计算数据集均值方差

参考:

https://blog.csdn.net/weixin_41765699/article/details/100118660

对于数据集获取简单进行修改 

import os
import cv2
import numpy as np

def searchDirFile(rootDir, list_, path_, endswith_):
    for dir_or_file in os.listdir(rootDir):
        filePath = os.path.join(rootDir, dir_or_file)
        if os.path.isfile(filePath):
            if os.path.basename(filePath).endswith(endswith_):
                temp = filePath.split('/')[-2]
                list_.append(temp)
                path_.append(filePath)
            else:
                continue
        elif os.path.isdir(filePath):
            searchDirFile(filePath, list_, path_, endswith_)
        else:
            print('not file and dir '+os.path.basename(filePath))

path = "/home/mydata"
namelist = []
pathlist = []
endswith = 'Texture_8Bit.png'
searchDirFile(path, namelist, pathlist, endswith)

R_channel = 0
G_channel = 0
B_channel = 0
for idx in range(len(pathlist)):
    filename = pathlist[idx]
    img = cv2.imread(filename) / 255.0
    R_channel = R_channel + np.sum(img[:, :, 0])
    G_channel = G_channel + np.sum(img[:, :, 1])
    B_channel = B_channel + np.sum(img[:, :, 2])

# 这里（512,512）是每幅图片的大小，所有图片尺寸都一样
num = len(pathlist) * 2064 * 1544
R_mean = R_channel / num
G_mean = G_channel / num
B_mean = B_channel / num

print("R_mean is %f, G_mean is %f, B_mean is %f" % (R_mean, G_mean, B_mean))
R_channel = 0
G_channel = 0
B_channel = 0
for idx in range(len(pathlist)):
    filename = pathlist[idx]
    img = cv2.imread(filename) / 255.0
    R_channel = R_channel + np.sum((img[:, :, 0] - R_mean) ** 2)
    G_channel = G_channel + np.sum((img[:, :, 1] - G_mean) ** 2)
    B_channel = B_channel + np.sum((img[:, :, 2] - B_mean) ** 2)

R_var = np.sqrt(R_channel / num)
G_var = np.sqrt(G_channel / num)
B_var = np.sqrt(B_channel / num)

print("R_var is %f, G_var is %f, B_var is %f" % (R_var, G_var, B_var))

 

上面必须图片大小一样,速度很慢

如果图像大小不一样,且要求速度较快:

https://blog.csdn.net/PanYHHH/article/details/107896526

https://zhuanlan.zhihu.com/p/275742390

通过pytorch 每次计算每张图的均值方差,直接计入总和,然后除以数据集数目