transforms.RandomCrop(size, padding=None, pad_if_needed=False, fill=0, padding_mode='constant')size：期望随机裁剪之后输出的尺寸padding：填充边界的值，单个（int）,两个（[左/右，上/下]），四个（各个边界）pad_if_needed :bool值，避免数组越界fill:填充padding_

transforms.Resize(size, interpolation=<InterpolationMode.BILINEAR: 'bilinear'>, max_size=None, antialias=None) antialias :如果img是PIL图像，则忽略该标志，并始终为True。如果img是张量，则默认情况下该标志为Falseimport torchvision.t

transforms.RandomAffine(degrees, translate=None, scale=None, shear=None, interpolation=<InterpolationMode.NEAREST: 'nearest'>, fill=0, fillcolor=None, resample=None, center=None)degrees：可从中选择的度数

transforms.RandomRotation(degrees, interpolation=<InterpolationMode.NEAREST: 'nearest'>, expand=False, center=None, fill=0, resample=None)expand:可选扩展标志。如果为true，则扩展输出，使其足够大，以容纳整个旋转图像。如果为false或省略，

transforms.RandomHorizontalFlip(p=0.5)import torchvision.transforms as transformfrom PIL import Imageimport matplotlib.pyplot as pltimport numpy as npimport torchimg0=Image.open('lin-xiao-xun-000003.j