第一种写法,先读进来,再计算。比较耗内存。
-
import cv2
-
import numpy as np
-
import torch
-
-
startt = 700
-
CNum = 100 # 挑选多少图片进行计算
-
imgs=[]
-
for i in range(startt, startt+CNum):
-
img_path = (root_path, filename[i])
-
img = (img_path)
-
img = img[:, :, :, ]
-
((img))
-
-
torch_imgs = (imgs, dim=3)
-
-
means, stdevs = [], []
-
for i in range(3):
-
pixels = torch_imgs[:, :, i, :] # 拉成一行
-
((pixels))
-
((pixels))
-
-
# cv2 读取的图像格式为BGR,PIL/Skimage读取到的都是RGB不用转
-
() # BGR --> RGB
-
()
-
-
print("normMean = {}".format(means))
-
print("normStd = {}".format(stdevs))
第二种写法,读一张算一张,比较耗时:先过一遍计算出均值,再过一遍计算出方差。
-
import os
-
from PIL import Image
-
import as plt
-
import numpy as np
-
from import imread
-
-
startt = 4000
-
CNum = 1000 # 挑选多少图片进行计算
-
num = 1000 * 3200 * 1800 # 这里(3200,1800)是每幅图片的大小,所有图片尺寸都一样
-
-
imgs=[]
-
R_channel = 0
-
G_channel = 0
-
B_channel = 0
-
for i in range(startt, startt+CNum):
-
img = imread((root_path, filename[i]))
-
R_channel = R_channel + np.sum(img[:, :, 0])
-
G_channel = G_channel + np.sum(img[:, :, 1])
-
B_channel = B_channel + np.sum(img[:, :, 2])
-
-
R_mean = R_channel / num
-
G_mean = G_channel / num
-
B_mean = B_channel / num
-
-
R_channel = 0
-
G_channel = 0
-
B_channel = 0
-
for i in range(startt, startt+CNum):
-
img = imread((root_path, filename[i]))
-
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_std = (R_channel/num)
-
G_std = (G_channel/num)
-
B_std = (B_channel/num)
-
-
# R:65.045966 G:70.3931815 B:78.0636285
-
print("R_mean is %f, G_mean is %f, B_mean is %f" % (R_mean, G_mean, B_mean))
-
print("R_std is %f, G_std is %f, B_std is %f" % (R_std, G_std, B_std))
第三种写法,只需要遍历一次:在一轮循环中计算出x,x^2; 然后x'=sum(x)/N ,又有sum(x^2),根据下式:
S^2
= sum((x-x')^2 )/N = sum(x^2+x'^2-2xx')/N
= {sum(x^2) + sum(x'^2) - 2x'*sum(x) }/N
= {sum(x^2) + N*(x'^2) - 2x'*(N*x') }/N
= {sum(x^2) - N*(x'^2) }/N
= sum(x^2)/N - x'^2
S = sqrt( sum(x^2)/N - (sum(x)/N )^2 )
可以知道,只需要经过一次遍历,就可以计算出数据集的均值和方差。
-
import os
-
from PIL import Image
-
import as plt
-
import numpy as np
-
from import imread
-
-
startt = 5000
-
CNum = 1000 # 挑选多少图片进行计算
-
R_channel = 0
-
G_channel = 0
-
B_channel = 0
-
R_channel_square = 0
-
G_channel_square = 0
-
B_channel_square = 0
-
pixels_num = 0
-
-
imgs = []
-
for i in range(startt, startt+CNum):
-
img = imread((root_path, filename[i]))
-
h, w, _ =
-
pixels_num += h*w # 统计单个通道的像素数量
-
-
R_temp = img[:, :, 0]
-
R_channel += np.sum(R_temp)
-
R_channel_square += np.sum((R_temp, 2.0))
-
G_temp = img[:, :, 1]
-
G_channel += np.sum(G_temp)
-
G_channel_square += np.sum((G_temp, 2.0))
-
B_temp = img[:, :, 2]
-
B_channel = B_channel + np.sum(B_temp)
-
B_channel_square += np.sum((B_temp, 2.0))
-
-
R_mean = R_channel / pixels_num
-
G_mean = G_channel / pixels_num
-
B_mean = B_channel / pixels_num
-
-
"""
-
S^2
-
= sum((x-x')^2 )/N = sum(x^2+x'^2-2xx')/N
-
= {sum(x^2) + sum(x'^2) - 2x'*sum(x) }/N
-
= {sum(x^2) + N*(x'^2) - 2x'*(N*x') }/N
-
= {sum(x^2) - N*(x'^2) }/N
-
= sum(x^2)/N - x'^2
-
"""
-
-
R_std = (R_channel_square/pixels_num - R_mean*R_mean)
-
G_std = (G_channel_square/pixels_num - G_mean*G_mean)
-
B_std = (B_channel_square/pixels_num - B_mean*B_mean)
-
-
print("R_mean is %f, G_mean is %f, B_mean is %f" % (R_mean, G_mean, B_mean))
-
print("R_std is %f, G_std is %f, B_std is %f" % (R_std, G_std, B_std))