How do you transform validation data in PyTorch?

1

When I was looking for tutorials on how to perform transformations, I noticed that some people do transformations like this: first, they resize, and then they center crop.

val_transform = transforms.Compose([
    transforms.Resize(size=(230)),
    transforms.CenterCrop(img_size),
    transforms.ToTensor()
])

Is it necessary to do it like this, or can we just resize?

train_transform = transforms.Compose([
    transforms.RandomResizedCrop(img_size, scale=(0.7, 1)),
    transforms.RandomHorizontalFlip(),  
    transforms.RandomVerticalFlip(),    
    transforms.RandomRotation(7),
    transforms.ToTensor()
])

val_transform = transforms.Compose([
    transforms.Resize(size=(img_size)),
    transforms.ToTensor()
])