevs.reverse()
- means = np.asarray(means) / num_imgs
- stdevs = np.asarray(stdevs) / num_imgs
- print( "normMean = {}".format(means))
- print( "normStd = {}".format(stdevs))
- print( 'transforms.Normalize(normMean = {}, normStd = {})'.format(means, stdevs))
参考:https://blog.csdn.net/weixin_38533896/article/details/85951903
标签:std,stdevs,img,means,python,print,path,os,mean 来源: https://blog.csdn.net/weixin_43955293/article/details/118441891
本站声明: 1. iCode9 技术分享网(下文简称本站)提供的所有内容,仅供技术学习、探讨和分享; 2. 关于本站的所有留言、评论、转载及引用,纯属内容发起人的个人观点,与本站观点和立场无关; 3. 关于本站的所有言论和文字,纯属内容发起人的个人观点,与本站观点和立场无关; 4. 本站文章均是网友提供,不完全保证技术分享内容的完整性、准确性、时效性、风险性和版权归属;如您发现该文章侵犯了您的权益,可联系我们第一时间进行删除; 5. 本站为非盈利性的个人网站,所有内容不会用来进行牟利,也不会利用任何形式的广告来间接获益,纯粹是为了广大技术爱好者提供技术内容和技术思想的分享性交流网站。