Function build_transform

EfficientViT/classification/data/datasets.py:102–140

(is_train, args)

def build_transform(is_train, args):
    resize_im = args.input_size > 32
    if is_train:
        # this should always dispatch to transforms_imagenet_train
        transform = create_transform(
            input_size=args.input_size,
            is_training=True,
            color_jitter=args.color_jitter,
            auto_augment=args.aa,
            interpolation=args.train_interpolation,
            re_prob=args.reprob,
            re_mode=args.remode,
            re_count=args.recount,
        )
        if not resize_im:
            # replace RandomResizedCropAndInterpolation with
            # RandomCrop
            transform.transforms[0] = transforms.RandomCrop(
                args.input_size, padding=4)
        return transform

    t = []
    if args.finetune:
        t.append(
            transforms.Resize((args.input_size, args.input_size),
                                interpolation=3)
        )
    else:
        if resize_im:
            size = int((256 / 224) * args.input_size)
            t.append(
                # to maintain same ratio w.r.t. 224 images
                transforms.Resize(size, interpolation=3),
            )
            t.append(transforms.CenterCrop(args.input_size))
    
    t.append(transforms.ToTensor())
    t.append(transforms.Normalize(IMAGENET_DEFAULT_MEAN, IMAGENET_DEFAULT_STD))
    return transforms.Compose(t)