📊 MindSpore 常用视觉变换类总结表

Mindspore中变换有两种, 一种是类, 先创建一个变换类, 然后调用该类实现变换, 以类为基础的变化都是放在

mindspore.dataset.vision

下的; 另一种是Functional, 直接调用函数进行变换, functional变换是放在

import mindspore.dataset.vision as transforms

下的. 实际上这个差不多的, 因此后续不做区分

🧠 使用建议（Tips）

ViT, ImageNet:

mean = [0.485 * 255, 0.456 * 255, 0.406 * 255]
std = [0.229 * 255, 0.224 * 255, 0.225 * 255]
trans_train = [
    transforms.RandomCropDecodeResize(size=224,
                                      scale=(0.08, 1.0),
                                      ratio=(0.75, 1.333)),
    transforms.RandomHorizontalFlip(prob=0.5),
    transforms.Normalize(mean=mean, std=std),
    transforms.HWC2CHW()
]
trans_val = [
    transforms.Decode(),
    transforms.Resize(224 + 32),
    transforms.CenterCrop(224),
    transforms.Normalize(mean=mean, std=std),
    transforms.HWC2CHW()
]

Resnet+ Cifa10:

trans = []
if usage == "train":
    trans += [
        vision.RandomCrop((32, 32), (4, 4, 4, 4)),
        vision.RandomHorizontalFlip(prob=0.5)
    ]

trans += [
    vision.Resize(resize),
    vision.Rescale(1.0 / 255.0, 0.0),
    vision.Normalize([0.4914, 0.4822, 0.4465], [0.2023, 0.1994, 0.2010]),
    vision.HWC2CHW()
]