pytorch做标准化利用transforms.Normalize(mean_vals, std_vals)，其中常用数据集的均值方差有：

if 'coco' in args.dataset: mean_vals = [0.471, 0.448, 0.408] std_vals = [0.234, 0.239, 0.242]elif 'imagenet' in args.dataset: mean_vals = [0.485, 0.456, 0.406] std_vals = [0.229, 0.224, 0.225]

计算自己数据集图像像素的均值方差：

import numpy as npimport cv2import random # calculate means and stdtrain_txt_path = './train_val_list.txt' CNum = 10000 # 挑选多少图片进行计算 img_h, img_w = 32, 32imgs = np.zeros([img_w, img_h, 3, 1])means, stdevs = [], [] with open(train_txt_path, 'r') as f: lines = f.readlines() random.shuffle(lines) # shuffle , 随机挑选图片 for i in tqdm_notebook(range(CNum)): img_path = os.path.join('./train', lines[i].rstrip().split()[0]) img = cv2.imread(img_path) img = cv2.resize(img, (img_h, img_w)) img = img[:, :, :, np.newaxis] imgs = np.concatenate((imgs, img), axis=3)# print(i) imgs = imgs.astype(np.float32)/255. for i in tqdm_notebook(range(3)): pixels = imgs[:,:,i,:].ravel() # 拉成一行 means.append(np.mean(pixels)) stdevs.append(np.std(pixels)) # cv2 读取的图像格式为BGR，PIL/Skimage读取到的都是RGB不用转means.reverse() # BGR --> RGBstdevs.reverse() print("normMean = {}".format(means))print("normStd = {}".format(stdevs))print('transforms.Normalize(normMean = {}, normStd = {})'.format(means, stdevs))

以上这篇计算pytorch标准化(Normalize)所需要数据集的均值和方差实例就是小编分享给大家的全部内容了，希望能给大家一个参考，也希望大家多多支持。