分类常用数据集的mean和std值及计算方法

计算数据集mean和std值的方法

with open(os.path.join(path,'train.txt'), 'r') as f:
    lines = f.readlines()
    for line in lines:
        index += 1
        a = os.path.join(line)
        num_imgs += 1
        img = cv2.imread(a[:-1])
        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()

分类常用数据集caltech101、caltech256、cub200、CIFAR10、CIFAR100、ImageNet、MiniImageNet的mean和std值计

caltech101_mean = [0.54870233, 0.53129903, 0.50505308]
catech101_std = [0.24957896, 0.24662743, 0.24811079]

caltech256_mean = [0.55201384, 0.53359979, 0.50502834]
caltech256_std = [0.24185446, 0.24112613, 0.24363275]

cub200_mean = [0.48560741861744905, 0.49941626449353244, 0.43237713785804116]
cub200_std = [0.2321024260764962, 0.22770540015765814, 0.2665100547329813]

CIFAR10_mean = (0.4914, 0.4822, 0.4465)
CIFAR10_std = (0.2023, 0.1994, 0.2010)

CIFAR100_mean = (0.5070751592371323, 0.48654887331495095, 0.4409178433670343)
CIFAR100_std = (0.2673342858792401, 0.2564384629170883, 0.27615047132568404)

mini_imagenet_mean = [0.485, 0.456, 0.406]
mini_imagenet_mean = [0.229, 0.224, 0.225]

imagenet_mean = [0.485, 0.456, 0.406],
imagenet_std = [0.229, 0.224, 0.225])